MCP servers and skills: search, filter by where they run, and compare.
Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review feedback, or green-check loops; do not wait for human approval, draft status, or
OfficialSkillApache-2.0★ 1.1k in collectionNo key
Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming c
OfficialSkillApache-2.0★ 48k in collectionNo key
Skill-first GitHub workflows for DeepSeek Harness: PR triage, review feedback, CI diagnosis, and safe publishing.
SkillApache-2.0★ 5No key
Local, model-neutral electronics MCP for CRUMB static analysis and Logisim-evolution project inspection, truth tables, and test vectors.
Node.jsApache-2.0★ 1Few starsNo key
AI infrastructure cartographer and operations daemon — Graphify for live infrastructure. Fingerprints, graphs, and watches Docker/Kubernetes/AWS/IaC for AI agents via CLI + MCP.
Node.jsApache-2.0Few starsNo key
Use when finished work needs to ship as a pull request, or when creating, syncing, updating metadata, checking status, monitoring CI, or addressing review comments on a PR. Not for reviewing a PR you
OfficialSkillApache-2.0★ 517 in collectionNo key
Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
PythonApache-2.0★ 151No key
AgentGate — scan, lock, and gate your MCP servers. npm-audit + lockfile + CI drift gate for the MCP era.
SkillApache-2.0Few starsNo key
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Persistent memory for AI agents. Agents forget. CI remembers.
Node.jsApache-2.0★ 3Few starsNeeds a key
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump t
OfficialSkillApache-2.0★ 48k in collectionNo key
Deterministic CI scanner and surface-risk scoring for MCP (Model Context Protocol) servers.
PythonApache-2.0★ 21No key
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
CI for Claude Skills — lint, eval, and regression-test SKILL.md files across a model matrix, with a self-growing eval loop that turns uncovered regressions into permanent test cases.
SkillApache-2.0★ 8No key
Author, audit, and improve Grafana SKILL.md files against Anthropic's published Agent Skills guidance and the four-dimension rubric the grafana/skills CI gate uses (conciseness, actionability, workflo
OfficialSkillApache-2.0★ 285 in collectionNo key
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
NVIDIA Design System and UI Agent Harness for AI/ML Factories, Robotics, and Autonomous Vehicles
OfficialSkillApache-2.0★ 93No key
Local, deterministic review of Git changes: weakened tests and CI gates, security boundaries, blast radius. CLI, GitHub Action, MCP server, and coding-agent plugins.
Node.jsApache-2.0★ 24No key
Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-brow
OfficialSkillApache-2.0★ 4.6kNo key
Campaign mode prunes one subsystem's whole test surface in one PR: one core area such as packages/eve/src/execution , one tier slice such as the dev server scenario suites, or one package such as pack
OfficialInstructionsApache-2.0★ 5.6k in collectionNo key
GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review",
OfficialSkillApache-2.0★ 1.1k in collectionNo key
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Astrid is a portable, capability-secure operating system for composable software.
SkillApache-2.0★ 10kNo key
Who stands behind it
