reconcile-claude-md
Update the project's CLAUDE.md to match its current structure and conventions.
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。
菜单
Update the project's CLAUDE.md to match its current structure and conventions.
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。
基于 SOC 职业分类
Make a set of things (code, prose, config, docs) consistent along a dimension the user names, by picking a canonical form and conforming every member to it.
Remove illegal states from data structures by redesigning their types so the illegal states cannot be represented at all.
Remove unnecessary comments from code: tombstones, redundant restatements, and comments a well-named variable or function would replace.
Perform a task with a worker agent, critique it with an adversary agent, and apply the accepted critiques with a reconciler agent.
Replace jargon and imported metaphors in code and prose with concrete, domain-fitting terms a reader understands without translation.
Create a new Claude Code skill following the conventions of existing skills.
| name | reconcile-claude-md |
| description | Update the project's CLAUDE.md to match its current structure and conventions. |
| argument-hint | [extra guidance or areas to focus on] |
Update the project's CLAUDE.md to match its current structure and conventions.
cat CLAUDE.md
$ARGUMENTS
/init and stopCLAUDE.md should have a shallow tree-style code block of the layout:
**/<name>/) annotated with
the pattern its contents followCLAUDE.md earns its tokens only with facts Claude can't cheaply derive:
These aren't exhaustive. Reason from first principles when none fits cleanly.