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.
45,604 skills from 2,205 repositories · updated 26 minutes ago
3,223 skills
- proof-drivenOutlineDriven/outline-driven-developmentUse when property-based testing, theorem proving, or formal proof tactics require zero unproven properties. Not for remote, credential, publish, deploy, or irreversible changes.TestingNo warnings★ 54↓ —
- vector-forgeOutlineDriven/outline-driven-developmentUse when crypto implementations and a vector harness need mutation-driven cross-implementation test vector expansion. Not for Wycheproof: use wycheproof. Not for fuzzing: use fuzz-harness-writing.TestingNo warnings★ 54↓ —
- ai-orchestratorarcasilesgroup/ai-engineeringBuild a whole feature end-to-end through subagents. It plans gated checkpoints, writes tests and prototypes, then loops each checkpoint through implement → behavior gate (CLI/code tests, UI e2e last) → UI gate (live vs prototype) → adversarial review gate until every checkpoint passes, then hands it to a human to review. Use when the user says "build X", "orchestrate X", "/ai-orchestrator <feature>", or asks to resume an orchestrated feature.TestingNo warnings★ 61↓ —
- ai-test-plannerarcasilesgroup/ai-engineeringPlan and write the tests for a feature, bottom-up. Everything that code or the CLI can verify (pure logic, API endpoints, DB constraints, auth/role rules) is tested without a browser. UI end-to-end tests come last and cover only what the lower layers can't. Use when the user asks to plan tests, write tests, or add test coverage for a feature or checkpoint (e.g. "/ai-test-planner discount rules").TestingNo warnings★ 61↓ —
- build-checkarcasilesgroup/ai-engineeringRun the project's objective quality gates — typecheck, lint, tests, and a production build, whatever this project actually uses — then diagnose any failure down to the file and root cause. Use before committing, opening a PR, or declaring work done, and whenever asked whether the code compiles, typechecks, lints, tests, or builds.TestingNo warnings★ 61↓ —
- grillingadriannoes/awesome-agentic-aiInterview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.TestingNo warnings★ 72↓ —
- pyvene-interventionsKalarisLabs/research-agent-skillsProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.TestingNo warnings★ 61↓ —
- qa-reviewarjun988/blender-skillsProduction QA gate for Blender assets using viewport screenshots, validation checklists, naming audits, and ship/no-ship verdicts via MCP.TestingNo warnings★ 550↓ —Also in 1 other repo
- youtube-studio-setupnaveedharri/benai-skillsStage 1 of the Ben AI publishing chain. Takes a freshly uploaded video from Studio draft to a saved Unlisted video: puts the title and both thumbnails in place, arms the title-and-thumbnail A/B test, then walks the whole Studio wizard (monetization on with mid-rolls, ad suitability rated, end screen set, checks read, visibility Unlisted). Runs FIRST, before chapters, because a draft has no caption track and Unlisted is the only state where YouTube generates one. Use when someone says "set up the video in Studio", "walk the publishing steps", "do the wizard", "get it to unlisted", "arm the A/B test", "set the end screen", "rate the ad suitability", or has just uploaded a video and wants it ready for the rest of the chain.TestingNo warnings★ 74↓ —
- youtube-link-setupnaveedharri/benai-skillsStage 3 of the Ben AI publishing chain. Makes a video's tracking links real before the video is published: imports the UTM links into Bitly on the c.benai.co domain, builds and publishes the Kit landing page when there is a lead magnet, registers it in the n8n form, and verifies every short link resolves to the right destination. Works with or without a Bitly API token; without one it walks the browser bulk-upload path, which needs no terminal. Use when someone says "upload the links to Bitly", "import the UTMs", "make the Bitly links", "set up the lead magnet", "create the landing page", "test the links", or has just run benai-utm-creator.TestingNo warnings★ 74↓ —
- youtube-packagingnaveedharri/benai-skillsCreate optimized YouTube packaging — titles and thumbnail concepts — for maximum click-through rate. Extends the title-generation skill with thumbnail planning, A/B testing suggestions, and packaging strategy aligned with the video brief. USE THIS SKILL WHEN: - User wants title + thumbnail for a video - User says "package this video", "thumbnail ideas", "title and thumbnail" - User mentions "YouTube packaging", "CTR optimization", "video packaging" - User has a video brief and wants to define the packaging TRIGGERS: "packaging", "title and thumbnail", "thumbnail", "CTR", "YouTube packaging", "package this video", "video packaging"TestingNo warnings★ 74↓ —
- browser-testingOutlineDriven/outline-driven-developmentUse when building, debugging, or verifying browser-rendered code, or running browser tests for PR- or branch-affected pages. Not for source, remote-system, credential, publish, or deploy changes.TestingNo warnings★ 54↓ —
- webapp-testingOutlineDriven/outline-driven-developmentUse when asked to verify frontend or UI behavior, or capture browser screenshots and console logs. Not for read-only inspection: use browser-testing. Not for remote or deploy changes.TestingNo warnings★ 54↓ —
- necessary-workOutlineDriven/outline-driven-developmentUse when work is about to grow past the ask, the task may already be done, or the user requests only the minimum. Not for executing the work: use tdd to build or strike-the-root to fix.TestingNo warnings★ 54↓ —
- kernel-testingOutlineDriven/outline-driven-developmentUse when writing KUnit tests, adding kselftest cases, fuzzing syscalls with syzkaller and kcov, running LTP, or wiring CI for a kernel patch.TestingNo warnings★ 54↓ —
- zeroize-auditOutlineDriven/outline-driven-developmentUse when auditing C, C++, or Rust secret-handling code to verify zeroization survives compiler optimization. Not for test vectors: use wycheproof.TestingNo warnings★ 54↓ —
- production-goOutlineDriven/outline-driven-developmentUse when writing, reviewing, debugging, or architecting Go code. Routes by project type and topic to conventions and reference chapters, then verifies with toolchain gates and unseen behavioral tests.TestingNo warnings★ 54↓ —
- test-strategyfishzjp/qa-skills"How should this be tested?" Evidence-backed risk map → scope and depth across functional domains and 10 testing-type axes; includes carry signals, excludes reasons. Not for: writing cases, requirement-analysis, pipeline (qa). 回答“这个功能应该怎么测”：风险挂证据（Risk Map），译为功能域+类型域十轴的范围与深度。不用于：写用例、需求建模、流水线。TestingNo warnings★ 50↓ —
- axolotlKalarisLabs/research-agent-skillsProvides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training with DPO, KTO, ORPO and GRPO, multimodal models, FSDP and multi-GPU setups, sequence (context) parallelism, NCCL bandwidth tests, dataset formats, compressed model saving for vLLM and llmcompressor, and custom integrations. Use when writing or debugging an Axolotl YAML config, choosing a dataset format for a fine-tuning run, setting up FSDP or context_parallel_size across GPUs, or running DPO, KTO, ORPO or GRPO training. Use when saving a compressed model for vLLM inference, or when writing a custom Axolotl plugin or integration. Not for inference serving or general Hugging Face Trainer scripts outside Axolotl.TestingNo warnings★ 61↓ —
- matlab-classify-tabular-datamatlab/matlab-agentic-toolkitUse this skill to classify tabular data end-to-end in MATLAB — load a dataset, prepare and clean it, select promising classifiers, train them, and compare accuracies with cross-validation, holdout, or hyperparameter optimization plus statistical tests. TRIGGER when: user asks to classify tabular data, pick classifiers for a dataset, compare classifier accuracy, run cross-validation or a holdout evaluation, or find the best model with statistical uncertainty. DO NOT TRIGGER when: user has non-tabular inputs (images, sequences, time series), wants a regression model, is training a specific neural network architecture (use matlab-train-network), or wants cost-sensitive learning or an arbitrary class-prior vector (this skill only supports the built-in uniform-prior toggle for imbalanced data).TestingNo warnings★ 1.2K↓ —
- transformNewhashgraph-online/awesome-codex-pluginsUse this to author and change a dbt project or a semantic layer: bootstrap a project (`transform init`), write or refactor models from staging to marts, add tests and docs, and define semantic models, entities, dimensions, and metrics in MetricFlow, Apache Ossie or SLayer YAML. Reach for it instead of editing model files by hand whenever a change spans more than one file or must stay consistent with the project: it validates the edit against the real schema, returns a reviewable diff with a plan id, and catches what otherwise fails at `dbt run`, such as wrong columns or broken refs. Bug-fix tickets count: "this model returns wrong numbers, fix it" is a transform task. Also for "build a staging model for this table", "define a revenue metric", "add a dimension to this entity". Warehouse builds are dev-target only, gated, and cost-surfaced first. If you have not verified the source tables' columns or grain, use explore first. For a project that drifted from the warehouse, use maintain.TestingNo warnings★ 1.4K↓ —
- change-management-evidence-samplingNewbetter-isms/grcskillsUse this skill when an auditor will test change management, or the team wants to know before they do, and asks "sample our production changes", "check our PR approvals", "do we have segregation of duties on deploys", "test change management before the audit", "were emergency changes approved" or "can a developer push to production alone". Builds the change population from what actually reached production, reconciles it with tickets and pull requests, draws a recorded sample, tests approval, testing, segregation and emergency attributes, and writes the results and the exceptions as facts.TestingNo warnings★ 51↓ —
- lov-xbti-creatorlovstudio/skillsCreate a complete custom BTI personality test (like LBTI, FBTI, etc.) based on the XBTI architecture. User provides a theme name and preferences, AI generates all content: dimensions, questions, personality types, descriptions, and avatar images via lov-image-creator. Trigger when user says "创建BTI", "自定义人格测试", "make a BTI", "custom personality test", "XBTI变体", "xbti-creator", or mentions creating something like LBTI/FBTI/etc.TestingNo warnings★ 72↓ —
- ca-fixarbiterForge/codeArbiterFix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.TestingNo warnings★ 148↓ —