MCP servers and skills: search, filter by where they run, and compare.
Pipeline de Spec-Driven Development em skills portáveis: PRD → TechSpec → tasks → execução → review → QA → bugfix.
SkillMIT★ 4Few starsNo key
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external
SkillMIT★ 67No key
PaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents: extract results, trace proof evidence, plan reading order, and review external dependencies without guessing.
PythonMIT★ 284No key
Test-first workflow to use before writing implementation code for any feature or bug fix.
SkillMITNo key
A memory vocabulary for game developers - the gamedev types and tags that Engram does not ship. Bring Engram; this brings the words: scene patterns, asset references, perf gotchas, pipeline steps. Uni
GoMIT★ 4Few starsNo key
29 drop-in Claude Code skills: cost-tier model routing, debugging (rubber-duck, test-first-bugfix, trust-but-verify), and 24 laws-of-software reference skills. Install with: npx skills add The-Artific
SkillMIT★ 6No key
Give Claude Code a memory and make it cite its sources — keyless skills for research, daily work, and an evidence-gated coding loop.
SkillMIT★ 9No key
Spec-Driven Development Plugins For ClaudeCode/Codex
SkillMIT★ 10No key
Curated AI Workflows, Skills & MCP servers for secure multi-agent development
SkillMIT★ 11No key
Node.jsMIT★ 4Few starsNo key
Read-only WHOOP v2 API access for MCP clients — direct OAuth, local SQLite cache, CSV/JSONL/Parquet exports
PythonMITFew starsNeeds a key
Forge — 文档驱动的 AI 辅助开发框架 | Document-driven AI development framework with 14 Skills covering brainstorm → PRD → design → engineering → QA → review → ship → retrospective
SkillMIT★ 13No key
X out the AI behavior you never want again - falsification-based CLAUDE.md/AGENTS.md compiler with evidence receipts
SkillMITFew starsNo key
Adversarial multi-agent code review — a committee of specialist reviewers that catches what single-pass AI review misses.
SkillMIT★ 4Few starsNo key
Reusable engineering skills and bounded review-fix loops for Codex and Agent Skills hosts.
SkillMIT★ 1Few starsNo key
Do Claude Code skills actually help? Benchmark AI coding agent skills, plugins & CLAUDE.md with and without them: pass rate, cost, false "done" claims, test tampering. Claude Code, OpenCode, Codex — a
Node.jsMITFew starsNo key
Who stands behind it
