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.
45,100 skills from 2,196 repositories · updated 12 hours ago
3,187 skills
- qanota-america/forgecat-agent-profilesSystematically QA test a web application and fix bugs found. (gstack)TestingNo warnings★ 93↓ —
- idea-refinenota-america/forgecat-agent-profilesRefines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".TestingNo warnings★ 93↓ —
- rust-stingerlegioncodeinc/vibe-coding-toolsRust development specialist for Cargo, async services, persistence, CLI/TUI, tests, upgrades, and current toolchains. Use for Rust implementation, review, migration, or release guidance.TestingNo warnings★ 94↓ —
- vectorsimota/agent-skillsAutomating browsers via Playwright and Chrome DevTools for data collection, form interaction, screenshot capture, and network monitoring. Task completion focus (vs Voyager for E2E testing).TestingReview first★ 95↓ —
- matrixsimota/agent-skillsControlling combinatorial explosion across multi-dimensional axes: minimum coverage sets, execution plans, test/deploy/UX/risk prioritization. Use when scoping multi-axis combinations.TestingReview first★ 95↓ —
- evo-build-diagnosisOpenLAIR/OpenSkillAnalyzes a Python repository to identify the root causes of build failures, including syntax errors, import errors, test failures, and build configuration issues. Use when diagnosing why a Python project fails to build or pass tests. Scans repository files for syntax errors via ast.parse/compile, parses pytest output and CI logs, checks build configuration files (pyproject.toml, setup.py, setup.cfg), identifies missing dependencies, and produces a structured diagnosis report.TestingNo warnings★ 97↓ —
- skill-creatorOpenLAIR/OpenSkillCreate 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.TestingNo warnings★ 97↓ —
- webapp-testingaisa-group/skill-injectToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.TestingNo warnings★ 100↓ —
- modernize-testsartemnovichkov/xcode-skillsModernize test suites to use modern Swift Testing features or migrate from XCTest.TestingNo warnings★ 61↓ —
- grill-memart337i/odoo-skillsInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me" outside an Odoo-specific context.TestingNo warnings★ 59↓ —
- grill-with-docsmart337i/odoo-skillsGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when the user wants to stress-test a plan against their project's language and documented decisions.TestingNo warnings★ 59↓ —
- clear-skiestmcfarlane/team-avatarAppa's clear skies for merge conflicts. Appa waits out the storm, then flies on once the sky is clear. Use for fix-merge-conflicts, /fix-merge-conflicts, "resolve the conflicts", "fix the merge conflict", "rebase broke", or a PR whose merge state is DIRTY. Resolves every conflict non-interactively with minimal edits, regenerates lockfiles with their tools, and proves the build and tests before staging.TestingReview first★ 110↓ —
- evaluate-modelxvirobotics/metaskillLoad the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.TestingNo warnings★ 73↓ —
- build-and-testxvirobotics/metaskillBuild the Xcode project and run the full test suite. Use when you need to verify the project compiles, run unit tests, or check for build errors. Reports pass/fail results with detailed error output.TestingNo warnings★ 73↓ —
- api-testxvirobotics/metaskillRun API integration tests against the running backend, verify endpoints return expected responses and status codes. Use after deploying a preview or starting the dev server.TestingNo warnings★ 73↓ —
- testing-coach-stingerlegioncodeinc/vibe-coding-toolsTeach contract-based testing through tiny exercises, failure interpretation and changed conditions. Use for learning assertions without copying implementation. Read README.md for the guide map.TestingNo warnings★ 94↓ —
- multiplayer-testingSummerEngine/summerTest a Summer multiplayer game with Local Play: several players, bad network, bots, a passing run.TestingReview first★ 88↓ —
- ios-qanota-america/forgecat-agent-profilesLive-device iOS QA for SwiftUI apps. (gstack)TestingNo warnings★ 93↓ —
- qanota-america/forgecat-agent-profilesSystematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases): "quality check", "test the app", "run QA".TestingNo warnings★ 93↓ —
- qanota-america/forgecat-agent-profilesSystematically QA test a web application and fix bugs found. (gstack)TestingNo warnings★ 93↓ —
- multiplayer-testingSummerEngine/summerTest a Summer multiplayer game with Local Play: several players, bad network, bots, a passing run.TestingReview first★ 88↓ —
- councilgavishap/omnia-vaultConvene a cross-model council on a hard decision — five seats, each filled by ONE real agent (some Codex, some Claude), giving independent opinions that are anonymized, cross-reviewed by the opposite bench, and synthesized into a ruled verdict. Use when the user says "council this", "convene the council", "get multiple perspectives on this", "I'm torn between X and Y", "which option should we pick", "pressure-test this decision", or faces a genuinely uncertain, expensive-if-wrong choice (pricing, positioning, pivot, architecture direction, build-vs-buy). NOT for questions with one right answer, creation tasks, or code review (that's `sparring`). The war-room is the plan; the council is who you ask before changing it.TestingNo warnings★ 82↓ —
- shipnota-america/forgecat-agent-profilesShip workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)TestingNo warnings★ 93↓ —
- custom-canvas-and-gestureszakariaf/Flutter-SkillsEnforces CustomPainter/Canvas discipline — the View/Painter/Scene split with a dumb painter fed one immutable Scene value type, shouldRepaint as a single value compare kept strictly separate from the AnimationController-as-repaint animation path, one shared affine transform read by BOTH painter and hit-tester (toCanvas/toLogical exact inverses, never re-derive scale), geometry hit-testing (integer lattice or rasterized region-ID buffer, never Path.contains), zero-allocation paint(), gesture-as-pure-translator emitting a typed command to a Notifier (never mutating in the handler), ExcludeSemantics + sibling Semantics speaking display values with redundant non-colour encoding, measured TextPainter fitting, first-party RoundedSuperellipseBorder, physical-pixel hairlines, and Directional-only geometry. Use when writing or reviewing a CustomPainter/CustomPaint, gestures on a canvas, tap/drag hit-testing, canvas animation, measured text fitting, or Semantics over custom-drawn pixels.TestingNo warnings★ 62↓ —