← 返回
未分类

Refactor AGENTS.md

Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or revie...
将 AGENTS.md 文件重构为最小根文件加主题特定的跟进文档,采用渐进式披露。用于清理、拆分或审查...
clarezoe clarezoe 来源
未分类 clawhub v1.0.2 2 版本 100000 Key: 无需
★ 0
Stars
📥 292
下载
💾 0
安装
2
版本
#agents-md#ai-config#claude-md#developer-tools#latest#progressive-disclosure#refactoring

概述

Refactor AGENTS.md files so the root file stays small, stable, and broadly useful while detailed guidance moves into focused follow-up docs. The skill helps identify contradictions, separate essentials from bloat, and produce a clearer instruction hierarchy that is easier for agents to follow.

  1. Identify whether the user wants a review, a rewrite proposal, or an in-repo refactor.
  2. Read the current AGENTS.md content and classify each instruction as root-essential, topic-specific, conflicting, redundant, vague, or stale.
  3. Keep only universal instructions in the root file, move the rest into topic docs, and surface any contradictions before editing.

The root AGENTS.md should contain only what applies to every task: a one-line project description, package manager expectations if non-default, non-standard build or typecheck commands, and truly universal constraints.

If two instructions disagree, do not silently merge them. Surface the conflict, explain the tradeoff briefly, and ask the user which version to keep before rewriting.

Move remaining guidance into separate files grouped by topic or behavior, not by author, chronology, or file location.

Flag redundant, vague, self-evident, or outdated instructions for deletion instead of preserving them in a new location.

Keep the root file as a router into narrower guidance. Detail belongs in follow-up docs that are only read when relevant.

Ask the user which mode they want:

  1. Review only
  2. Propose a rewrite
  3. Apply the refactor in the repo

If the user already gave enough context, skip extra questions and go straight to the matching workflow.

workflows/audit-agents-md.md

workflows/audit-agents-md.md

workflows/refactor-agents-md.md

All shared guidance lives in references/:

Principles and heuristics: references/principles.md

Review an AGENTS.md file, classify instructions, and propose a minimal split.

Inspect the repo and rewrite AGENTS.md files in place.

The skill is complete when it can consistently:

  • identify contradictions before rewriting
  • keep root AGENTS.md content minimal
  • split topic-specific guidance into separate docs
  • flag redundant, vague, and stale instructions for deletion
  • produce a clear proposed file structure or apply it in the repo

版本历史

共 2 个版本

  • v1.0.2 当前
    2026-06-11 17:58
  • v1.0.0
    2026-05-21 14:23 安全 安全

安全检测

腾讯云安全 (Keen)

队列中

腾讯云安全 (Sanbu)

队列中

🔗 相关推荐

dev-programming

YouTube

byungkyu
使用托管OAuth集成YouTube Data API,支持搜索视频、管理播放列表、获取频道数据及评论互动,适用于用户需要时使用此技能。
★ 142 📥 42,218
dev-programming

Github

steipete
使用 `gh` CLI 与 GitHub 交互,通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。
★ 688 📥 331,768
ai-agent

Close Loop

clarezoe
会话结束流程:交付变更、整合记忆、应用自我改进,并在安全门控制下准备发布成果。
★ 2 📥 1,753