菜单
Sync plans, docs, and instruction files after behavior, commands, contracts, or workflows change. Also covers harness-internal consistency after skill, hook, rule, or script changes. Invoked after /test and before /cross-review as the doc-maintainer agent; inline execution is only a dispatch-failure fallback.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/yoshpy-dev/ralph --skill sync-docs命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Lead's operating manual for the org runtime. Use it to organize, oversee, and disband an org (its seats). Auto-invoked when promoting the current session to Lead to organize seats, or when the headless lead (`ralph org start`) needs its operating procedure.
Execute an approved plan in small coherent slices from an isolated task worktree, updating progress, evidence, and docs as implementation evolves. Invoke automatically after an approved plan exists and the task worktree is ready.
Sync plans, docs, and instruction files after behavior, commands, contracts, or workflows change. Also covers harness-internal consistency after skill, hook, rule, or script changes. Invoked after /test and before /cross-review as the doc-maintainer agent; inline execution is only a dispatch-failure fallback.
正在显示 SKILL.md
| name | sync-docs |
| description | Sync plans, docs, and instruction files after behavior, commands, contracts, or workflows change. Also covers harness-internal consistency after skill, hook, rule, or script changes. Invoked after /test and before /cross-review as the doc-maintainer agent; inline execution is only a dispatch-failure fallback. |
Use this skill when implementation or harness structure changed enough that documentation may have drifted.
Update, as needed:
README.mdAGENTS.mdCLAUDE.md.claude/rules/docs/quality/docs/reports/ links or referencesKeep AGENTS.md short and stable. If a new rule is path- or topic-specific, put it in .claude/rules/ instead.
When skills, hooks, rules, scripts, or language packs changed, also check:
AGENTS.md Repo map still reflect the skill set? Does README.md list the current operating loop?.claude/settings.json reference the correct hook scripts? Are removed hooks cleaned out?.claude/rules/ match the languages and topics actually in the project? Are paths: globs still accurate?scripts/detect-languages.sh detect the language? Is there a matching .claude/rules/ralph/<lang>.md? Does packs/languages/<lang>/verify.sh run a real verifier (not the placeholder)?README.md Quick Start still reference valid scripts? Does docs/architecture/repo-map.md list the current scripts?docs/quality/definition-of-done.md match the actual completion workflow in /work? Does docs/quality/quality-gates.md list verifiers that actually exist?/pr SKILL.md pre-checks align with /self-review, /verify, and /test output? Does the PR template match the current plan template fields? Does AGENTS.md primary loop include the PR step?This skill runs under both Claude Code and Codex. The execution mode follows
the conventions in AGENTS.md and .codex/AGENTS.override.md.
| Aspect | Claude Code | Codex |
|---|---|---|
| Skill invocation | /skill-name slash command | $skill-name mention or the /skills menu (avoid the /skill-name form — it collides with built-ins) |
| Skill body path | .claude/skills/<name>/SKILL.md | .agents/skills/<name>/SKILL.md |
| Subagent mechanism | Task(subagent_type=...) when a policy delegates | .codex/agents/ custom agents when a policy delegates |
| Structured prompts | AskUserQuestion | Numbered options printed to stdout, awaiting a digit reply |
| Artifacts | docs/reports/, docs/plans/, docs/specs/ (shared) | Same (CLI-agnostic) |
The drift check (./scripts/check-skill-sync.sh) cross-checks both bodies and
invocation metadata — editing only one side will fail CI.