Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Make a codebase agent-ready with progressive-disclosure documentation, domain-context and ADR discipline, regression-aware quality gates, documentation checks, and opinionated stack-specific project skill recommendations. Uses AGENTS.md directly with Claude Code 2.1.277+ without requiring a CLAUDE.md symlink.
Agent-Ready Codebase Assessment — scores your codebase across 8 dimensions, including agent-instruction and domain-context topology, and generates an actionable improvement roadmap framed around the Stripe AI benchmark.
Audit codebase documentation for accuracy, completeness, and freshness against actual code. Auto-fixes small discrepancies, reports structural changes. Companion to agent-ready.
★not rated 62▲
+2 2d agoA
tokens not measured
originalMIT
Proactive documentation drift detector. Hooks into commits to identify docs referencing changed code, flags drift before staleness accumulates, and resolves warnings via targeted fixes.
★not rated 62▲
+2 2d agoA
tokens not measured
originalMIT
MCP server for Buttondown email newsletter API. Runs locally from the buttondown-mcp npm package.
★not rated 1 8mo agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: