AgentSkillsCN

optimizing-claude-code

对代码库进行 Claude 代码就绪度审计，并提出改进建议。当用户要求检查 CLAUDE.md 的质量、审查设置、评估项目组织结构，或为代理式工作进行优化时，可使用此功能。

SKILL.md
--- frontmatter
name: optimizing-claude-code
description: Audits repositories for Claude Code readiness and suggests improvements. Use when asked to check CLAUDE.md quality, review settings, audit project organization, or optimize for agentic work.

Optimizing Claude Code

Default: Audit-only. Present findings and await approval before modifying files.

Workflow

1. Run Audit

Execute from repo root:

bash
python scripts/audit_repo.py --root . --include-user-scope

Analyzes:

  • •Repository scale and directory hotspots
  • •CLAUDE.md files (discovery, quality, @imports)
  • •Settings (user/project/local scopes)
  • •MCP configurations
  • •Skills and subagents

2. Generate Report

Structure output as:

Executive Summary (5 bullets max)

  • •Readiness assessment
  • •Key strengths
  • •Critical gaps
  • •Priority actions

Repository Profile

  • •File count and scale (Small/Medium/Large)
  • •Primary language/framework

Memory Files Assessment

  • •Per-file metrics
  • •@import validation
  • •Content quality
  • •Staleness indicators

Settings & Configuration

  • •Permissions analysis
  • •MCP server inventory
  • •Skills/subagents discovered

Issues by Priority

  • •P0: Blocks agentic work
  • •P1: High impact
  • •P2: Nice-to-have

Recommendations

  • •Specific suggested edits
  • •Reference best practices
  • •Do NOT apply without approval

3. Apply Changes (If Requested)

When asked to implement:

  1. •Confirm which changes
  2. •Edit incrementally
  3. •Show diffs
  4. •Re-audit to verify

Large Repository Guidance

When file count exceeds 3000, include scaling recommendations:

  • •Vanilla context becomes unreliable at scale
  • •Consider context engines or retrieval layers
  • •Strategic CLAUDE.md placement becomes critical
  • •Focus on navigation aids over exhaustive documentation

Reference Files

  • •best-practices.md: Environment setup, CLAUDE.md structure, prompting patterns, workflows, safety
  • •rubric.md: CLAUDE.md scoring criteria (0-16 scale), anti-patterns, templates
  • •checklist.md: Step-by-step audit workflow, prioritization guide