Squashed 'docs/standards/playbook/' changes from c3f8137..25d895d

25d895d 🐛 fix(gitea_workflow): clean up temp repos after job steps 2bc3b11 🐛 fix(gitea_workflow): clean up temporary repo dirs in workflows 98c3f30 📝 docs(agent_rules): allow plan execution on current branch 16c7230 📝 docs(prompts): define custom verify layering 8efc4dd 🐛 fix(skills): quote commit-message description bc8498f 🐛 fix(ci): install tomli for gitea tests 55cda3b 🐛 fix(tests): report missing toml parser clearly c0729c7 🐛 fix(playbook): import Optional for cli compatibility 63e24bf 📦 deps(skills): sync thirdparty skills d2f9356 🐛 fix(ci): isolate gitea workflow repos 588b81d 🐛 fix(ci): inline gitea workflow bootstrap e0b1c3a ♻️ refactor(skills): standardize first-party skill contracts 2c5050d ♻️ refactor(skills): rename repo skills source dir f049dfb 📦 deps(skills): drop duplicate first-party superpowers skills 234b335 ✨ feat(workflow): add superpowers planning and execution state tracking c1702a6 📝 docs(markdown): format tracked markdown and drop stale templates 2325409 📝 docs(markdown): clarify optional markdownlint usage 214c44e 🔧 chore(markdown): add markdownlint baseline and lint fixes a22b324 📝 docs(templates): add execution and memory-bank prompt templates 223a797 📝 docs(templates): update README for Claude Code and current features 4ac8672 📝 docs: simplify README + platform-agnostic tools + auto-create local rules 2431c9d 📝 docs: add claude_md config and use cross-platform paths d64b248 📝 docs: fix README.md inaccuracies and add Claude Code info c8d6bf2 🐛 fix(playbook): use relative paths in CLAUDE.md when not at project root 6518f0f ✨ feat(playbook): auto-create CLAUDE.md with path discovery 6ec9a45 ✨ feat(skills): add skill_link symlink support + platform-agnostic prompt 9f8b6b5 📝 docs: update README and config example for Claude Code support 79cff6c 📝 docs(skills): add Claude Code platform support 452c6f5 ✨ feat(playbook): auto-inject AGENTS.md into CLAUDE.md e1dbf3c 🐛 fix(skills): remove dual-path from commit-message skill f3a7259 🔧 chore(ci): use prepare_repo.sh in both workflows da08212 🔧 chore(ci): extract prepare_repo.sh and clean up workflows 7ade85e 🗑️ remove(tsl): drop syntax_book/, data/ source and build script f94dba0 ♻️ refactor(skills): update playbook.py and tests for thirdparty/ layout b3df412 ♻️ refactor(skills): separate thirdparty skills into thirdparty/ subdirectory 64950e7 📦 deps(skills): sync thirdparty skills a2e3cb0 ✨ feat(playbook): add no_backup deploy controls 8609d59 🐛 fix(docs): repair reference catalog source links 956da11 🐛 fix(playbook): publish hidden ci test fixes 3f67754 📦 deps(skills): sync thirdparty skills 08ca87b 📦 deps(skills): add karpathy thirdparty sync 96b705b 📝 docs(tsl): rebuild canonical syntax and routing manual 3ed5052 📦 deps(skills): sync thirdparty skills 60108dd 📦 deps(skills): sync thirdparty skills da85d4e 🐛 fix(thirdparty): prune nested project snapshots a2a697e 📦 deps(skills): sync thirdparty skills 9df610a 🐛 fix(thirdparty): exclude duplicated superpowers skills 33dd5bb 🐛 fix(thirdparty): preserve optional manifest fields 91b0ea7 🐛 fix(thirdparty): preserve manifest during snapshot update 2e26f98 🔧 chore(thirdparty): generalize skills sync pipeline 5b9c1e3 📦 deps(skills): sync superpowers 2f2d34a 📝 docs(readme): normalize subtree command spacing 62db7db 🐛 fix(ci): serialize superpowers update and sync 3463223 🐛 fix(ci): use literal superpowers sync paths 48f6de8 📦 deps(skills): sync superpowers 4b23529 🔧 chore(ci): merge superpowers update and sync workflow a56d75b 📦 deps(skills): sync superpowers 84bcefa 🔧 chore(ci): use ci[bot] commit author name 00a07e5 📦 deps(skills): sync superpowers 7b84daf 🐛 fix(templates): enforce main loop progress tracking 51373d7 🔧 chore(ci): automate superpowers sync workflow eaaa39c 🐛 fix(ci): prevent stale superpowers sync from restoring skills block 79755c6 📦 deps(skills): sync superpowers 836d878 📦 deps(skills): sync superpowers 8216c9f 📦 deps(skills): sync superpowers 9439505 🐛 fix(playbook): address reported repo issues git-subtree-dir: docs/standards/playbook git-subtree-split: 25d895d8b3f56624ccfe99ad7289e9eb49e0f316
2026-05-24 13:04:14 +08:00
parent 35e6a301aa
commit 3d83740f88
292 changed files with 30774 additions and 218828 deletions
@@ -1,17 +1,22 @@
 # SKILLS

-本文件定义：如何在仓库中落地与维护 **Codex CLI skills**（实验功能），
+本文件定义：如何在仓库中落地与维护 **AI agent skills**，
 并给出与本 Playbook（`docs/` + `rulesets/`）配套的技能编写建议与内置技能清单。

-> 提示：Codex skills 是“按用户安装”的（默认在
-> `~/.agents/skills`）。本仓库将 skills 以可分发的形式放在
-> `codex/skills/`，并提供脚本一键安装到你的 `~/.agents`。
+支持的平台：
+
+| 平台        | skills 目录         |
+| ----------- | ------------------- |
+| Codex CLI   | `~/.agents/skills/` |
+| Claude Code | `~/.claude/skills/` |
+
+> 提示：本仓库将 skills 以可分发的形式放在 `skills/`，并提供脚本一键安装到对应平台目录。

 ---

 ## 1. 启用 skills（必做）

-在 `$CODEX_HOME/config.toml`（通常是 `~/.codex/config.toml`）中启用：
+**Codex CLI** — 在 `~/.codex/config.toml` 中启用：

 ```toml
 [features]
@@ -20,41 +25,64 @@ skills = true

 修改后需要重启 `codex` 才会重新发现技能。

+**Claude Code** — 在 `~/.claude/settings.json` 中启用（或通过 `/config` 命令）：
+
+```json
+{
+  "skills": true
+}
+```
+
 ---

 ## 2. 本仓库的 skills 目录结构

-本 Playbook 以“可 vendoring”的方式提供 skills：
+本 Playbook 以“可分发、可安装”的方式提供 skills：

 ```txt
-codex/skills/
-  <skill-name>/
+skills/
+  <skill-name>/         # 本仓库自维护
    SKILL.md
    references/        # 可选：拆分参考文档
    templates/         # 可选：模板
    scripts/           # 可选：脚本/命令封装
+  thirdparty/          # 第三方同步（不可手动修改）
+    <skill-name>/
+      SKILL.md
+    .sources/          # 第三方来源清单
 ```

 最终安装到本机后，对应路径为：

-```txt
-~/.agents/skills/<skill-name>/SKILL.md
-```
+| 平台        | 路径                                     |
+| ----------- | ---------------------------------------- |
+| Codex CLI   | `~/.agents/skills/<skill-name>/SKILL.md` |
+| Claude Code | `~/.claude/skills/<skill-name>/SKILL.md` |

 ---

 ## 3. 安装到本机（推荐）

-使用统一入口 `playbook.py` 安装 skills（会把 `codex/skills/*` 复制到 `~/.agents/skills/`）：
+使用统一入口 `playbook.py` 安装 skills，通过 `agents_home` 指定目标平台目录：
+
+**Codex CLI：**

 ```toml
 # playbook.toml
 [playbook]
-project_root = "."
+project_root = “.”

 [install_skills]
-mode = "all"            # list|all
-agents_home = "~/.agents"
+mode = “all”
+agents_home = “~/.agents”
+```
+
+**Claude Code：**
+
+```toml
+[install_skills]
+mode = “all”
+agents_home = “~/.claude”
 ```

 ```bash
@@ -65,32 +93,31 @@ python scripts/playbook.py -config playbook.toml

 ```toml
 [install_skills]
-mode = "list"
-skills = ["style-cleanup", "commit-message"]
+mode = “list”
+skills = [“style-cleanup”, “commit-message”]
+agents_home = “~/.claude”   # 或 ~/.agents
 ```

-如果希望“项目内本地安装”（不污染全局）：
+`[install_skills]` 默认会先把已存在的 skill 目录重命名为 `*.bak.<timestamp>`，再复制新版本，便于手动回退。若不需要备份：

 ```toml
 [install_skills]
-mode = "all"
-agents_home = "./.agents"
+mode = “all”
+agents_home = “~/.claude”
+no_backup = true
 ```

-> 注意：Codex 默认从 `~/.agents/skills` 加载 skills；使用本地安装时，需要确保 Codex 能发现该路径。
-
-如果你的项目通过 `git subtree` vendoring 本 Playbook（推荐前缀
-`docs/standards/playbook`），则在目标项目里执行：
+如果你的项目已经把本 Playbook 部署到项目内，则在目标项目里执行：

 ```bash
-python docs/standards/playbook/scripts/playbook.py -config playbook.toml
+python <deploy_root>/scripts/playbook.py -config playbook.toml
 ```

-安装后重启 `codex`，即可在运行时看到 `## Skills` 列表。
+其中 `<deploy_root>` 默认为 `docs/standards/playbook`。

 ---

-## 4. `SKILL.md` 最小规范（Codex）
+## 4. `SKILL.md` 最小规范

 - 文件名必须是 `SKILL.md`
 - 必须包含 YAML frontmatter（用 `---` 包裹），且至少包含：
@@ -103,7 +130,8 @@ python docs/standards/playbook/scripts/playbook.py -config playbook.toml
 ## 5. 使用方式

 - 在对话中通过 `$<skill-name>` 直接点名触发（例如：`$style-cleanup`）
- 在 Codex TUI 中可用 `/skills` 浏览与插入
+- Codex TUI：可用 `/skills` 浏览与插入
+- Claude Code：通过 `/skills` 命令或直接在对话中触发

 ---

@@ -129,24 +157,19 @@ python docs/standards/playbook/scripts/playbook.py -config playbook.toml
 - C++：`docs/cpp/code_style.md`、`docs/cpp/naming.md`、`docs/cpp/toolchain.md`
 - Python：`docs/python/style_guide.md`、`docs/python/tooling.md`、`docs/python/configuration.md`

-若你的项目通过 git subtree 引入本 Playbook，常见路径为
-`docs/standards/playbook/docs/...`；把上述 `docs/` 前缀替换为
-`docs/standards/playbook/docs/` 即可。
+若你的项目把本 Playbook 部署到项目内，文档根路径为
+`<deploy_root>/docs/...`；其中 `<deploy_root>` 默认为 `docs/standards/playbook`，也可以按项目配置改成 `custom/playbook` 等自定义目录。

 ---

 ## 8. 本 Playbook 原生 skills

-位于 `codex/skills/`（Playbook 自维护部分），当前共 4 个。
-第三方 superpowers 列表见第 9 节。
+位于 `skills/`（Playbook 自维护部分），当前共 3 个。
+第三方 skills 来源见第 9 节。

 ### 语言特定 Skills

- **`tsl-guide`**：TSL/TSF 语法与编码完整指南
-  - 渐进式教学体系：基础语法 → 高级特性 → 函数库 → 最佳实践
-  - 包含 4 个子文档：primer.md / advanced.md / functions_index.md / common_patterns.md
-  - 总计约 1000 行，按需加载
-  - 触发词：TSL 语法, 写 TSL, TSL 函数, TSL class, 矩阵操作, TS-SQL 等
+当前仓库不再内置语言特定 skill；TSL 相关问题请直接查阅 `rulesets/tsl/index.md` 与 `docs/tsl/`。

 ### 通用工作流 Skills

@@ -156,46 +179,30 @@ python docs/standards/playbook/scripts/playbook.py -config playbook.toml

 ---

-## 9. Third-party Skills (superpowers)
+## 9. Third-party Skills

-来源：`codex/skills/.sources/superpowers.list`（第三方来源清单）。
-本节仅列出 superpowers 体系 skills，与本 Playbook 原生 skills 分离。
+来源：`skills/thirdparty/.sources/`（第三方来源清单目录）。

-### Third-party Skills (superpowers)
+- `superpowers.list`
+- `ui-ux-pro-max.list`
+- `andrej-karpathy-skills.list`

-### Third-party Skills (superpowers)
+部署链路：

-### Third-party Skills (superpowers)
-
-### Third-party Skills (superpowers)
-
-<!-- superpowers:skills:start -->
- \
- \
- \
- \
- \
- \
- \
- \
- \
- \
- \
- \
- \
- \
-<!-- superpowers:skills:end -->
+- `thirdparty/skill` 分支保存上游快照 `andrej-karpathy-skills/`
+- 自动同步后，`karpathy-guidelines/` 会落到仓库内 `skills/thirdparty/karpathy-guidelines/`
+- 运行 `[install_skills]` 时，再复制到目标平台 skills 目录（`~/.agents/skills/` 或 `~/.claude/skills/`）
+- 该 skill 本身不依赖 Playbook 文档路径重写，也不需要像 `ui-ux-pro-max` 那样额外渲染

 ---

 ## 10. 运行时排障

 - 不触发：
-  - 确认已启用 `[features] skills = true`
-  - 确认 skill 已安装到 `$CODEX_HOME/skills/<name>/SKILL.md`
-  - 重启 `codex`（skills 只在启动时加载）
- 触发错：减少不同 skill 的 `description`
-  关键词重叠；让触发词更具体（语言/工具/目录名/流程名）。
+  - Codex：确认已启用 `[features] skills = true`，重启 `codex`
+  - Claude Code：确认 skills 已启用，重启 Claude Code
+  - 确认 skill 已安装到对应平台目录（`~/.agents/skills/` 或 `~/.claude/skills/`）
+- 触发错：减少不同 skill 的 `description` 关键词重叠；让触发词更具体（语言/工具/目录名/流程名）。
 - 启动报错：通常是 YAML frontmatter 不合法或字段超长；修复后重启即可。

 ---