{"id":"192efc35-203c-4286-ac56-5f3e49e309f7","shortId":"CT6LT4","kind":"skill","title":"optimizing-claude-code","tagline":"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.","description":"# Optimizing Claude Code\n\n**Default**: Audit-only. Present findings and await approval before modifying files.\n\n## Workflow\n\n### 1. Run Audit\n\nExecute from repo root:\n\n```bash\npython scripts/audit_repo.py --root . --include-user-scope\n```\n\nAnalyzes:\n- Repository scale and directory hotspots\n- CLAUDE.md files (discovery, quality, @imports)\n- Settings (user/project/local scopes)\n- MCP configurations\n- Skills and subagents\n\n### 2. Generate Report\n\nStructure output as:\n\n**Executive Summary** (5 bullets max)\n- Readiness assessment\n- Key strengths\n- Critical gaps\n- Priority actions\n\n**Repository Profile**\n- File count and scale (Small/Medium/Large)\n- Primary language/framework\n\n**Memory Files Assessment**\n- Per-file metrics\n- @import validation\n- Content quality\n- Staleness indicators\n\n**Settings & Configuration**\n- Permissions analysis\n- MCP server inventory\n- Skills/subagents discovered\n\n**Issues by Priority**\n- P0: Blocks agentic work\n- P1: High impact\n- P2: Nice-to-have\n\n**Recommendations**\n- Specific suggested edits\n- Reference best practices\n- Do NOT apply without approval\n\n### 3. Apply Changes (If Requested)\n\nWhen asked to implement:\n1. Confirm which changes\n2. Edit incrementally\n3. Show diffs\n4. Re-audit to verify\n\n## Large Repository Guidance\n\nWhen file count exceeds 3000, include scaling recommendations:\n- Vanilla context becomes unreliable at scale\n- Consider context engines or retrieval layers\n- Strategic CLAUDE.md placement becomes critical\n- Focus on navigation aids over exhaustive documentation\n\n## Reference Files\n\n- **[best-practices.md](references/best-practices.md)**: Environment setup, CLAUDE.md structure, prompting patterns, workflows, safety\n- **[rubric.md](references/rubric.md)**: CLAUDE.md scoring criteria (0-16 scale), anti-patterns, templates\n- **[checklist.md](references/checklist.md)**: Step-by-step audit workflow, prioritization guide","tags":["optimizing","claude","code","driven","development","codealive-ai","agent-safety","agent-skills","ai-coding","ai-driven-development","ai-safety","antigravity"],"capabilities":["skill","source-codealive-ai","skill-optimizing-claude-code","topic-agent-safety","topic-agent-skills","topic-ai-coding","topic-ai-driven-development","topic-ai-safety","topic-antigravity","topic-bash","topic-claude-code","topic-codex-cli","topic-cursor","topic-developer-tools","topic-gemini-cli"],"categories":["ai-driven-development"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/CodeAlive-AI/ai-driven-development/optimizing-claude-code","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add CodeAlive-AI/ai-driven-development","source_repo":"https://github.com/CodeAlive-AI/ai-driven-development","install_from":"skills.sh"}},"qualityScore":"0.483","qualityRationale":"deterministic score 0.48 from registry signals: · indexed on github topic:agent-skills · 67 github stars · SKILL.md body (1,888 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:57:07.067Z","embedding":null,"createdAt":"2026-05-04T06:56:23.440Z","updatedAt":"2026-05-18T18:57:07.067Z","lastSeenAt":"2026-05-18T18:57:07.067Z","tsv":"'-16':236 '0':235 '1':47,167 '2':81,171 '3':158,174 '3000':190 '4':177 '5':89 'action':99 'agent':29,136 'aid':214 'analysi':125 'analyz':62 'anti':239 'anti-pattern':238 'appli':155,159 'approv':42,157 'ask':16,164 'assess':93,111 'audit':5,23,36,49,180,248 'audit-on':35 'await':41 'bash':54 'becom':196,209 'best':151 'best-practices.md':220 'block':135 'bullet':90 'chang':160,170 'check':18 'checklist.md':242 'claud':3,8,32 'claude.md':19,68,207,224,232 'code':4,9,33 'configur':77,123 'confirm':168 'consid':200 'content':118 'context':195,201 'count':103,188 'criteria':234 'critic':96,210 'default':34 'diff':176 'directori':66 'discov':130 'discoveri':70 'document':217 'edit':149,172 'engin':202 'environ':222 'exceed':189 'execut':50,87 'exhaust':216 'file':45,69,102,110,114,187,219 'find':39 'focus':211 'gap':97 'generat':82 'guid':251 'guidanc':185 'high':139 'hotspot':67 'impact':140 'implement':166 'import':72,116 'improv':13 'includ':59,191 'include-user-scop':58 'increment':173 'indic':121 'inventori':128 'issu':131 'key':94 'language/framework':108 'larg':183 'layer':205 'max':91 'mcp':76,126 'memori':109 'metric':115 'modifi':44 'navig':213 'nice':143 'nice-to-hav':142 'optim':2,27,31 'optimizing-claude-cod':1 'organ':25 'output':85 'p0':134 'p1':138 'p2':141 'pattern':227,240 'per':113 'per-fil':112 'permiss':124 'placement':208 'practic':152 'present':38 'primari':107 'priorit':250 'prioriti':98,133 'profil':101 'project':24 'prompt':226 'python':55 'qualiti':20,71,119 're':179 're-audit':178 'readi':10,92 'recommend':146,193 'refer':150,218 'references/best-practices.md':221 'references/checklist.md':243 'references/rubric.md':231 'repo':52 'report':83 'repositori':6,63,100,184 'request':162 'retriev':204 'review':21 'root':53,57 'rubric.md':230 'run':48 'safeti':229 'scale':64,105,192,199,237 'scope':61,75 'score':233 'scripts/audit_repo.py':56 'server':127 'set':22,73,122 'setup':223 'show':175 'skill':78 'skill-optimizing-claude-code' 'skills/subagents':129 'small/medium/large':106 'source-codealive-ai' 'specif':147 'stale':120 'step':245,247 'step-by-step':244 'strateg':206 'strength':95 'structur':84,225 'subag':80 'suggest':12,148 'summari':88 'templat':241 'topic-agent-safety' 'topic-agent-skills' 'topic-ai-coding' 'topic-ai-driven-development' 'topic-ai-safety' 'topic-antigravity' 'topic-bash' 'topic-claude-code' 'topic-codex-cli' 'topic-cursor' 'topic-developer-tools' 'topic-gemini-cli' 'unreli':197 'use':14 'user':60 'user/project/local':74 'valid':117 'vanilla':194 'verifi':182 'without':156 'work':30,137 'workflow':46,228,249","prices":[{"id":"ff6ed62c-f0e8-4181-a9c6-ca341f165bb4","listingId":"192efc35-203c-4286-ac56-5f3e49e309f7","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"CodeAlive-AI","category":"ai-driven-development","install_from":"skills.sh"},"createdAt":"2026-05-04T06:56:23.440Z"}],"sources":[{"listingId":"192efc35-203c-4286-ac56-5f3e49e309f7","source":"github","sourceId":"CodeAlive-AI/ai-driven-development/optimizing-claude-code","sourceUrl":"https://github.com/CodeAlive-AI/ai-driven-development/tree/main/skills/optimizing-claude-code","isPrimary":false,"firstSeenAt":"2026-05-04T06:56:23.440Z","lastSeenAt":"2026-05-18T18:57:07.067Z"}],"details":{"listingId":"192efc35-203c-4286-ac56-5f3e49e309f7","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"CodeAlive-AI","slug":"optimizing-claude-code","github":{"repo":"CodeAlive-AI/ai-driven-development","stars":67,"topics":["agent-safety","agent-skills","ai-coding","ai-driven-development","ai-safety","antigravity","bash","claude-code","codex-cli","cursor","developer-tools","gemini-cli","hooks","mcp","multi-agent","opencode","plugins","prompt-engineering","skills","subagents"],"license":"mit","html_url":"https://github.com/CodeAlive-AI/ai-driven-development","pushed_at":"2026-05-12T20:04:46Z","description":"Practices, protocols, and skills for AI-driven software development. 18 skills + 1 Bash safety hook for Claude Code, Codex CLI, OpenCode, Cursor, Gemini CLI, Antigravity, and any agent supporting the Agent Skills standard.","skill_md_sha":"6a76ec6b540d139c116c36891a0265db666cf118","skill_md_path":"skills/optimizing-claude-code/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/CodeAlive-AI/ai-driven-development/tree/main/skills/optimizing-claude-code"},"layout":"multi","source":"github","category":"ai-driven-development","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."},"skills_sh_url":"https://skills.sh/CodeAlive-AI/ai-driven-development/optimizing-claude-code"},"updatedAt":"2026-05-18T18:57:07.067Z"}}