MCP servers and skills: search, filter by where they run, and compare.
An agent skill that raises test coverage on a scope you choose, with one agent per uncovered file, writing test code only unless you approve a source change. A calling skill can pass the scope instead
SkillMITFew starsNo key
Cloudflare Security Audit Skill 中文社区增强版：证据驱动的 Spring Security 与中国技术栈代码审计
SkillMIT★ 2Few starsNo key
Deterministic, local paper assembler and exam checker for AI agents: assemble from a local item bank against a blueprint (coverage, difficulty quotas, points, time) with a reproducible seed; check pap
SkillMITFew starsNo key
Harvest — plain-English training-data scout: 12 experts fan out over HuggingFace + GitHub and compose coverage-scored training packs. MCP server, no API keys or Bridge required.
Node.jsApache-2.0★ 1Few starsNo key
MCP server for covdbg: C++ code coverage on Windows for AI agents. Run tests, find uncovered code, and add targeted tests. No rebuild required.
SkillApache-2.0Few starsNo key
The live Claude Code rule set I ship production software with — 33 rules, 22 standards, 14 agent roles, each traced to the measurement or incident that produced it.
SkillMIT★ 1Few starsNo key
Take your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No
SkillMIT★ 1.3kNo key
Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampering, hold the CRAP bar on changed functions, check diff coverage, secrets and dependencie
SkillMIT★ 19No key
General-purpose, evidence-driven AI security audit skill: stack recon, adaptive hunting, independent adversarial validation, coverage ledger, structured findings and reports for any repository.
SkillMITFew starsNo key
Cross-platform AI agent skill for threat-model-driven AppSec reviews in Claude Code, Cursor, and OpenAI Codex. Maps attack surfaces, verifies findings independently, validates coverage, scores with CV
SkillMIT★ 2Few starsNo key
SkillMIT★ 2Few starsNo key
AI agent skill that audits JS/TS monorepos (Nx, Turborepo, pnpm/yarn/npm/bun) for boundaries, circular deps, caching, CI test coverage, and test code leaking to prod
SkillMIT★ 8No key
Security scanner for MCP servers, source trees, and packages, with explicit findings and coverage reporting.
GoApache-2.0★ 24No key
Agent skills for running a music release campaign: plan, pitch, coverage, handoff.
SkillMITFew starsNo key
Deterministic, local compliance-clause review skill for AI agents: versioned JSON rule packs, evidence-anchored findings, and Markdown/JSON reports with explicit framework coverage levels (PIPL baseli
SkillMITFew starsNo key
A client, CLI and MCP server for the qBittorrent WebUI API. All 123 endpoints, checked against qBittorrent's source.
PythonMITFew starsNo key
Free, offline gate for AI-written tests: proves tests fail when the code is wrong, catches weakened tests in a change, and finds untested risky edges in JavaScript and TypeScript.
Node.jsApache-2.0★ 1Few starsNo key
Whole-repository code review by AI agents: blocks, a coverage map, hypotheses with verdicts, four roles. An Agent Skill.
SkillMIT★ 3Few starsNo key
Who raised today, in one place. Open-source funding feed built on Firecrawl: verified rounds with a dashboard, Slack, feeds, an API, and an MCP server.
OfficialSkillMIT★ 8No key
Your docs are lying. One-page feature docs with diagrams, checked against your code, kept true in CI, and shared as a wiki.
SkillMITFew starsNo key
Read-only MCP server exposing esimkenya.com's live eSIM provider/plan data for AI assistants
Hosted by authorMITFew starsNo key
SkillMIT★ 1Few starsNo key
Evidence-backed code context for AI coding agents: semantic + lexical search, a cross-project code and contract graph, and versioned team memory across all your repositories — served over MCP, CLI and
SkillApache-2.0★ 5No key
A Claude Code skill that designs a brand identity as one system: logo, typography and colour palette built together from one brief, measured, compared as identity cards, and delivered as a brand guide
SkillMIT★ 162No key
Who stands behind it
