2 Commits
Author SHA1 Message Date
阿白叔andClaude Opus 4.7 dfa84743f9 docs: add product project spec, distinguish date vs semver tags
Distill task_assistant's COLLABORATION_AND_RELEASE_WORKFLOW into a
team-wide product project spec and clarify when each tag style applies.

- Add docs/08-product-spec.md: semver triplet (internal/display/tag),
  manifest schema, dist-channel separation, user-confirmed update
  flow, feedback/log handling, sensitive-info scan, release flow,
  minimum delivery checklist
- docs/03-git-workflow.md: split tagging into spec (YYYYMMDD) vs
  product (vX.Y.Z) sections, link to 08
- README.md, CLAUDE.md, AGENTS.md: update versioning section and doc
  index to reference 08

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-20 14:45:28 +08:00
阿白叔andClaude Opus 4.7 154f592f3c docs: split language by audience, add Codex / AGENTS.md spec
Language policy: Chinese for human-facing files (README, docs/,
human-fillable templates), English for AI-facing files (CLAUDE.md,
AGENTS.md, AI templates). Commits / PRs / branches / tags stay
English.

- Translate docs/01-06 to Chinese
- Translate README.md, PR / handoff / project README templates to Chinese
- Drop README.en.md (redundant once language policy is explicit)
- Rewrite CLAUDE.md and CLAUDE.md.template under the new policy
- Add AGENTS.md (root) and templates/AGENTS.md.template for Codex
- Add docs/07-codex.md covering Codex usage and AGENTS.md / CLAUDE.md sync rules

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-20 09:44:15 +08:00
17 changed files with 1260 additions and 694 deletions

No files matched your search

+103
View File
@@ -0,0 +1,103 @@
# AGENTS.md — team-guide
Context for AI coding agents (Codex CLI, Codex in IDEs, other
AGENTS.md-aware tools) working in this repository.
> Sister file: `CLAUDE.md` (read by Claude Code). The two files cover
> the same ground — keep them in sync. Whichever tool runs reads its
> own file.
## Project
This repo holds our team's working agreements (1–3 person team,
AI-assisted "vibe coding" development). It is **documentation, not code**.
There is no build, test, or lint step. Acceptance is "a human can read
the change and would have written the same."
## Editing rules
When editing files in this repo:
- One rule per bullet. If a rule needs a paragraph of justification,
split the rule out and put the justification on a `**Why:**` line.
- Lead with the rule, then `**Why:**`, then `**How to apply:**` only
when non-obvious. Skip them when the rule speaks for itself.
- No emoji. No decorative headers. No "🚀 Getting started!" energy.
- Keep each doc under ~150 lines. Past that, split.
- Examples beat prose. A 3-line code block beats a paragraph of
description.
## Language policy
- **Human-facing**: Chinese. `README.md`, `docs/*.md`, and the
human-fillable templates (`templates/README.md.template`,
`templates/PR_DESCRIPTION.template.md`,
`templates/HANDOFF_CHECKLIST.template.md`) are in Chinese.
- **AI-facing**: English. `CLAUDE.md`, `AGENTS.md`,
`templates/CLAUDE.md.template`, `templates/AGENTS.md.template`, and
`docs/07-codex.md`'s code blocks / examples are in English.
- **Commit messages, PR titles, branch names, tag annotations**: English.
AI tools and search work better on English Git metadata.
If you're an agent and you're about to write Chinese into a file the
human would never read, stop — you have the wrong file.
## What goes where
| Topic | File |
| ---------------------------------------------- | --------------------------------- |
| Human + AI work split | `docs/01-vibe-coding.md` |
| Claude Code config (CLAUDE.md, hooks, memory) | `docs/02-claude-code.md` |
| Branches, commits, PRs, tagging | `docs/03-git-workflow.md` |
| Skill catalog, planning cadence | `docs/04-skills-and-planning.md` |
| Naming, comments, code style | `docs/05-code-style.md` |
| Task packages, handoff checklists | `docs/06-handoff.md` |
| Codex usage and AGENTS.md conventions | `docs/07-codex.md` |
| Product project spec (semver, manifest, build) | `docs/08-product-spec.md` |
## What NOT to do
- Don't add a doc for a rule we've used once. Wait until it's bitten
twice — then write it.
- Don't write process for processes' sake. If nobody would read or
follow it, don't write it.
- Don't quote external sources at length (license / copyright). Link
instead.
- Don't translate `CLAUDE.md` / `AGENTS.md` into Chinese. They're for
AI tools.
- Don't translate Chinese docs into English "for completeness." Pick
one language per file and stick with it.
## Commits
- Format: `<area>: <imperative summary under 60 chars>`. Examples:
`git-workflow: clarify branch naming`, `docs: add Codex section`.
- One topic per commit. "and" in the summary means split it.
- Always include the `Co-Authored-By` trailer when AI-assisted.
## Versioning / releases
Two tag styles, by project type:
- **Spec repos** (this one, other agreement docs) — date tags:
`YYYYMMDD`, with `-N` suffix for same-day reissues (`20260520-2`).
Tag from `main`.
- **Product repos** (task_assistant, authoring-tool — anything with
versioned artifacts shipped to users) — semver: `v<x.y.z>`. Tag from
`dev`. Internal version (`0.2.4`), display version (`V0.2.4`), and
tag (`v0.2.4`) must stay in sync. See `docs/08-product-spec.md` for
the full ruleset (manifest, release-field sync list, sensitive-info
scan, minimum delivery checklist).
Universal rules:
- Annotated tags only. Tag messages summarize what changed.
- Tags are immutable once pushed. If a tag is wrong, cut a new one.
- This repo is a spec repo, so tagging here means a date tag.
## Working directory expectations
- The repo is small (10–20 files). You can `Read` everything before
acting; you don't need to spawn a sub-agent for exploration.
- Do not introduce `package.json`, `Makefile`, CI configs, or other
toolchain files unless explicitly asked. This is a docs repo.
+91 -28
View File
@@ -1,46 +1,109 @@
# CLAUDE.md — team-guide
This repo holds our team's working agreements. When editing it, behave like
a careful technical writer, not a coder.
Context for Claude Code working in this repository.
## Context
> Sister file: `AGENTS.md` (read by Codex). The two files cover the
> same ground — keep them in sync. Whichever tool runs reads its own
> file. See `docs/07-codex.md` for the sync rules.
- **Audience**: 1–3 person team, AI-assisted development ("vibe coding").
- **Language**: English. All docs, all commits, all PR titles.
- **Tone**: short, declarative, opinionated. No fluff, no hedging, no marketing voice.
## Project
This repo holds our team's working agreements (1–3 person team,
AI-assisted "vibe coding" development). It is **documentation, not code**.
There is no build, test, or lint step. Acceptance is "a human can read
the change and would have written the same."
## Editing rules
- One rule per bullet. If a rule needs a paragraph of justification, split
the rule out and put the justification in a *Why* line.
- Lead with the rule, then `**Why:**`, then `**How to apply:**` only when
the rule is non-obvious. Skip them when the rule speaks for itself.
When editing files in this repo:
- One rule per bullet. If a rule needs a paragraph of justification,
split the rule out and put the justification on a `**Why:**` line.
- Lead with the rule, then `**Why:**`, then `**How to apply:**` only
when non-obvious. Skip them when the rule speaks for itself.
- No emoji. No decorative headers. No "🚀 Getting started!" energy.
- Keep each doc under ~150 lines. If it's growing past that, the doc is
probably two docs.
- Examples beat prose. Prefer a 3-line code block over a paragraph
describing the code.
- Keep each doc under ~150 lines. Past that, split.
- Examples beat prose. A 3-line code block beats a paragraph of
description.
## Language policy
- **Human-facing**: Chinese. `README.md`, `docs/*.md`, and the
human-fillable templates (`templates/README.md.template`,
`templates/PR_DESCRIPTION.template.md`,
`templates/HANDOFF_CHECKLIST.template.md`) are in Chinese.
- **AI-facing**: English. `CLAUDE.md`, `AGENTS.md`,
`templates/CLAUDE.md.template`, `templates/AGENTS.md.template`. Code
blocks and command examples inside Chinese docs also stay English.
- **Commit messages, PR titles, branch names, tag annotations**: English.
AI tools and search work better on English Git metadata.
If you're an agent and you're about to write Chinese into a file the
human would never read (or vice versa), stop — you have the wrong file.
## What goes where
| If you're writing about… | Put it in… |
| ---------------------------------------- | -------------------------------- |
| How humans and AI split a task | `docs/01-vibe-coding.md` |
| Claude Code config (CLAUDE.md, hooks…) | `docs/02-claude-code.md` |
| Branches, commits, PRs | `docs/03-git-workflow.md` |
| Which skills to install, planning cadence| `docs/04-skills-and-planning.md` |
| Naming, comments, file structure | `docs/05-code-style.md` |
| Task packages, handoff between members | `docs/06-handoff.md` |
| Topic | File |
| ---------------------------------------------- | --------------------------------- |
| Human + AI work split | `docs/01-vibe-coding.md` |
| Claude Code config (CLAUDE.md, hooks, memory) | `docs/02-claude-code.md` |
| Branches, commits, PRs, tagging | `docs/03-git-workflow.md` |
| Skill catalog, planning cadence | `docs/04-skills-and-planning.md` |
| Naming, comments, code style | `docs/05-code-style.md` |
| Task packages, handoff checklists | `docs/06-handoff.md` |
| Codex usage and AGENTS.md conventions | `docs/07-codex.md` |
| Product project spec (semver, manifest, build) | `docs/08-product-spec.md` |
## What NOT to do
- Don't add a doc for a rule we've used once. Wait until it's bitten us
- Don't add a doc for a rule we've used once. Wait until it's bitten
twice — then write it.
- Don't write process for processes' sake. If nobody would read or follow
it, don't write it.
- Don't quote external sources at length (license/copyright). Link instead.
- Don't write process for processes' sake. If nobody would read or
follow it, don't write it.
- Don't quote external sources at length (license / copyright). Link
instead.
- Don't translate `CLAUDE.md` / `AGENTS.md` into Chinese. They're for
AI tools.
- Don't translate Chinese docs into English "for completeness." Pick
one language per file and stick with it.
## Commits
- Commit message: `<area>: <imperative summary>` — e.g. `git-workflow: clarify branch naming`.
- One topic per commit. If a commit message has "and" in it, it's two commits.
- Format: `<area>: <imperative summary under 60 chars>`. Examples:
`git-workflow: clarify branch naming`, `docs: add Codex section`.
- One topic per commit. "and" in the summary means split it.
- Always include the `Co-Authored-By` trailer when AI-assisted.
## Versioning / releases
Two tag styles, by project type:
- **Spec repos** (this one, other agreement docs) — date tags:
`YYYYMMDD`, with `-N` suffix for same-day reissues (`20260520-2`).
Tag from `main`.
- **Product repos** (task_assistant, authoring-tool — anything with
versioned artifacts shipped to users) — semver: `v<x.y.z>`. Tag from
`dev`. Internal version (`0.2.4`), display version (`V0.2.4`), and
tag (`v0.2.4`) must stay in sync. See `docs/08-product-spec.md` for
the full ruleset (manifest, release-field sync list, sensitive-info
scan, minimum delivery checklist).
Universal rules:
- Annotated tags only. Tag messages summarize what changed.
- Tags are immutable once pushed. If a tag is wrong, cut a new one.
- This repo is a spec repo, so tagging here means a date tag.
## Sync with AGENTS.md
If you change this file, update `AGENTS.md` to match (and vice versa).
The two files describe the same project to different tools — drift
breaks one of them silently. Reviewer should block PRs that touch only
one side.
## Working directory expectations
- The repo is small (≈20 files). You can `Read` everything before
acting; you don't need to spawn a sub-agent for exploration.
- Do not introduce `package.json`, `Makefile`, CI configs, or other
toolchain files unless explicitly asked. This is a docs repo.
-58
View File
@@ -1,58 +0,0 @@
# team-guide
> 中文版:[README.md](README.md)
Working agreements for our team's AI-assisted ("vibe coding") development.
Small team, English docs, opinionated but light.
## What this repo is
A single source of truth for **how we work**, not what we build. It covers:
- How we use Claude Code (CLAUDE.md, permissions, hooks, memory, skills)
- How we collaborate with AI when writing code (vibe coding norms)
- Git workflow (branches, commits, PRs, review)
- Skill management and project planning rhythm
- Code & deliverable style (naming, comments, READMEs, task packages, handoffs)
Every doc is short. If a rule needs more than half a page to justify, it
probably isn't a rule yet — it's a discussion.
## Layout
```
team-guide/
├── README.md ← you are here
├── CLAUDE.md ← context Claude Code loads when working in this repo
├── docs/
│ ├── 01-vibe-coding.md ← how humans + AI split the work
│ ├── 02-claude-code.md ← CLAUDE.md / permissions / hooks / memory / skills
│ ├── 03-git-workflow.md ← branches, commits, PRs, review
│ ├── 04-skills-and-planning.md ← skill catalog + planning cadence
│ ├── 05-code-style.md ← naming, comments, structure
│ └── 06-handoff.md ← task packages, handoff checklists
└── templates/
├── CLAUDE.md.template
├── README.md.template
├── PR_DESCRIPTION.template.md
└── HANDOFF_CHECKLIST.template.md
```
## How to use it
1. **New team member** — read `docs/01-vibe-coding.md` and `docs/03-git-workflow.md` first. The rest is reference.
2. **Starting a new project** — copy the templates from `templates/` into the new repo and fill them in. Drop a top-level `CLAUDE.md` that points back here.
3. **Disagreeing with a rule** — open a PR against this repo. Don't silently diverge.
## Versioning
Releases are tagged by date: `YYYYMMDD` (e.g. `20260520`). Each tag is a
snapshot of `main` from that day, suitable for "this is the version we
agreed to follow." See `docs/03-git-workflow.md` for the tagging rules.
- Latest tag: see [`git tag --sort=-creatordate`](https://git.simgreek.com/simgreek/team-guide/tags) on the remote
- `main` is always the working copy; tags are checkpoints
## License
Internal.
+44 -25
View File
@@ -1,66 +1,85 @@
# team-guide
> English: [README.en.md](README.en.md)
我们小团队的 AI 协作(vibe coding)开发约定。
1–3 人规模,英文写文档,规则不多但都是真踩过的坑。
1–3 人规模,规则不多但都是真踩过的坑。
## 这个仓库是什么
工作方式的唯一来源——不是项目代码,是**怎么干活**。覆盖:
- 怎么用 Claude Code(CLAUDE.md、permission、hook、memory、skill)
- 怎么用 Codex(AGENTS.md、approval 模式、与 Claude Code 的分工)
- 写代码时人和 AI 怎么分工(vibe coding 守则)
- Git 工作流(分支、commit、PR、review)
- Git 工作流(分支、commit、PR、review、tag)
- Skill 管理与项目规划节奏
- 代码与产出风格(命名、注释、README、任务包、handoff)
- 产品类项目(task_assistant 这类有版本、有发行包的)的设计与发版规范
每篇都很短。一条规则要超过半页才能解释清楚的,多半还不是规则——是个待讨论项。
## 语言策略
- **给人看的**:中文。`README.md`、`docs/*.md`、人填的 template
(README、PR、handoff)都是中文。
- **给 AI 看的**:英文。`CLAUDE.md`、`AGENTS.md`、对应 template、
以及中文文档里的代码块 / 命令示例。
- **Commit / PR / 分支 / tag**:英文。AI 工具和搜索都更吃英文 metadata。
## 目录
```
team-guide/
├── README.md ← 中文版(你正在看)
├── README.en.md ← English version
├── CLAUDE.md ← Claude Code 在本仓库工作时加载的上下文
├── README.md ← 你正在看(中文,给人)
├── CLAUDE.md ← Claude Code 读的项目上下文(英文)
├── AGENTS.md ← Codex 读的项目上下文(英文)
├── docs/
│ ├── 01-vibe-coding.md ← 人 + AI 怎么分工
│ ├── 02-claude-code.md ← CLAUDE.md / permission / hook / memory / skill
│ ├── 03-git-workflow.md ← 分支、commit、PR、review、tag
│ ├── 04-skills-and-planning.md ← skill 目录 + 规划节奏
│ ├── 05-code-style.md ← 命名、注释、结构
│ └── 06-handoff.md ← 任务包、handoff 清单
│ ├── 06-handoff.md ← 任务包、handoff 清单
│ ├── 07-codex.md ← Codex 使用、AGENTS.md 同步规则
│ └── 08-product-spec.md ← 产品类项目的设计与发版规范
└── templates/
├── CLAUDE.md.template
├── README.md.template
├── PR_DESCRIPTION.template.md
└── HANDOFF_CHECKLIST.template.md
├── CLAUDE.md.template ← 给 AI 看(英文)
├── AGENTS.md.template ← 给 AI 看(英文)
├── README.md.template ← 给人填(中文)
├── PR_DESCRIPTION.template.md ← 给人填(中文)
└── HANDOFF_CHECKLIST.template.md ← 给人填(中文)
```
## 怎么用
1. **新成员** —— 先读 [`docs/01-vibe-coding.md`](docs/01-vibe-coding.md) 和 [`docs/03-git-workflow.md`](docs/03-git-workflow.md),其他当参考手册查。
2. **新项目** —— 从 `templates/` 复制模板到新仓库填上,再在新仓库根目录放一个 `CLAUDE.md` 指回这里。
1. **新成员** —— 先读 [`docs/01-vibe-coding.md`](docs/01-vibe-coding.md) 和
[`docs/03-git-workflow.md`](docs/03-git-workflow.md),其他当参考手册查。
2. **新项目** —— 从 `templates/` 复制对应模板到新仓库填上。新仓库
根目录同时放 `CLAUDE.md` 和 `AGENTS.md`,两个文件保持同步
(见 [`docs/07-codex.md`](docs/07-codex.md))。
3. **不同意某条规则** —— 在本仓库开 PR 改它,不要私下绕开。
## 文档语言约定
- 仓库内所有 `.md` 用**英文**,包括 commit message、PR 标题、tag 注释。
- 这个 README 提供中文入口;剩下的内容直接读英文版本。
- 跟外部团队/客户的交付物按对方语言来——本仓库的规则只管内部。
## 版本管理
按日期打 tag,格式 `YYYYMMDD`,比如 `20260520`。
按**项目类型**分两种 tag 风格:
- `main` 永远是当前工作副本,随时合并。
- 一天最多一个 tag。同一天有多次发布,用 `YYYYMMDD-N` 后缀(`20260520-2`)。
- **规范类**(本仓库 team-guide、其他规约文档)—— 按日期:
`YYYYMMDD`,比如 `20260520`。同一天多次发布加 `-N` 后缀
(`20260520-2`)。
- **产品类**(task_assistant、authoring-tool 这种有版本、有发行包
的)—— semver:`v0.2.4`。三处版本号必须同步(内部 `0.2.4` /
显示 `V0.2.4` / tag `v0.2.4`),细则见
[`docs/08-product-spec.md`](docs/08-product-spec.md)。
通用规则:
- `main`(规范类)/ `dev`(产品类)永远是当前工作副本,随时合并。
- Tag 一旦推到远端就不能改、不能删、不能 force-push。
- 大改写新 tag,不动旧 tag。
- 谁要"用某一版",告诉对方 tag 名(例:`team-guide @ 20260520`)就行。
- 谁要"用某一版",告诉对方 tag 名(例:`team-guide @ 20260520`、
`task_assistant @ v0.2.4`)就行。
打 tag 的具体命令和场景见 [`docs/03-git-workflow.md`](docs/03-git-workflow.md) 的 Tagging 一节。
打 tag 的具体命令和场景见 [`docs/03-git-workflow.md`](docs/03-git-workflow.md)
的 Tag 一节。
最近 tag 列表:[git.simgreek.com/simgreek/team-guide/tags](https://git.simgreek.com/simgreek/team-guide/tags)
+57 -64
View File
@@ -1,84 +1,77 @@
# 01 — Vibe coding
# 01 — Vibe coding(人机协作)
How humans and AI split the work on this team.
人和 AI 在团队里怎么分工。
## The premise
## 前提
Claude Code writes most of the code. Humans steer: framing problems,
making decisions, deciding what's good enough to ship. We're not racing
the AI — we're using it to skip typing so we can spend more time
thinking.
Claude / Codex 写大部分代码。人负责把方向:定义问题、做决策、判断
什么算"够好可以发"。我们不是在跟 AI 比谁打字快——是用 AI 把打字时间
省下来,多花点时间在思考上。
## The split
## 分工
**Claude does:**
**AI 干的:**
- Read code and explain it
- Write first-pass implementations against a clear spec
- Refactor mechanically (renames, extractions, type changes)
- Run tests, builds, linters; iterate on errors
- Generate boilerplate (configs, fixtures, templates, CRUD)
- Search across the workspace and summarize findings
- 读代码、解释代码
- 拿到清晰 spec 后写第一版实现
- 机械重构(重命名、抽函数、改类型)
- 跑测试 / build / lint,按报错迭代
- 生成模板代码(配置、fixture、CRUD)
- 跨工作区搜索、汇总
**Humans do:**
**人干的:**
- Decide what to build and why
- Frame the spec before Claude touches code
- Approve any change with non-local consequences (deps, schema, infra, auth, secrets)
- Read every diff before merging
- Make the call when Claude has tried twice and is going in circles
- Write the commit message and PR description (Claude drafts; you sign off)
- 决定要做什么、为什么做
- 在 AI 动手前把 spec 写清楚
- 批准任何有外溢影响的改动(依赖、schema、infra、auth、密钥)
- 合并前读完每一行 diff
- AI 已经试错两次还在打转时,叫停
- 写 commit message 和 PR description(AI 起草,你定稿)
If a task feels like it's drifting toward "Claude decides", stop and
write a short spec yourself first.
如果你觉得任务正在朝"AI 替我决策"漂移,先停下来自己写一段 spec。
## Prompt habits
## 提示词习惯
- **Frame, don't dictate.** Tell Claude the goal, the constraints, and
what you've already ruled out. Don't prescribe steps unless the steps
are the point.
- **Name the file.** "Fix the bug in `eval-agent/runner.py`" is better
than "fix the bug." Save Claude a search.
- **Say what done looks like.** "Tests pass and the new flag defaults to
off" — measurable. "Make it cleaner" — not.
- **One task per turn.** If you have three unrelated asks, send three
messages or open three sessions. Mixed contexts produce mixed results.
- **Push back on bad output.** If the diff is wrong, say so plainly and
point at the part that's wrong. Don't accept code you wouldn't write
yourself.
- **给框架,不给步骤。** 告诉 AI 目标、约束、你已经否决了哪些方案。
除非步骤本身就是关键,否则别一步步指挥。
- **点名文件。** "修一下 `eval-agent/runner.py` 里的 bug"比"修一下那个
bug"省一次搜索。
- **说清楚什么算完成。** "测试通过、新 flag 默认关"——可衡量。
"干净一点"——不行。
- **一轮一件事。** 三个不相关的请求就开三条对话或三个 session。
上下文混在一起,输出也会混。
- **看到不对就 push back。** diff 写错了就直说哪里错。别接受你自己
不会写出来的代码。
## When to stop and take over
## 什么时候叫停 AI、自己上
Stop letting Claude drive when:
出现以下情况停手:
- It's failed the same approach twice and the error is unchanged.
- It's adding code "for safety" that the task didn't ask for.
- The diff has grown past what you can read in one sitting.
- You can't explain the change to a teammate without re-reading the diff.
- It's about to do something irreversible (delete data, force-push,
change auth) — confirm explicitly.
- 同一个方案试了两次,错误信息都没变。
- AI 在加任务里没要求的"防御性代码"。
- diff 已经长到你一次坐下来读不完。
- 你没法在不重新看 diff 的情况下跟同事讲清楚改了什么。
- 它马上要做不可逆的事(删数据、force push、动 auth)——必须明确
确认。
If you stop and take over, write down *why* in the PR description so
the next person doesn't repeat the loop.
如果你叫停了自己上,把"为什么叫停"写进 PR description——下一个人
不至于重蹈覆辙。
## Verifying AI output
## 验收 AI 产出
Treat every Claude diff like a PR from a fast junior:
把 AI 的每一份 diff 当一个跑得快的实习生 PR 来 review:
1. Does it build?
2. Do the tests pass — and do new tests actually test the new code?
3. Did it touch files outside the stated scope? Look at every one.
4. Did it add deps? Check the lockfile diff.
5. Read every comment Claude added. Half of them are noise — delete those.
6. Run the feature end-to-end if it's user-facing. Type checks ≠ working software.
1. 能 build 吗?
2. 测试过吗——新写的测试是不是真的覆盖了新代码?
3. 改没改 spec 范围之外的文件?每个都看一遍。
4. 加依赖了吗?看 lockfile diff。
5. AI 加的注释一条条读。一半是噪音,删掉。
6. 用户可见的功能要端到端跑一遍。类型检查通过 ≠ 功能正常。
## Anti-patterns
## 反模式
- **Snowballing context.** Long sessions accumulate stale assumptions.
Start a new session for a new task.
- **Approval-by-default.** "Looks good" without reading the diff is how
bugs ship. Read it.
- **Outsourcing the spec.** "Figure out what we should do" is not a
prompt — it's avoidance.
- **Letting AI rewrite history.** If Claude wants to refactor unrelated
code "while we're here", say no. Open a separate task.
- **上下文滚雪球。** 长 session 会带进过期假设。新任务开新 session。
- **闭眼批准。** 不读 diff 就说"看着没问题"是 bug 上线的标准姿势。
读 diff。
- **把 spec 也外包了。** "你看着办"不是提示词,是逃避。
- **顺手改无关代码。** AI 想"既然来了顺便重构一下"——拒绝。开新任务。
+78 -85
View File
@@ -1,129 +1,122 @@
# 02 — Claude Code
How we configure and use Claude Code across projects.
我们在每个项目里怎么配置和使用 Claude Code。
## Configuration files
## 配置文件
Each project should have:
每个项目应该有:
```
<repo>/
├── CLAUDE.md ← project context (committed)
├── CLAUDE.md ← 项目上下文(提交进仓库)
├── AGENTS.md ← Codex / 通用 agent 上下文(提交)
└── .claude/
├── settings.json ← shared settings (committed)
├── settings.local.json ← personal overrides (gitignored)
└── skills/ ← project-local skills (committed)
├── settings.json ← 共享设置(提交)
├── settings.local.json ← 个人覆盖(gitignore)
└── skills/ ← 项目级 skill(提交)
```
`settings.local.json` is **always** gitignored. Personal API keys, local
paths, and individual hook tweaks live there.
`settings.local.json` **永远** gitignore。个人 API key、本地路径、
个人 hook 调整都放这里。
## CLAUDE.md content
`AGENTS.md` 见 [docs/07-codex.md](07-codex.md)——给 Claude 看 `CLAUDE.md`,
给 Codex 看 `AGENTS.md`,两个文件内容大体一致,工具读各自的。
Every `CLAUDE.md` answers, in this order:
## CLAUDE.md 的内容
1. **What is this project?** Two sentences max.
2. **How do I run it?** Build, test, lint commands as bash blocks.
3. **Architecture in one paragraph.** Where the entry points are and
how data flows. No diagrams unless they save words.
4. **Conventions specific to this repo.** Naming, layout, patterns
that aren't obvious from the code.
5. **Don'ts.** Things Claude has gotten wrong before. One line each.
每个 `CLAUDE.md` 按这个顺序回答:
A new contributor (human or AI) should be productive after reading it
once. If a `CLAUDE.md` is over 100 lines, it's drifted into documentation
and should be split.
1. **这是个什么项目?** 最多两句话。
2. **怎么跑?** Build、test、lint 命令,写成 bash 块。
3. **架构一段话。** 入口在哪、数据怎么流。除非能省字,否则不画图。
4. **本仓库特有的约定。** 命名、目录、那些不看注释看不出来的模式。
5. **不要做的事。** Claude 以前在这里翻过的车,每条一行。
Use `templates/CLAUDE.md.template` as the starting point.
新人(人或 AI)读一遍就该能上手干活。`CLAUDE.md` 超过 100 行,说明
它已经偷偷变成"文档"了,应该拆出去。
## Permissions
用 `templates/CLAUDE.md.template` 起手。
Default permission posture: **prompt for everything risky, allow read-only
freely.**
## 权限(permission)
In `.claude/settings.json`, allow these without prompting:
默认姿态:**只读自由放行,能改的都问一下。**
- All `Read`, `Glob`, `Grep` tools
- `Bash(git status)`, `Bash(git diff)`, `Bash(git log)`, `Bash(git branch)`
- Project-specific read-only commands (e.g. `Bash(npm test)`, `Bash(pytest)`)
`.claude/settings.json` 里可以无提示放行:
Always prompt for:
- 所有 `Read`、`Glob`、`Grep`
- `Bash(git status)`、`Bash(git diff)`、`Bash(git log)`、`Bash(git branch)`
- 项目特定的只读命令(`Bash(npm test)`、`Bash(pytest)` 这类)
- File `Edit` / `Write` outside the working tree
- `Bash` with destructive verbs (`rm`, `mv`, `git push`, `git reset --hard`, package installs)
- Any MCP tool that talks to a remote service
永远要弹窗确认:
When you find yourself approving the same prompt over and over, run the
`fewer-permission-prompts` skill — it scans your transcripts and
proposes an allowlist.
- 工作树之外的 `Edit` / `Write`
- 带破坏动词的 `Bash`(`rm`、`mv`、`git push`、`git reset --hard`、装包)
- 任何会跟外部服务对话的 MCP 工具
## Hooks
如果你发现自己在反复批准同一类提示,跑一下 `fewer-permission-prompts`
skill——它会扫 transcript 给你列一份允许列表。
Hooks are how the harness enforces rules automatically — Claude itself
won't reliably remember a "from now on…" instruction across sessions.
## Hook(钩子)
Use hooks for:
Hook 是让 harness 自动执行规则的方式——AI 自己**不可靠地**记住"以后
都要 X",跨 session 会忘。
- Auto-formatting on file edit (Prettier, ruff, gofmt)
- Blocking edits to protected paths (`.env`, generated files, `dist/`)
- Auto-running tests after a write to a known test path
- Notifying on session stop / long-running task completion
适合用 hook 的事:
Don't use hooks for:
- 文件保存后自动格式化(Prettier、ruff、gofmt)
- 阻止改受保护路径(`.env`、生成文件、`dist/`)
- 写测试路径后自动跑测试
- session 结束 / 长任务完成时通知
- One-off checks ("just remember to do X this week")
- Anything that depends on Claude's judgment ("only run if it makes sense")
不适合用 hook 的:
Configure via the `update-config` skill or edit `.claude/settings.json`
directly. Document each hook with a one-line comment in the JSON.
- 一次性检查("这周记得 X 一下")
- 任何依赖 AI 判断的("觉得有必要就跑")
## Memory
通过 `update-config` skill 配置,或者直接编辑 `.claude/settings.json`。
JSON 里每个 hook 加一行注释说明。
The harness has a per-machine memory system. Use it for:
## Memory(记忆)
- **User**: who you are, your role, your preferences.
- **Feedback**: corrections you've given Claude that should stick across
sessions (with the *why*).
- **Project**: facts about ongoing work that aren't in the code (deadlines,
stakeholder decisions, why a refactor is happening).
- **Reference**: pointers to external resources (Linear projects, Grafana
dashboards, internal wikis).
Harness 有按机器的记忆系统。用法:
Don't put memory content in `CLAUDE.md`. CLAUDE.md is project context,
shared with the team. Memory is personal, per-machine, and lives outside
the repo.
- **User**:你是谁、角色、偏好。
- **Feedback**:你给 AI 的纠正,要跨 session 保留的(带上**为什么**)。
- **Project**:进行中工作的事实,代码里没写的(截止日期、相关方决策、
为什么要重构)。
- **Reference**:外部资源指针(Linear 项目、Grafana dashboard、内网 wiki)。
Don't use memory as a notes app. If it's task-scoped, it goes in a plan or
PR description.
不要把 memory 内容塞进 `CLAUDE.md`。CLAUDE.md 是项目上下文,团队共享。
Memory 是个人的、按机器的,不进仓库。
## Skills
不要把 memory 当便签本用。任务级别的东西塞进 plan 或 PR description。
Skills live in three places:
## Skill(技能)
- **User skills** (`~/.claude/skills/`) — installed once, available everywhere
- **Project skills** (`<repo>/.claude/skills/`) — committed, shared with team
- **Plugin skills** — installed via marketplace
Skill 在三个地方:
Promote a workflow to a skill once you've done it the same way three
times. See `docs/04-skills-and-planning.md` for the catalog.
- **用户级**(`~/.claude/skills/`)—— 装一次到处可用
- **项目级**(`<repo>/.claude/skills/`)—— 提交进仓库,团队共享
- **插件**—— 通过 marketplace 安装
## Sub-agents
同一个流程做了三次都一样,就提升成 skill。目录见
[docs/04-skills-and-planning.md](04-skills-and-planning.md)。
Spawn a sub-agent (via the `Agent` tool) when:
## Sub-agent(子 agent)
- The task needs a search across many files and you don't want the
results in your main context.
- You want a second, independent read on a design or diff.
- The work is genuinely parallel (e.g. researching three options).
什么时候开 sub-agent(用 `Agent` 工具):
Don't spawn sub-agents for tasks the main agent can do in two tool calls.
The handoff overhead isn't free.
- 任务要跨很多文件搜索,又不想把搜索结果塞进主上下文。
- 想让另一个独立视角再看一遍设计或 diff。
- 工作真的并行(比如同时调研三个方案)。
## Sessions
主 agent 两次工具调用就能搞定的事,别开 sub-agent。交接成本不是免费
的。
- One task per session. Open a new session for a new task.
- If a session is running long and the context bar is filling, finish
the current step, summarize state into a plan or PR draft, then start
fresh.
- Don't use `--continue` to resume a session from yesterday on a new
topic. The stale context will leak in.
## Session
- 一个 session 一个任务。新任务开新 session。
- session 跑长了、上下文条快满了:先收尾当前步骤,把状态总结进 plan
或 PR draft,然后开新 session。
- 别用 `--continue` 把昨天的 session 拉回来做新主题。陈旧上下文会
渗进来。
+103 -87
View File
@@ -1,35 +1,35 @@
# 03 — Git workflow
# 03 — Git 工作流
Small team, light process. Branches, commits, PRs, review.
小团队,流程从轻。分支、commit、PR、review、tag。
## Branches
## 分支
- `main` is always shippable. No direct pushes. No exceptions.
- Feature branches: `<owner>/<short-slug>` — e.g. `bai/auth-retry`,
`bai/eval-agent-rerun`. Lowercase, hyphens, your handle as prefix.
- Long-lived integration branches: `integration/<topic>` — only with
team agreement.
- Delete branches after merge. Old branches confuse search.
- `main` 永远可发。不直接 push,没有例外。
- 功能分支:`<owner>/<short-slug>` —— 比如 `bai/auth-retry`、
`bai/eval-agent-rerun`。小写、连字符、你的 handle 做前缀。
- 长期集成分支:`integration/<topic>` —— 团队同意才用。
- 合并完删分支。老分支会污染搜索结果。
## Commits
## Commit
Format:
格式:
```
<area>: <imperative summary under 60 chars>
<area>: <祈使句小结,60 字符以内>
<optional body — what changed and why, not how>
<可选 body —— 写改了什么、为什么,不写怎么改>
```
- `<area>` is a directory or component, lowercase: `eval-agent`,
`task_assistant`, `docs`, `git-workflow`.
- Imperative: "add", "fix", "rename" — not "added" / "adding".
- Body wraps at ~72 chars. Skip it for trivial commits.
- One topic per commit. "and" in the summary means split it.
- AI-assisted commits get the `Co-Authored-By` trailer Claude Code adds
by default. Don't strip it.
- `<area>` 是目录或组件,小写:`eval-agent`、`task_assistant`、
`docs`、`git-workflow`。
- 祈使句:`add`、`fix`、`rename`,不要 `added` / `adding`。
- Body 在 ~72 字符换行。普通改动跳过 body。
- 一个 commit 一个主题。摘要里出现"and"——拆。
- AI 协作的 commit 保留 Claude Code 默认加的 `Co-Authored-By` trailer。
别去掉。
- Commit message 用英文(vibe coding 守则之一:给 AI 看的内容用英文)。
Examples:
例:
```
eval-agent: rerun failed tasks with stable seed
@@ -37,64 +37,70 @@ docs: clarify branch naming in git-workflow
task_assistant: drop unused legacy export path
```
## Pull requests
## Pull Request
- One PR per topic. If you can't describe it in one sentence, it's
multiple PRs.
- Title under 70 chars, same shape as a commit summary.
- Description uses `templates/PR_DESCRIPTION.template.md`.
- Push to your feature branch with `-u` the first time so it tracks
remote.
- Open the PR as soon as you have something runnable, even if it's a
draft. Review-as-you-go beats review-at-the-end.
- 一个 PR 一个主题。一句话说不清楚——拆成多个 PR。
- 标题 70 字符以内,跟 commit 摘要同一形态。
- Description 用 `templates/PR_DESCRIPTION.template.md`。
- 第一次 push feature 分支用 `-u`,让它跟踪远端。
- 有可跑的东西就开 PR,draft 也行。边写边 review 比写完再 review 好。
## Review
We review every PR before merge, even our own AI-assisted ones.
每个 PR 都要 review,包括 AI 协作出的,自己也不能跳。
Reviewer checks:
Reviewer 检查清单:
1. Does the description match the diff? If the diff has surprises, ask.
2. Read every file changed. If a file isn't related to the stated
topic, ask why it's in the PR.
3. Run the change locally if it's not obviously correct from reading.
4. New deps, schema changes, env vars, or auth-touching code → block
until justified.
5. Comment on the *least* important issue first; save the merge-blocker
for last so it's clearly the gate.
1. Description 跟 diff 对得上吗?diff 有惊喜——发问。
2. 改的每个文件都看一遍。文件跟主题无关——发问为什么进了 PR。
3. 改动不是显而易见就本地跑一遍。
4. 新依赖、schema 变更、env var、动 auth 的代码——讲清楚理由前
block。
5. 评论先发**最不重要**的;merge-blocker 留到最后,让它明显是闸门。
Author follow-ups:
作者收尾:
- Address every comment, even with "agreed, fixed in <commit>".
- If you disagree, push back in writing. Don't silently ignore.
- Squash fixup commits before merge if the history is noisy.
- 每条评论都回应,哪怕只是"同意,已在 <commit> 修"。
- 不同意写出来 push back,不要默默忽略。
- 合并前把噪音 commit 压一下(squash fixup commits)。
## Merging
## 合并
- Squash for feature branches. Merge commits are reserved for
integration branches.
- Final squash message follows the commit format above. The PR title is
usually the right starting point.
- Delete the branch on merge.
- Feature 分支用 squash。Merge commit 留给集成分支。
- 最终 squash message 按 commit 格式写。PR 标题通常就是好起点。
- 合并完删分支。
## Tagging (versioning)
## Tag(版本管理)
We tag by date: `YYYYMMDD` (e.g. `20260520`). Each tag is a snapshot of
`main` worth pointing at — "this is the version we agreed to follow."
按项目类型分两种 tag 风格:
Rules:
| 项目类型 | Tag 格式 | 例子 | 用在哪儿 |
| -------- | ------------------- | -------------------------- | ------------------------------------- |
| 规范类 | `YYYYMMDD[-N]` | `20260520`、`20260520-2` | team-guide、规约文档、内部约定仓库 |
| 产品类 | `vX.Y.Z` | `v0.2.4` | task_assistant、有版本和发行包的产品 |
- Tag only on `main`. Tagging a feature branch is a smell.
- One tag per day max. If you cut a second one the same day, suffix with
`-N`: `20260520-2`, `20260520-3`.
- Tag messages are annotated, not lightweight. Use `git tag -a` and
write one or two sentences about what changed since the last tag.
- A tag, once pushed, is immutable. No deleting, no moving, no force-tag.
If the tag is wrong, cut a new one.
- Tag the commit, push the tag, and announce the tag name. That's the
release.
判断标准:会有"用户"拿到这个项目的版本化产物——产品类。否则——规范
类。详细规则见 [`docs/08-product-spec.md`](08-product-spec.md)。
Cut a tag:
每个 tag 是 `main` 某一时刻的快照——值得指着说"我们就按这版来"。
通用规则(两类都适用):
- 只在 `main`(规范类)或 `dev`(产品类)上打 tag。功能分支打 tag
是 smell。
- 用 annotated tag,不用 lightweight。`git tag -a` 加一两句说自上次
tag 以来改了什么。
- Tag 一旦推到远端就不能改、不能删、不能 force-tag。错了就再切一个。
- Tag commit、push tag、告诉大家 tag 名字——这就是发布。
规范类专属:一天最多一个 tag。同一天再切一个,加 `-N` 后缀:
`20260520-2`、`20260520-3`。
产品类专属:semver 三元组、产品 README 必备版本字段同步、tag
message 用 `<Project> V<x.y.z>`——细则见
[`docs/08-product-spec.md`](08-product-spec.md)。
切 tag(规范类):
```bash
git checkout main
@@ -103,35 +109,45 @@ git tag -a 20260520 -m "team-guide 20260520: bilingual README, dated tags"
git push origin 20260520
```
List / inspect:
切 tag(产品类):
```bash
git tag --sort=-creatordate # newest first
git show 20260520 # show what's in a tag
git log --oneline 20260513..20260520 # what changed between tags
git checkout dev
git pull --ff-only <remote> dev
git tag -a v0.2.4 HEAD -m "<Project> V0.2.4"
git push <remote> v0.2.4
```
When to cut a tag:
查看 / 对比:
- The docs in this repo changed in a way teammates need to read.
- A template was added, removed, or restructured.
- A new convention is now in effect (not just proposed).
```bash
git tag --sort=-creatordate # 按时间倒序
git show 20260520 # 看一个 tag 里有什么
git log --oneline 20260513..20260520 # 两个 tag 之间改了什么
```
When NOT to cut a tag:
什么时候切 tag(规范类):
- Typo fixes, formatting, broken links → just push to `main`.
- Drafts under discussion → use a PR, don't tag.
- 本仓库的 docs 改了,队友需要重新读。
- 加了、删了或重组了 template。
- 新的约定正式生效(不是还在讨论)。
## What NOT to do
什么时候**不**切 tag(规范类):
- No `git push --force` to `main`. Period. To your own branch, only if
nobody else has pulled it.
- No `--no-verify` to skip hooks. Fix what the hook is complaining
about.
- No amending pushed commits. Once it's on the remote, add a new commit.
- No deleting or moving tags after they've been pushed. Cut a new one
instead.
- No committing `.env`, credentials, or files larger than ~5 MB without
a Git LFS conversation first.
- No staging with `git add .` or `git add -A` when there are untracked
files you don't recognize. Stage by name.
- 改错别字、调格式、修死链 → 直接 push 到 `main`。
- 还在讨论的草稿 → 走 PR,不打 tag。
产品类切 tag 跟着发版走,触发条件由[最低交付标准](08-product-spec.md#最低交付标准每次可给别人用的版本)
决定。
## 不要做的事
- 不要 `git push --force` 到 `main`。永远不要。push 到自己分支
也只在确定没人 pull 过的情况下。
- 不要 `--no-verify` 跳 hook。修 hook 报的问题。
- 不要 amend 已经 push 的 commit。已经在远端的就加新 commit。
- 不要删或移已经 push 的 tag。错了就切新的。
- 不要提交 `.env`、密钥、或者 ~5 MB 以上的文件——大文件先聊
Git LFS。
- 有不认识的 untracked 文件时,不要 `git add .` / `git add -A`。
按文件名加。
+66 -77
View File
@@ -1,112 +1,101 @@
# 04 — Skills and planning
# 04 — Skill 与规划
How we manage the skill catalog and how we plan work as a small team.
我们怎么管 skill 目录、小团队怎么排活。
## Skill catalog
## Skill 目录
A "skill" is a reusable, named workflow Claude Code can invoke. We keep
three catalogs:
"Skill"是 Claude Code 能调用的、命名好的可复用流程。我们维护三份:
- **Personal** (`~/.claude/skills/`) — private, per developer.
- **Team** (`<repo>/.claude/skills/`) — committed, shared via the project.
- **Bundled / plugin** — installed from a marketplace.
- **个人**(`~/.claude/skills/`)—— 私人,每人自己管。
- **团队**(`<repo>/.claude/skills/`)—— 提交进仓库,跟项目共享。
- **打包 / 插件** —— 从 marketplace 装。
### When to make a skill
### 什么时候做 skill
Promote a workflow to a skill when **all three** are true:
工作流提升成 skill 要**同时**满足三条:
1. You've done it the same way three times.
2. The steps are stable enough to write down.
3. Someone else on the team would do it the same way if shown.
1. 你已经用同样的方式做过三次。
2. 步骤稳定到能写下来。
3. 别人按你写的也会做出同样的东西。
If only two are true, leave it as a prompt snippet in your notes.
只满足两条——留在你的提示词笔记里。
### Skill design rules
### Skill 设计规则
- One skill, one job. Skills that branch on "what does the user want?"
are two skills.
- Name the skill as a verb phrase: `review-pr`, `cut-release`,
`rebuild-fixtures`. Not `pr-helper`.
- Description (the one-liner the model sees) must say *when to invoke*,
not what the skill does. The model decides on the *when*.
- Keep `SKILL.md` under 200 lines. Long skills get broken into stages.
- Examples beat instructions. Show one good run.
- 一个 skill 一件事。要分支判断"用户想干什么"——拆成两个。
- 用动词短语命名:`review-pr`、`cut-release`、`rebuild-fixtures`。
不要 `pr-helper`。
- Description(模型看的那行字)说**什么时候触发**,不是 skill 干啥。
触发由模型判断。
- `SKILL.md` 200 行以内。长 skill 拆成阶段。
- 例子比说明强。给一个跑通的 run。
### Reviewing skills
### Skill review
Treat a new skill like a PR: read it, run it once on a real task, then
merge. Skills that nobody runs after a month get archived (move to
`.claude/skills/_archive/`).
新 skill 当 PR 看:读、在真实任务上跑一次、merge。一个月没人用的
skill 归档(移到 `.claude/skills/_archive/`)。
### Active skills (this team)
### 当前活跃 skill(团队)
Maintain this list as we go. Drop a one-line description and the path.
边走边维护。每条一行说明 + 路径。
```
# Personal recommendations (install with marketplace or copy):
# anthropic-skills:consolidate-memory — periodic memory cleanup
# simplify — review changed code for reuse/quality
# fewer-permission-prompts — propose allowlist from transcripts
# review — review a pull request
# security-review — security pass on pending changes
# 推荐安装的(marketplace 或拷贝):
# anthropic-skills:consolidate-memory — 周期性 memory 整理
# simplify — review 改动找复用 / 质量问题
# fewer-permission-prompts — 从 transcript 提议 allowlist
# review — review pull request
# security-review — 对 pending 改动做安全 pass
# Team skills (in this repo):
# (none yet — add as we promote workflows)
# 团队 skill(本仓库):
# (还没有 —— 提升成 skill 后加进来)
```
## Planning cadence
## 规划节奏
We're 1–3 people. Process should be the lightest thing that keeps us
aligned. Right now that's:
我们 1–3 人。流程能保持对齐就够轻。当下做法:
### Weekly
### 每周
- One short async written sync (Mon morning). Each person posts:
1. What I shipped last week (one line per item).
2. What I'm picking up this week (one line per item).
3. What's blocked or unclear (the only section worth reading carefully).
- 30-minute live call mid-week. Agenda comes from the "blocked or
unclear" lines.
- 一次异步书面同步(周一上午)。每人发:
1. 上周交付了什么(每条一行)。
2. 这周准备捡什么(每条一行)。
3. 哪儿卡住或不清楚(**唯一**值得仔细读的部分)。
- 周中 30 分钟实时会。议题来自上面那条"卡住或不清楚"。
### Per-task
### 每个任务
Before starting work that will take more than ~half a day:
要超过半天的活,开工前:
1. Write a 5-line spec: *Goal / Why / Done when / Out of scope / Risks*.
2. Drop it in the PR description (draft PR is fine) **before** writing
code.
3. If Claude is going to do most of the typing, the spec is also the
prompt — paste it in.
1. 写 5 行 spec:*目标 / 为什么 / 完成标准 / 范围外 / 风险*。
2. 在 PR description 里贴上(draft PR 也行),**写代码前**。
3. AI 要替你打字的话,这段 spec 就是提示词——直接喂进去。
After finishing:
收尾:
1. PR description updated to match what actually shipped.
2. Anything you learned that future-you would want goes into Claude
memory (feedback / project type) — see `docs/02-claude-code.md`.
1. PR description 更新到跟实际交付一致。
2. 学到的、未来你想看到的,进 Claude memory(feedback / project 类型)
—— 见 [docs/02-claude-code.md](02-claude-code.md)。
### Per-quarter
### 每季度
One half-day to:
留半天:
- Re-read this `team-guide` repo. Open PRs for what's stale.
- Review the skill catalog. Archive what we don't use.
- Run `consolidate-memory` against personal memory files.
- 重读本仓库。过期的开 PR 改。
- 重审 skill 目录。不用的归档。
- 跑 `consolidate-memory` 整理个人 memory 文件。
## Project structure
## 项目结构
When starting a new project under this workspace:
工作区下开新项目:
1. Copy `templates/README.md.template` and `templates/CLAUDE.md.template`.
2. `git init` immediately, even if the project is throwaway. Throwaway
projects survive longer than you expect.
3. First commit: scaffolding only, no real code. Makes future `git log`
readable.
4. Add the project to the workspace `README` (when we have one) so it's
discoverable.
1. 复制 `templates/README.md.template` 和 `templates/CLAUDE.md.template`。
2. 立刻 `git init`,哪怕项目是一次性的。一次性项目活得比你想的久。
3. 第一个 commit 只放脚手架,没有真实代码。让 `git log` 后续好读。
4. 把项目加进工作区 README(有了之后),让别人能发现。
## What planning is *not*
## 规划**不是**
- It's not Jira tickets. We don't need a board for two people.
- It's not Gantt charts. If we need one, we're building the wrong thing.
- It's not status theater. The Monday post is for spotting blocks, not
for proving you worked.
- 不是 Jira ticket。两个人不需要看板。
- 不是 Gantt 图。需要 Gantt 说明在做错的东西。
- 不是状态秀。周一帖是为了发现卡点,不是证明你干了活。
+70 -85
View File
@@ -1,111 +1,96 @@
# 05 — Code & deliverable style
# 05 — 代码与产出风格
Naming, comments, structure. Same rules apply whether a human or Claude
typed the code.
命名、注释、结构。不论是人写的还是 AI 写的代码,都按这套来。
## Naming
## 命名
- **Files** — lowercase, hyphens for docs (`git-workflow.md`),
underscores for Python (`task_runner.py`), kebab for JS/TS where the
ecosystem prefers it. Match the surrounding project.
- **Functions** — verb phrases. `loadConfig`, not `config`. `runTask`,
not `taskRunner`.
- **Variables** — say what they are, not their type. `users`, not
`userArray`. `retryCount`, not `n`.
- **Booleans** — `is*`, `has*`, `should*`. `isReady`, not `ready`.
- **Constants** — `UPPER_SNAKE_CASE` only when truly module-level
constants. Inside functions, just use a normal `const`.
- **No abbreviations** unless they're a domain term. `database`, not
`db`. `request`, not `req`. (`req`/`res` in Express handlers is fine —
domain convention.)
- **文件** —— 小写。文档用连字符(`git-workflow.md`),Python 用
下划线(`task_runner.py`),JS/TS 跟生态走 kebab。匹配周围项目。
- **函数** —— 动词短语。`loadConfig` 不是 `config`;`runTask`
不是 `taskRunner`。
- **变量** —— 写它**是什么**,不写它的类型。`users` 不是
`userArray`;`retryCount` 不是 `n`。
- **布尔** —— `is*`、`has*`、`should*`。`isReady` 不是 `ready`。
- **常量** —— `UPPER_SNAKE_CASE` 仅用于真正的模块级常量。函数内用
普通 `const`。
- **不要缩写**——除非是领域术语。`database` 不是 `db`,`request`
不是 `req`。(Express handler 里的 `req`/`res` 是领域约定,可以。)
## Comments
## 注释
Default to none. A comment is justified when **all** are true:
默认不写。要写注释,**全部**条件成立:
- The *why* is non-obvious from the code.
- A future reader would otherwise misread the code.
- The code itself can't be made clearer (rename, extract, restructure).
- "为什么"从代码里看不出来。
- 未来读代码的人不写注释会读错。
- 代码本身改不清晰(重命名、抽函数、重组都试过)。
Don't write:
不要写:
- `// increment counter` next to `counter++`
- `// added for the auth refactor` — belongs in the commit message
- Block comments restating function signatures
- TODOs without an owner or a date — they rot. Either fix it now, file
an issue, or delete the comment.
- `// increment counter` 紧挨着 `counter++`
- `// added for the auth refactor` —— 这话该在 commit message 里
- 一大段 docstring 只是把签名复述一遍
- 没有 owner 没有日期的 TODO —— 它们会烂掉。要么现在修,要么开
issue,要么删了。
Do write:
可以写:
- One-liners explaining a non-obvious workaround, with the *why*.
- A `# NOTE:` when behavior would surprise a reader.
- Module headers only when a file does something the directory layout
doesn't already explain.
- 一行解释一个非显而易见的 workaround,带上**为什么**。
- `# NOTE:` 标注会让读者意外的行为。
- 文件头注释,仅限于这个文件做的事目录结构没说清楚。
## File structure
## 文件结构
- One concept per file. If you can't summarize the file in one sentence,
split it.
- Keep tests next to the code, not in a parallel tree, unless the
project already does the parallel tree.
- Generated files go in `dist/`, `build/`, or similar — and into
`.gitignore`. Never edit a generated file.
- Lockfiles are checked in. Always.
- 一个文件一个概念。一句话说不清这个文件干啥——拆。
- 测试文件挨着代码放,除非项目本来就是平行测试树。
- 生成文件进 `dist/` / `build/` 这类目录,进 `.gitignore`。永远
不改生成文件。
- Lockfile 必须 commit,永远。
## Errors
## 错误
- Fail loudly at boundaries (user input, external APIs, file I/O).
- Don't `try/except` to silence errors. If you catch, you handle.
- Internal functions trust their callers. Don't validate the same input
three layers deep.
- Logged errors include enough context to debug from logs alone — what
was being attempted, which inputs, which path.
- 在边界处(用户输入、外部 API、文件 I/O)大声失败。
- 不要 `try/except` 吞错。捕了就处理。
- 内部函数信任调用方,不要在三层深度上重复校验同一个输入。
- 日志里的错要带够上下文,光看日志能调试——做的什么操作、输入是
什么、走的哪条路径。
## Tests
## 测试
- Test the behavior, not the implementation. If a refactor that
preserves behavior breaks a test, the test was wrong.
- One assertion per test, ideally. "Tests that test many things at once
fail unhelpfully."
- Fixtures live next to the tests that use them.
- Slow / flaky tests get marked or quarantined, not silently retried.
- New code without a test is incomplete unless the project genuinely
has no test infrastructure (rare, and a bug in itself).
- 测行为,不测实现。一个保留行为的重构把测试搞挂了——是测试错。
- 一个测试一个断言为佳。"啥都测的测试,挂了你不知道是哪一个挂了。"
- Fixture 和用它的测试放一起。
- 慢 / flaky 的测试加标记或隔离,不要默默重试。
- 没测试的新代码就是没写完——除非项目真的没有测试基础设施
(罕见,而且这本身是个 bug)。
## READMEs
## README
Every repo has a `README.md`. It answers, in order:
每个仓库都要有 `README.md`。按这个顺序回答:
1. **What is this?** One paragraph.
2. **How do I run it?** Bash blocks for setup, run, test.
3. **How do I develop on it?** Where the code lives, what the conventions
are.
4. **Where does the data come from / go to?** Only if non-obvious.
5. **Pointers.** Related repos, dashboards, docs.
1. **这是什么?** 一段话。
2. **怎么跑?** Setup / run / test 的 bash 块。
3. **怎么开发?** 代码在哪,约定是什么。
4. **数据从哪来 / 去哪?** 仅当不显然才写。
5. **指针。** 关联仓库、dashboard、文档。
Use `templates/README.md.template`. If the README is shorter than the
template, that's fine — delete the unused sections.
用 `templates/README.md.template`。如果你的 README 比模板短,没问题
——把没用的 section 删掉。
## Deliverables (task packages, datasets, exports)
## 交付物(任务包、数据集、导出)
When we ship a deliverable to a partner or downstream consumer:
给伙伴或下游交付时:
1. Versioned filename: `<name>-v<n>.<ext>` or `<name>-<YYYYMMDD>.<ext>`.
Pick one convention per project and stick to it.
2. Ships with a `README` describing schema, generation date, known
limitations.
3. Ships with a verification report (counts, checksums, sanity checks)
in the same archive.
4. Exact commit hash that produced it goes in the README.
1. 文件名带版本:`<name>-v<n>.<ext>` 或 `<name>-<YYYYMMDD>.<ext>`。
一个项目一种约定,定了别变。
2. 配 `README` 写明 schema、生成日期、已知限制。
3. 配验证报告(计数、checksum、合理性检查),跟交付物一起打包。
4. 生成它的 commit hash 写进 README。
See `docs/06-handoff.md` for the full checklist.
完整 checklist 见 [docs/06-handoff.md](06-handoff.md)。
## What NOT to do
## 不要做的事
- Don't introduce a third way to do something we already do two ways.
Pick one and migrate.
- Don't add config options "for flexibility" without a real use case.
YAGNI.
- Don't refactor unrelated code in a feature PR. Open a separate PR.
- Don't optimize before measuring. "It might be slow" is not a
measurement.
- 不要引入第三种做某件事的方式——已经有两种了。挑一种统一。
- 不要"为了灵活性"加配置开关,没有真实用例就别加。YAGNI。
- 不要在功能 PR 里顺手重构无关代码。开新 PR。
- 不要没量就先优化。"可能慢"不是测量结果。
+61 -79
View File
@@ -1,41 +1,37 @@
# 06 — Handoff
# 06 — Handoff(交接)
Task packages, deliverables, and how we hand work between team members
or to external consumers.
任务包、交付物、团队成员之间或对外部消费方的交接。
## Why this matters
## 为什么这事重要
Handoff failures cost more than the original work. A package that's
"obviously how it works" to the author is a half-day of confusion for
the recipient. Treat handoff as part of the deliverable, not as
afterthought packaging.
交接出问题的成本比原工作高。作者觉得"显然就是这么用的"的包,到接收方
手里是半天的迷茫。把交接当**交付物的一部分**对待,不是事后包装。
## Two kinds of handoff
## 两种 handoff
1. **Internal** — passing work to another team member (or future-you).
Usually a branch, a PR, or a half-finished prototype.
2. **External** — shipping a versioned artifact to a partner, customer,
or downstream pipeline. Usually a zip, a dataset, or a release.
1. **内部** —— 把工作交给队友(或未来的你)。通常是分支、PR、半成品
原型。
2. **外部** —— 给伙伴、客户或下游 pipeline 发版本化产物。通常是 zip、
数据集、release。
Both use the checklist in `templates/HANDOFF_CHECKLIST.template.md`. The
external case has a higher bar.
两种都用 `templates/HANDOFF_CHECKLIST.template.md`。外部的标准更高。
## Task packages
## 任务包
When we ship a task package (e.g. `praxis-sample-5.zip`,
`task-assistant-v0.2-handoff-*.zip`), it must contain:
我们发的任务包(比如 `praxis-sample-5.zip`、
`task-assistant-v0.2-handoff-*.zip`)必须包含:
```
<package>/
├── README.md ← what this is, who it's for, how to use it
├── CHANGELOG.md ← what changed since the last version
├── VERIFICATION.md ← counts, checksums, sanity checks
├── manifest.json ← machine-readable metadata
├── data/ ← the actual deliverable
└── scripts/ ← only what's needed to use the package
├── README.md ← 这是什么、给谁用、怎么用
├── CHANGELOG.md ← 自上一版改了什么
├── VERIFICATION.md ← 计数、checksum、合理性检查
├── manifest.json ← 机器可读的元数据
├── data/ ← 真正的交付物
└── scripts/ ← 用这个包必须的脚本
```
`manifest.json` minimum fields:
`manifest.json` 至少要有:
```json
{
@@ -49,73 +45,59 @@ When we ship a task package (e.g. `praxis-sample-5.zip`,
}
```
If you can't fill a field, leave it as `null` and explain in the README.
Never make one up.
填不出的字段写 `null`,在 README 里解释。**永远不要瞎编**。
## Internal handoff (branch / PR)
## 内部 handoff(分支 / PR)
Before handing off:
交出去之前:
- PR description is current. The summary describes what shipped, not
what was attempted.
- The "test plan" section in the PR template is filled in honestly. If
you didn't test something, say so — don't bury it.
- Any AI-assisted decisions that surprised you go in a `## Notes for
reviewer` section. "Claude tried X first, that didn't work because Y,
here's the working approach" saves the reviewer a re-derivation.
- Local-only state (env vars, scratch data) is documented or scripted.
"Works on my machine" is not a handoff.
- PR description 是最新的。Summary 写实际交付了什么,不是尝试过什么。
- PR template 里的 "test plan" 老老实实填。没测就说没测——别埋。
- AI 协作中让你意外的决策放进 `## Notes for reviewer`。"AI 先试了 X
不行因为 Y,最后用了 Z"——省 reviewer 重推一遍。
- 本地状态(env var、临时数据)要文档化或脚本化。"在我机器上能跑"
不算交接。
The recipient should be able to:
接收方应该能:
1. `git checkout` the branch
2. Read the PR description
3. Run the test plan
4. Form an opinion
1. `git checkout` 这个分支
2. 读 PR description
3. 跑 test plan
4. 形成自己的判断
— without messaging you. If they have to message you, the handoff is
incomplete.
—— **不用问你**。如果接收方还要私聊你,handoff 就是不完整的。
## External handoff (versioned artifact)
## 外部 handoff(版本化产物)
Higher bar. In addition to the task package contents above:
标准更高。除上面任务包内容外:
- **Reproducibility.** Someone with access to the source repo can
rebuild the artifact from the commit hash in `manifest.json`. Test
this at least once before the first release.
- **Verification report.** A machine-checkable report (JSON or
similar) showing the artifact passed our pre-ship checks. Include
what was checked and the result.
- **Provenance.** If the artifact was generated using AI assistance,
note the model and any human-in-the-loop steps. Not for ceremony —
for debugging when something looks wrong six months from now.
- **License & attribution.** Even for internal partners. Be explicit
about what they can and can't do with the data.
- **可重现。** 有源码访问的人能从 `manifest.json` 里的 commit hash
重建产物。第一次发布前测一遍。
- **验证报告。** 一份机器可读(JSON 之类)的报告,记录预发检查的
通过情况。写清楚检查了什么、结果是什么。
- **来源(provenance)。** AI 协助生成的,写明用的哪个模型、人工
审核步骤是什么。不是为了仪式感——是为了半年后产物有问题时好查。
- **License 与署名。** 内部伙伴也要写。明确他们能用、不能用。
## What NOT to ship
## 不要发的东西
- Files larger than ~500 MB without a conversation about delivery
channel.
- Anything containing real PII unless that was explicitly the deal.
- `.env`, secrets, API keys, internal hostnames.
- "Final final v3" filenames. Use the version field. If it's `final`,
it's `v1.0`.
- A package without a README. Even a one-line README beats none.
- 没聊过传输渠道的 ~500 MB 以上文件。
- 含真实 PII 的内容——除非交付协议里就明确包含。
- `.env`、密钥、API key、内部主机名。
- "final final v3" 命名。用 version 字段。要是 final,那就是 `v1.0`。
- 没有 README 的包。一行 README 也比没有强。
## Receiving a handoff
## 收到 handoff 时
When you're on the receiving end:
你是接收方:
1. Read the README first, fully. Resist the urge to start running
scripts.
2. Run the verification report. If it doesn't pass, stop and message
the sender before doing anything else.
3. Note any surprise — naming, missing files, version mismatch — and
send it back to the sender within a day. Drift gets worse with
silence.
1. 先**完整读** README。忍住直接跑脚本的冲动。
2. 跑一遍验证报告。不通过——停下来联系发送方再做任何事。
3. 任何意外(命名、缺文件、版本不对)一天内反馈给发送方。drift 不
反馈只会越来越歪。
## Templates
## 模板
- `templates/HANDOFF_CHECKLIST.template.md` — fill out per handoff,
ships in the package.
- `templates/PR_DESCRIPTION.template.md` — for internal handoff via PR.
- `templates/HANDOFF_CHECKLIST.template.md` —— 每次交接填一份,跟
包一起发。
- `templates/PR_DESCRIPTION.template.md` —— 内部 handoff 走 PR 用。
+114
View File
@@ -0,0 +1,114 @@
# 07 — Codex
我们怎么在团队里用 Codex(CLI 与 IDE 集成),以及 `AGENTS.md` 怎么写。
## 为什么要规范
Codex 不读 `CLAUDE.md`。Claude Code 默认不读 `AGENTS.md`。两个工具在
同一个仓库里干活,看的是不同的"项目说明书"。如果只写一份,另一边就
是裸奔。
我们的做法:**两份都写,内容保持同步**。哪边的工具进来读哪边的文件。
## 文件分工
```
<repo>/
├── CLAUDE.md ← Claude Code 读的项目上下文
├── AGENTS.md ← Codex CLI / Codex IDE 读的项目上下文
└── docs/... ← 给人读的文档(中文)
```
两个文件**内容大体一致**:项目是什么、怎么跑、架构、本仓库特有的
约定、不要做什么。
它们的区别是:
- `CLAUDE.md` 偶尔会引用 Claude Code 特有的概念(skill、sub-agent、
permission mode、`.claude/settings.json`)。
- `AGENTS.md` 偶尔会引用 Codex 特有的概念(approval 模式、
`~/.codex/config.toml`、MCP server 配置)。
- 双方共有的部分(项目背景、命名约定、语言策略、commit 格式)必须
完全一致。
## 同步责任
谁改了 `CLAUDE.md`,谁顺手改 `AGENTS.md`(反之亦然)。在 PR 描述里
加一句"Synced AGENTS.md"或"Synced CLAUDE.md"——reviewer 一眼就能确认。
如果 PR 只改了一边,reviewer **block** 这个 PR,让作者补上。
要是哪天发现两边内容已经漂移得太远,开一个专门的 PR 重新对齐,
不要在功能 PR 里捎带修。
## Codex 使用约定
### 启动方式
- 终端:`codex`(不指定 prompt 进交互模式)或 `codex "<prompt>"`(一次性
任务)。在仓库根目录启动,让它能找到 `AGENTS.md`。
- IDE:用官方插件(VS Code / JetBrains)。仓库根目录的 `AGENTS.md`
自动加载。
### Approval 模式
默认用 `on-request`(命令前问一下)。机器是个人的、风险可控的环境
才用 `on-failure` 或 `never`。生产环境、共享机器、不熟悉的仓库——
保持 `on-request`。
调整方式见 Codex 文档;个人偏好放进 `~/.codex/config.toml`,**不要**
提交进仓库。
### 沙盒(sandbox)
- 写代码 + 跑测试:`workspace-write` + 网络 off。够用了。
- 需要联网装包 / fetch 资源:临时切 `workspace-write` + 网络 on,跑完
切回。
- `danger-full-access` 几乎不用。除非你知道自己在干嘛而且代价能承担。
### 不要让 Codex 干的事
跟 Claude Code 一样:
- 删数据、`git push --force`、改 auth、动密钥——**人决策**。
- 改 schema、加依赖、改 CI——**人审批**。
- 跨仓库的改动——**手动协调**,不要让 agent 一次推两个仓库。
## AGENTS.md 写法
每个项目的 `AGENTS.md` 按这个顺序写:
1. **项目** —— 一两句话定位。不要超过两句。
2. **怎么跑** —— Build / test / lint 命令,bash 块。
3. **架构** —— 一段话。入口、数据流、核心模块。能省字就省字。
4. **本仓库特有约定** —— 命名、目录、那些代码里看不出来的模式。
5. **语言策略** —— 哪些文件是中文(人看),哪些是英文(AI 看),
commit / PR / branch / tag 用什么语言。
6. **不要做的事** —— 翻过的车,每条一行。
100 行以内是目标,超出说明它在朝"通用文档"漂移,该拆。
模板见 `templates/AGENTS.md.template`。
## 工具选择建议
不是非此即彼,但有偏好:
- **写 docs / 写规范** —— Claude Code(这个仓库就是它写的)。
- **大段重构 / 跨多文件功能** —— Claude Code,因为有 plan mode 和
sub-agent。
- **窄范围编辑、跑个测试、改个配置** —— Codex CLI,启动快。
- **IDE 内 inline 改一段** —— Codex IDE 插件或 Cursor,看习惯。
两个工具混着用没问题,只要:
- 一个 session 一个工具(别又开 Claude Code 又开 Codex 改同一个文件,
互相覆盖很难追)。
- 两边产出的 commit 都按本仓库的 commit 格式([03-git-workflow.md](03-git-workflow.md))。
## 配置同步与个人覆盖
- 项目级:`AGENTS.md`、`CLAUDE.md`、`.claude/settings.json` 都进仓库。
- 个人级:`~/.codex/config.toml`、`~/.claude/settings.json`、
`.claude/settings.local.json`——**永远不进仓库**,gitignore 已经覆盖。
- 个人 token 永远不写进仓库里的任何文件,包括 `AGENTS.md`。
+291
View File
@@ -0,0 +1,291 @@
# 08 — 产品类项目规范
把 task_assistant 这类**有版本、有发行包、有用户使用**的项目从设计
到发布要遵循的约定写下来。规范性文件(像本仓库 team-guide 自己)按
日期 tag;产品代码按 semver。
## 两类项目的分界
| 维度 | 规范类(team-guide、规约文档) | 产品类(task_assistant、authoring-tool) |
| ---------- | ----------------------------- | ---------------------------------------- |
| 内容 | 文档、约定、模板 | 可执行代码、可发行的产物 |
| Tag 格式 | `YYYYMMDD` / `YYYYMMDD-N` | `v<major>.<minor>.<patch>` |
| 验收 | 人能读懂 | 测试通过、能跑起来 |
| 分发渠道 | Git 仓库本身 | Git(源码)+ 分发渠道(OpenList、HF 等) |
| 版本字段同步 | 没有 | 多处必须同步(见下文) |
| 用户 | 团队成员 | 真实使用者 |
不确定一个项目是哪类,问自己:"会有'用户'拿到这个项目的版本化产物
吗?" 会就是产品类。
## 版本号
**Semver 三元组**:`major.minor.patch`。
- **major** —— 不向后兼容的改动(schema 改了、CLI 参数改了、产物格式改了)
- **minor** —— 向后兼容的功能增加
- **patch** —— bug fix、性能优化、内部重构
我们的项目内部用三种写法,**三处必须同步**:
| 用途 | 格式 | 例子 | 在哪儿出现 |
| ------------ | ------------------ | ---------------- | ----------------------------------- |
| 内部版本号 | `X.Y.Z` | `0.2.4` | `package.json`、`pyproject.toml` |
| 显示版本号 | `VX.Y.Z` | `V0.2.4` | UI 胶囊、README 标题、release note |
| Git tag | `vX.Y.Z` | `v0.2.4` | Git tag 名 |
发布时**一个不能漏**的同步检查清单(用 task_assistant 举例):
```
package.json "version": "0.2.4"
public/index.html version chip 初始值
server.js fallback 版本
scripts/build-release.js fallback 版本 + release notes
scripts/build-release-windows.js fallback 版本 + release notes
README.md 标题、版本状态段
README.en.md 同上
```
每个项目都该在 README 里列一份"发版必改的版本字段"清单,**位置写
死**。漏一处下一版就漂移。
## Tag
```bash
git tag -a v0.2.4 HEAD -m "<project-name> V0.2.4"
git push <remote> v0.2.4
```
规则:
- 用 annotated tag(`-a`),不用 lightweight。
- Tag message 用英文,格式 `<Project Name> V<x.y.z>`,跟 displayVersion
一致。
- 一个版本一个 tag。同版本不同平台不要分多个 tag。
- 已经用于发行的 tag **不要移动**。错了发 patch(`v0.2.5`)覆盖。
- 误打的 tag 在**没用于发行前**可以删:
```bash
git tag -d v0.2.4
git push <remote> :refs/tags/v0.2.4
git tag -a v0.2.4 <correct-sha> -m "<Project> V0.2.4"
git push <remote> v0.2.4
```
## 分支策略
产品类项目至少有:
- **`dev`** —— 默认协作分支。日常开发、bug 修复、文档更新、发行前
准备都进这里。
- **功能分支** —— `<owner>/<slug>`,开 PR 合到 `dev`。
不留含义不清的 `master`。需要稳定分支时用明确名字,比如:
```
release/v0.3
release/v0.3-hotfix
```
发布从 `dev` 起步——拉取 → 检查 → 改版本号 → 打 tag → 构建 → 上传。
## Git 与分发分家
**Git 管源码,分发渠道(OpenList / Hugging Face / 其他)管发行物**。
两者职责不混。
进 Git:
- 源代码、构建脚本、文档、协作规范、必要的小型静态资源、模板、
role / 配置表。
不进 Git:
```
config/ 本地配置
logs/ 运行日志
feedback-records/ 用户反馈
generated_task_packages/ 任务输出
reports/ 验证报告
runtime-temp/ 临时运行态
release/ release-build/ release-dev/ release-merge/
.venv/ __pycache__/ node_modules/
```
进分发渠道(典型路径,按项目调):
```
/<project>/dist/ 面向使用者的发行 zip + manifest
/<project>/feedback/<machine-id>/ 用户上传的反馈
```
发行 zip **必须自包含**:用户解压点击就能跑,不在用户机器上装
依赖。具体内容随项目变,但原则不变。
## Manifest
每次发布在分发渠道根目录放一份 `manifest.json`,客户端启动时读它判
断有没有更新:
```json
{
"name": "<project-name>",
"version": "0.2.4",
"displayVersion": "V0.2.4",
"released_at": "2026-05-18T17:00:00Z",
"platforms": {
"windows": {
"url": "<dist-url>/<project>-v0.2.4-windows.zip",
"size": 123456789,
"sha256": "<hex>"
},
"macos-arm64": { "url": "...", "size": ..., "sha256": "..." },
"macos-x64": { "url": "...", "size": ..., "sha256": "..." }
},
"release_notes": "<short markdown>"
}
```
上传后**重新拉一遍** manifest,肉眼对一遍 size 和 sha256 是不是新的。
看到 size 跟旧版一致——分发渠道有缓存或上传出错。
## 更新机制
我们做的是"用户确认式更新",不是无人值守强推:
1. 客户端启动时拉 manifest,比版本号。
2. 有新版**提示用户**,不直接下载。
3. 用户点同意,下载到本地。
4. 用户点安装,重启生效。
任何一步不要替用户跳过。这条往后写进每个产品的 `CLAUDE.md` /
`AGENTS.md` 的"Don'ts"。
## 反馈与日志
反馈走"本地优先 + 异步上传":
```
本地:
feedback-records/feedback-<timestamp>-<id>.json
logs/<project>-YYYY-MM-DD.jsonl
云端(上传成功后):
/<project>/feedback/<machine-id>/<feedback-file>.json
```
规则:
- 上传**失败不影响本地保存**。UI 提示"本地已存,上传失败可重试"。
- 反馈和日志**必须脱敏**:API key、Bearer token、cookie、password、
secret、私密账号——发上去之前在客户端就抹掉。
- 排查问题时让用户走反馈页提交,**不要**让用户直接发 `config/` 或
完整日志目录。
## 敏感信息检查
提交前每次都做:
```bash
git diff --cached
```
定期跑关键词扫描(PowerShell 例子见 task_assistant 的
COLLABORATION_AND_RELEASE_WORKFLOW.md,bash 大致等价):
```bash
git grep -nE "sk-|hf_|Bearer |apiKey|ANTHROPIC_API_KEY|OPENAI_API_KEY|password|secret" \
-- ':!*.lock' ':!vendor/**' ':!**/__pycache__/**'
```
命中**必须人工判断**,不能照单提交,也不能照单删(注释里的 demo
key 跟真 key 都会命中)。
误提交真密钥的应急流程:
1. **立刻**让对应 key/token 失效。
2. 删除或更换本地配置。
3. 通知协作者。
4. 评估要不要重写 Git 历史(`git filter-repo` 或团队约定的方式)。
只追加一个"删除 key"的 commit 是**不够安全**的——历史里仍然能看到。
## 发版流程(标准动作)
```bash
# 1. 同步
git checkout dev
git pull --ff-only <remote> dev
git status --short --branch
# 2. 检查
<lint command>
<test command>
# 3. 改版本号(按本项目的"必改清单"逐项改)
# package.json、UI 胶囊、server.js、build script、README
# 4. commit + tag
git add <files>
git commit -m "chore: release vX.Y.Z"
git tag -a vX.Y.Z HEAD -m "<Project> VX.Y.Z"
git push <remote> dev
git push <remote> vX.Y.Z
# 5. 构建
<build command>
# 6. 上传 manifest + zip 到分发渠道,验证 size/sha256
```
## 产品 README 必备段落
每个产品类项目的 README,在通用 README 模板基础上,**额外**包含:
- **版本状态段** —— 当前源码版本、内部版本号、协作分支、协作仓库、
历史迁移来源(如果有)、默认本地服务地址(如果有)、默认输出
目录。
- **快速启动段** —— 按平台分(Windows / macOS / Linux),覆盖
解压、启动、访问、关闭。
- **发行包内置内容清单** —— 让用户知道完整包应该有什么。
- **发版必改字段清单** —— 给开发者的,写明哪些文件要同步改版本号。
人填模板见 [`templates/README.md.template`](../templates/README.md.template);
产品项目按上面清单加段落。
## 最低交付标准(每次"可给别人用"的版本)
照搬 task_assistant 的清单,按项目改:
- [ ] `<remote>/dev` 有对应 commit
- [ ] `<remote>` 有对应 tag(`v<x.y.z>`)
- [ ] `package.json` / `pyproject.toml` 版本正确
- [ ] UI 上版本胶囊显示正确
- [ ] Lint / typecheck / test 全通过
- [ ] 分发渠道 manifest 指向正确平台包
- [ ] manifest 的 size / sha256 与实际文件一致
- [ ] 发行包解压点击启动脚本即可运行
- [ ] 包内**没有** API key、日志、用户反馈、生成产物、验证报告
任意一项没勾——不算"可给别人用"。
## 项目里要落地什么
新建产品类项目时,除了 [`docs/02-claude-code.md`](02-claude-code.md)
里的标准(`CLAUDE.md` + `AGENTS.md` + `.claude/`),还要:
1. **`docs/COLLABORATION_AND_RELEASE_WORKFLOW.md`**(或类似名字)——
这份团队规范的项目特化版,包含本项目的版本字段清单、构建命令、
分发路径。task_assistant 那份就是范本。
2. **`scripts/build-release.*`** —— 构建脚本,输出 zip + 更新
`manifest.json`。
3. **发版必改字段清单** —— 写进 `CLAUDE.md` / `AGENTS.md` 或上面那份
workflow 里,**唯一来源**。
4. **CHANGELOG.md** —— 一个版本一段,按 semver 顺序排,简述用户能感
知的改动。
不必落地的(YAGNI):
- 复杂的发版编排工具(Lerna、Changesets)—— 人手够了。
- 自动化 release notes 生成 —— commit message 够好就够用。
- 多环境配置体系 —— 真有需要再说。
+69
View File
@@ -0,0 +1,69 @@
# AGENTS.md — <project name>
<!--
Template. Copy into a new repo and fill the bracketed sections.
Sister file: CLAUDE.md (Claude Code reads that one). Keep them in sync.
Delete sections that don't apply. Keep total length under ~100 lines.
-->
## Project
<One or two sentences. What does it do, who is it for.>
## Run it
```bash
# install
<command>
# run
<command>
# test
<command>
# lint / typecheck
<command>
```
## Architecture
<One paragraph. Where are the entry points, how does data flow, what
are the major modules. Skip diagrams unless they save words.>
Key files:
- `<path>` — <one-line role>
- `<path>` — <one-line role>
## Conventions specific to this repo
<Anything that's not obvious from reading the code. Naming patterns,
where to add new features, what's auto-generated, etc.>
## Language policy
<If this project follows the team's bilingual policy, copy this:>
- Human-facing docs (README, `docs/*.md`, human-fillable templates) are
in Chinese.
- AI-facing files (`CLAUDE.md`, `AGENTS.md`, AI-only templates) are in
English.
- Commit messages, PR titles, branch names, tag annotations: English.
## Don'ts
<Things Codex / Claude / a new contributor has gotten wrong before.
One line each. Add to this list as you discover them.>
- Don't <…>
- Don't <…>
## External resources
<Links to dashboards, related repos, docs, ticket trackers.>
## Sync
When you edit this file, also update `CLAUDE.md` (and vice versa). The
two files describe the same project to different tools.
+18 -2
View File
@@ -2,10 +2,11 @@
<!--
Template. Copy into a new repo and fill the bracketed sections.
Sister file: AGENTS.md (Codex reads that one). Keep them in sync.
Delete sections that don't apply. Keep total length under ~100 lines.
-->
## What this project is
## Project
<One or two sentences. What does it do, who is it for.>
@@ -40,9 +41,19 @@ Key files:
<Anything that's not obvious from reading the code. Naming patterns,
where to add new features, what's auto-generated, etc.>
## Language policy
<If this project follows the team's bilingual policy, copy this:>
- Human-facing docs (README, `docs/*.md`, human-fillable templates) are
in Chinese.
- AI-facing files (`CLAUDE.md`, `AGENTS.md`, AI-only templates) are in
English.
- Commit messages, PR titles, branch names, tag annotations: English.
## Don'ts
<Things Claude or a new contributor has gotten wrong before.
<Things Claude / Codex / a new contributor has gotten wrong before.
One line each. Add to this list as you discover them.>
- Don't <…>
@@ -51,3 +62,8 @@ One line each. Add to this list as you discover them.>
## External resources
<Links to dashboards, related repos, docs, ticket trackers.>
## Sync
When you edit this file, also update `AGENTS.md` (and vice versa). The
two files describe the same project to different tools.
+44 -50
View File
@@ -1,71 +1,65 @@
# Handoff checklist — <package or branch name>
# Handoff 清单 — <包名或分支名>
<!--
Fill this out before declaring the handoff complete.
Ships inside the package for external handoffs.
Lives in the PR description for internal handoffs.
交付前填完整。外部 handoff 一起放进包里;内部 handoff 放进 PR
description。正文中文,技术字段(commit hash、ISO 时间戳等)保留
英文格式。
-->
## Identity
## 身份信息
- **Name**: <package or branch name>
- **Version**: <e.g. v0.5.0 or commit sha>
- **Generated at**: <ISO timestamp>
- **Source repo**: <url>
- **Source commit**: <full sha>
- **Author / handoff owner**: <name>
- **Recipient**: <name or team>
- **名称**:<包名或分支名>
- **版本**:<比如 v0.5.0 或 commit sha 或 tag 比如 20260520>
- **生成时间**:<ISO 时间戳>
- **源仓库**:<url>
- **源 commit**:<full sha>
- **作者 / handoff owner**:<name>
- **接收方**:<name 或团队>
## Contents
## 内容物
- [ ] `README.md` — describes what this is, how to use it
- [ ] `CHANGELOG.md` — what's different from the previous version (or
"first release")
- [ ] `manifest.json` — machine-readable metadata, all fields filled or
explicitly null
- [ ] `VERIFICATION.md` — what we checked, what passed
- [ ] Data / artifacts — the actual deliverable
- [ ] Scripts — only what's needed to use the package
- [ ] `README.md` —— 这是什么、怎么用
- [ ] `CHANGELOG.md` —— 跟上一版的差异(首发就写"first release")
- [ ] `manifest.json` —— 机器可读元数据,所有字段都填了或显式 null
- [ ] `VERIFICATION.md` —— 检查了什么、结果如何
- [ ] 数据 / 产物 —— 真正的交付物
- [ ] 脚本 —— 仅限于使用本包必须的脚本
## Verification
## 验证
- [ ] Record / file counts match expected
- [ ] Checksums computed and recorded
- [ ] Sanity checks pass (list them)
- [ ] No secrets, `.env`, or credentials included
- [ ] No PII unless explicitly part of the deliverable
- [ ] Total size reasonable for delivery channel
- [ ] 记录数 / 文件数与预期一致
- [ ] Checksum 已计算并记录
- [ ] 合理性检查通过(列出来)
- [ ] 不含密钥、`.env`、credential
- [ ] 不含 PII(除非交付协议里就明确包含)
- [ ] 总大小在传输渠道可接受范围
Verification report path: `<path>`
验证报告路径:`<path>`
## Reproducibility
## 可重现性
- [ ] Confirmed someone with repo access can rebuild from
`source_commit` (note who tested this and when)
- [ ] Build / generation command documented in `README.md`
- [ ] External dependencies pinned to versions
- [ ] 已确认有源仓库访问的人能从 `source_commit` 重建产物(写明
谁测的、什么时候测的)
- [ ] 构建 / 生成命令写在 `README.md` 里
- [ ] 外部依赖锁版本
## Provenance (if AI-assisted)
## 来源(AI 协助生成时填)
- Model used: <e.g. claude-opus-4-7>
- Human-in-the-loop steps: <which parts a human reviewed / approved>
- Notable AI-assisted decisions: <anything that would matter if the
output looks wrong six months from now>
- 使用的模型:<比如 claude-opus-4-7、gpt-5-codex>
- 人工审核步骤:<人审 / 批准了哪些部分>
- 值得标注的 AI 决策:<半年后产物有问题时会想知道的事>
## Known limitations
## 已知限制
<Things that don't work, edge cases that aren't covered, follow-ups
that didn't make this version. Be specific. "Works on my machine" is
not a limitation, it's a problem to fix before shipping.>
<不能用的场景、未覆盖的边界、本版没赶上的后续。具体写。"在我机器
上能跑"不是限制——是发布前要修的问题。>
- <…>
- <…>
## Recipient instructions
## 给接收方的说明
- [ ] Read `README.md` first
- [ ] Run the verification report — if it fails, stop and contact the
sender
- [ ] Confirm receipt within <X days>
- [ ] Report any surprises (missing files, version mismatch, naming)
back to the sender within <X days>
- [ ] 先读 `README.md`
- [ ] 跑验证报告 —— 不通过就停下来联系发送方
- [ ] <X 天>内确认收到
- [ ] 任何意外(缺文件、版本不对、命名异常)<X 天>内反馈给发送方
+27 -30
View File
@@ -1,52 +1,49 @@
<!--
PR description template. Title goes in the PR title field, not here.
Title format: <area>: <imperative summary under 70 chars>
PR description 模板。标题写在 PR 标题栏,不在这里。
标题格式:<area>: <祈使句小结,70 字符以内>。英文。
正文中文。
-->
## Summary
## Summary(小结)
<One sentence describing what this PR does. Then 1–3 bullets if needed.>
<一句话说清这个 PR 干了什么。需要的话再加 1–3 条 bullet。>
- <bullet>
- <bullet>
## Why
## Why(为什么)
<The motivation. What problem does this solve, what decision does it
implement, what bug does it fix. If this links to an issue or earlier
discussion, link it here.>
<动机。解决什么问题、落实什么决策、修哪个 bug。如果挂着 issue
或者之前的讨论,链上来。>
## What changed
## What changed(改了什么)
<Bulleted list of the actual changes, grouped by area if it spans
multiple. Keep it factual — the diff is the source of truth, this is
just a map.>
<列出实际改动,跨多个区域时按区域分组。写事实就行——diff 是真相
来源,这只是地图。>
- `<file or area>` — <change>
- `<file or area>` — <change>
- `<文件或区域>` — <改动>
- `<文件或区域>` — <改动>
## Test plan
## Test plan(测试方案)
<Bulleted checklist. Mark `[x]` for done, `[ ]` for didn't do (and
explain why below). Be honest — "didn't test" is acceptable, "claimed
tested but didn't" is not.>
<勾选式 checklist。做了的勾 `[x]`,没做的留 `[ ]` 并在下面解释为什么。
诚实——"没测"可以接受,"声称测了但没测"不行。>
- [ ] Unit tests pass locally (`<command>`)
- [ ] Lint / typecheck pass (`<command>`)
- [ ] <feature-specific check>
- [ ] <feature-specific check>
- [ ] 单元测试本地通过(`<command>`)
- [ ] Lint / typecheck 通过(`<command>`)
- [ ] <功能特定的检查>
- [ ] <功能特定的检查>
## Out of scope
## Out of scope(范围外)
<Things you noticed but explicitly chose not to fix in this PR. Helps
reviewers not bring them up.>
<你注意到但**显式选择不在这个 PR 修**的东西。帮 reviewer 不要在这些
点上提出来。>
## Notes for reviewer
## Notes for reviewer(给 reviewer 的提示)
<Anything that surprised you, AI-assisted decisions worth flagging,
shortcuts taken, or "I considered X but went with Y because Z". Skip
this section if there's nothing notable.>
<让你意外的地方、值得标注的 AI 协作决策、走过的捷径,或者"我考虑
过 X 但选了 Y 因为 Z"。没什么可写就删掉这一节。>
---
🤖 AI-assisted with Claude Code.
🤖 AI 协助完成(Claude Code / Codex)。
+24 -24
View File
@@ -1,62 +1,62 @@
# <project name>
# <项目名>
<One sentence. What this is, in plain language.>
<一句话。这是什么,用大白话写。>
## What it does
## 这玩意儿干啥的
<One paragraph. Slightly more detail than the tagline. Who would use
it, what problem it solves, what it explicitly does not do.>
<一段话。比 tagline 多点细节。谁会用、解决什么问题、明确**不**做
什么。>
## Quick start
## 快速上手
```bash
# clone
git clone <url>
cd <repo>
# install
# 安装
<command>
# run
# 跑起来
<command>
```
Expected output:
预期输出:
```
<a few lines of what the user should see>
<几行用户应该看到的内容>
```
## Development
## 开发
```bash
# tests
# 测试
<command>
# lint / typecheck
<command>
# format
# 格式化
<command>
```
Code lives in `<dir>`. Tests live in `<dir>`. See [docs/](docs/) for
deeper architecture notes (or delete this line if there are none).
代码在 `<dir>`。测试在 `<dir>`。架构细节看 [docs/](docs/)(没有就
删掉这行)。
## Configuration
## 配置
<Env vars, config files, secrets. Point to a `.env.example` if there is
one. Don't list real values.>
<env var、配置文件、密钥。指向 `.env.example` 如果有的话。不写真实
值。>
## Data sources / outputs
## 数据来源 / 流向
<Only if non-obvious. Where does input come from, where do outputs go.>
<仅当不显然时写。输入从哪来,输出到哪去。>
## Related
## 相关链接
- <link>
- <link>
- <链接>
- <链接>
## License
<Internal / MIT / etc.>
<Internal / MIT / 等等。>