Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
10,471 skills from 307 repositories · updated 8 minutes ago
927 skills
- github-ci-debugDevin-AXIS/iPolloWorkDiagnose failing GitHub Actions runs from bounded run, job, and step evidence, propose a focused fix, and modify the local checkout only when the requested task includes implementation.EngineeringNo warnings★ 7.1K↓ —
- skill-vettingmohitagw15856/pm-claude-skillsVet an agent skill before installing it — read the SKILL.md and any scripts for the red-flag patterns (credential access, obfuscation, exfiltration, prompt injection), audit its blast radius, and produce a risk-tiered verdict. Use when asked is this skill safe to install, vet this SKILL.md, review this skill from a marketplace, or check what this skill can do to my machine. Produces the risk classification with quoted evidence, the permission-surface audit, the red-flag checklist results, and an install/sandbox/reject recommendation.EngineeringNo warnings★ 1.5K↓ —
- github-publish-changesDevin-AXIS/iPolloWorkPublish intentional local changes by confirming scope, creating a branch when needed, staging selected files, committing, pushing, and creating a Draft Pull Request through the connected GitHub service.EngineeringNo warnings★ 7.1K↓ —
- github-review-follow-upDevin-AXIS/iPolloWorkInspect unresolved GitHub pull request review threads, group actionable feedback, implement selected fixes locally, and only reply or resolve threads after explicit user intent.EngineeringNo warnings★ 7.1K↓ —
- sentry-fix-verificationDevin-AXIS/iPolloWorkVerify a production fix by linking the changed code and release to Sentry issue state and post-release event trends without resolving issues prematurely.EngineeringNo warnings★ 7.1K↓ —
- OpenAI AutomationComposioHQ/awesome-claude-skillsAutomate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio MCP integration.EngineeringNo warnings★ 77.6K↓ —Also in 1 other repo
- wechat-official-reviewDevin-AXIS/iPolloWorkTurn bounded draft, publication, and comment evidence into a concise WeChat Official Account operating review and next-step plan.EngineeringNo warnings★ 7.1K↓ —
- gita5c-ai/babysitterGit workflows, branching strategies, and hooks.EngineeringNo warnings★ 1.9K↓ —
- code-reviewa5c-ai/babysitterStructured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.EngineeringNo warnings★ 1.9K↓ —
- git-integrationa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationEngineeringNo warnings★ 1.9K↓ —
- swift-concurrencyAvdLee/Swift-Concurrency-Agent-SkillDiagnose Swift Concurrency issues, refactor callback-based code to async/await, and guide Swift 6 migration when working with tasks, actors, @MainActor, Sendable, data races, thread safety, or concurrency-related compiler and linter warnings.EngineeringNo warnings★ 1.7K↓ —
- code-generationa5c-ai/babysitterMinimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.EngineeringNo warnings★ 1.9K↓ —
- issue-trackinga5c-ai/babysitterTrack beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.EngineeringNo warnings★ 1.9K↓ —
- kip-librariana5c-ai/babysitterCanonical kip knowledge-store patterns for any process or agent: recall prior facts before work, assert decisions/gate outcomes/rejections as structured facts after work, resolve entities with explicit --model sonnet, and invoke the CLI Windows-safely via node packages/kip-sdk/dist/cli/kip.js when kip is not on PATH.EngineeringNo warnings★ 1.9K↓ —
- trpca5c-ai/babysittertRPC end-to-end type safety, procedures, routers, middleware, and React integration.EngineeringNo warnings★ 1.9K↓ —
- code-reviewa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationEngineeringNo warnings★ 1.9K↓ —
- debugging-patternsa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationEngineeringNo warnings★ 1.9K↓ —
- code-review-gatea5c-ai/babysitterArchitect code review with DRY, YAGNI, abstraction, and test coverage principle enforcementEngineeringNo warnings★ 1.9K↓ —
- pr-shepherdinga5c-ai/babysitterMonitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.EngineeringNo warnings★ 1.9K↓ —
- code-review-gatea5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationEngineeringNo warnings★ 1.9K↓ —
- code-review-patternsa5c-ai/babysitterMulti-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.EngineeringNo warnings★ 1.9K↓ —
- git-lfsa5c-ai/babysitterGit LFS skill for large game assets.EngineeringNo warnings★ 1.9K↓ —
- systematic-debugginga5c-ai/babysitterStructured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.EngineeringNo warnings★ 1.9K↓ —
- adversarial-reviewa5c-ai/babysitterFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.EngineeringNo warnings★ 1.9K↓ —