Skills publicadas
Mostrando 12 de 828cm-skill-share
[Deprecated] skill lifecycle merged. Use `cm-skill-evolution` instead.
cm-quality-gate
Use before any deployment or completion claim. Enforces test gates, evidence-based verification, and frontend safety checks. No deploy without passing. No claims without evidence.
cm-skill-mastery
[Deprecated] discovery and meta-skill merged. Use `cm-skill-index` instead.
cm-codeintell
Unified code intelligence — Skeleton Index (zero-dep, <4s) + AST knowledge graph (CodeGraph) + architecture diagrams (Mermaid) + smart context builder. Pre-indexes code structure so AI agents understand any codebase instantly. 95% token compression for onboarding. 30% fewer tokens for deep analysis.
cm-reactor
Strategic codebase re-direction when requirements change, architecture doesn't fit, or tech debt blocks progress. TRIZ-powered pivot protocol for large codebases.
cm-autopilot
Easy-to-use conversational CLI (Claude Code style) for non-technical users to spawn parallel AI tasks supervised by a visual web dashboard.
cm-qa-visual-cli
[Deprecated] browser daemon overlap. Use `cm-browse` instead.
cm-mcp-engineering
Use when you need to interact with the MCP engineering bridge tools (cm_plan, cm_review, cm_qa, cm_deploy, cm_search).
cm-reactor
Strategic codebase re-direction when requirements change, architecture doesn't fit, or tech debt blocks progress. TRIZ-powered pivot protocol for large codebases.
cm-skill-health
[Deprecated] skill lifecycle merged. Use `cm-skill-evolution` instead.
cm-execution
Use when executing approved implementation plans. Routes to 1 of 6 execution modes (batch/subagent/parallel/RARV/TRIZ/party) based on task shape. Loads detail refs on-demand.
cm-guardian-runtime
Use when you need to check if a destructive command is blocked or run guardian freeze checks.