创建、审计并完善项目 CLAUDE.md 说明文件
Scanned 9/2/2026
Install to Claude Code
npx -y skills add wangzhe04/ruyi-workbench-oss --skill claude-md-management --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Claude Md Management?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wangzhe04-claude-md-management)More formats (shields.io, HTML) on the badges page.
---
name: 项目记忆管理
description: 创建、审计并完善项目 CLAUDE.md 说明文件
---
# CLAUDE.md Management
Use this skill to create, audit, or improve project `CLAUDE.md` files for offline Claude Code use.
Workflow:
1. Run `claude_md_audit` to find existing instruction files and gaps.
2. Use `project_snapshot`, `dependency_inventory`, and local README files to identify real commands and conventions.
3. Keep `CLAUDE.md` short, project-specific, and executable.
4. Include offline constraints: no public downloads, no external services unless explicitly configured, and where vendored docs/resources live.
5. Add safe working rules for tests, generated files, secrets, and user edits.
6. Verify every command path or script before writing it.
Recommended sections:
- Project purpose
- Local setup and offline resources
- Build/test commands
- Coding conventions
- Safety boundaries
- Useful MCP tools
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...