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.
45,585 skills from 2,205 repositories · updated 13 minutes ago
3,218 skills
- e2e-testingnahid-sparktales/agent-dispatcherBuild and keep end-to-end suites that are worth their runtime — which journeys belong at this level, selectors that survive refactors, waiting on state instead of sleeping, per-spec data isolation, and flake triage that finds the cause. Use when adding or repairing an e2e suite, when specs are slow or intermittently red, or when deciding whether a case belongs here at all. Not for one-off checking that a change renders, not for unit or integration tests, and not for load testing.TestingNo warnings★ 59↓ —
- agent-evalsnahid-sparktales/agent-dispatcherBuild an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check properties rather than vibes, a recorded baseline, and per-case diffs in both directions. Use before claiming a prompt, model or agent change is an improvement, when agent behaviour must not regress, or when someone reports "it seems better" after eyeballing a handful of outputs. Not for tracing what one run did (llm-observability), not for testing deterministic code, and never as evidence that behaviour the suite does not measure is safe.TestingNo warnings★ 59↓ —
- ci-cdnahid-sparktales/agent-dispatcherDesign the shape of a delivery pipeline — what each stage actually proves, what gates what, where verification belongs, and how a run reports the truth instead of a green tick. Use when a pipeline is being designed or restructured, when a release got through a passing pipeline broken, when deciding what blocks a merge or a deploy, or when a stage claims more than it ran. Not for provider-specific workflow YAML (github-actions), image authoring (docker), writing the tests themselves (test-design), or handling an outage in progress.TestingNo warnings★ 59↓ —
- ase-meta-compatrse/aseSelf-test the LLM's ability to execute ASE's core interpreter machinery (control flow, XML placeholders, regex matching, arithmetic) and report an overall compatibility rating. Use when the user wants to check how well the current model/harness is compatible with ASE, or asks to "test ASE compatibility" or "check ASE compatibility".TestingNo warnings★ 60↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- 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-stress-testarcasilesgroup/ai-engineeringTest system behavior under extreme load to find breaking points, capacity limits, and failure modes. Covers stress, spike, and breakpoint testing with k6 (primary), JMeter, or Locust. Refuses unbounded concurrency and production saturation without explicit approval. Trigger for "stress test", "load test until it breaks", "find the breaking point", "capacity test", "spike test", "how much traffic can we handle", "system limits", "what's our max load". Not for frontend performance or Core Web Vitals — use /ai-audit-design. Not for general load testing to validate expected traffic — use /ai-verify with existing benchmarks. Not for diagnosing a performance failure — use /ai-debug.TestingNo warnings★ 61↓ —
- ai-agents-mdarcasilesgroup/ai-engineeringCreates, audits and maintains the AGENTS.md a repository owes its coding agents, following the agents.md convention (https://agents.md/). Decides root-only versus nested AGENTS.md files from the repo's real shape, interviews the tree (not the user) for build/test/lint commands, and writes only what an agent cannot deduce from the code. Audits a set that already exists: a rule the code states, a child repeating its parent, a command that no longer runs, a zone with no route in. Also the in-session maintenance path: a governed agent MAY edit AGENTS.md directly (blueprint §9.2 — it is not sacred) when the repo's real state made a rule stale. Trigger for "create AGENTS.md", "update AGENTS.md", "audit AGENTS.md", "split AGENTS.md", "AGENTS.md is too long", "the agent reads the wrong file", "the agent ignores our conventions", "set up agent instructions", "edit AGENTS.md". Not for runtime agent contracts (goals, gates, budgets) — use /ai-orchestrator. Not for documentation users read — use /ai-write.TestingNo warnings★ 61↓ —
- ai-prarcasilesgroup/ai-engineeringThe pull-request loop, opened from the local `main` with no worktree: cut the pull-request branch from the local `main`, push it, open the pull request against `main` with a body assembled from the merge commits the branch carries, watch CI and the review comments, fix only what is obvious in bounded iterations, then merge with auto-merge on by default. The human's verb decides how far the run goes: "open the pull request" opens it and stops, while "finish the PR", "land the PR", "merge it" or "run the full PR loop" carries the run through the merge — an ask that names neither is the open one. A session that is still building never pushes. Not for diagnosing non-CI failures — use ai-debug. Not for adding test coverage — use ai-verify.TestingNo warnings★ 61↓ —
- audit-installationTserenTserenov/FMT-exocortex-templateАудит пользовательской инсталляции IWE. Запускает scripts/iwe-audit.sh + MCP healthcheck + smoke-test ритуала через sentinel-механику (контракт dry-run-contract.md), передаёт отчёт subagent'у в роли VR.R.002 Аудитор (context isolation) → verdict ✅/⚠️/❌ по 6 компонентам (Inventory, L1 drift, {{GOVERNANCE_REPO}}, L3 customizations, MCP, ритуал). Используй после restore из бэкапа, после update.sh, или при еженедельной сверке.TestingNo warnings★ 63↓ —
- grill-meDianel555/DSkillsGrill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report without writing code. Use when the user wants to clarify requirements, stress-test an idea, compare approaches, or plan before coding.TestingNo warnings★ 65↓ —
- arize-datasetArize-ai/arize-skillsCreates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.TestingNo warnings★ 66↓ —
- create-manual-test-instructionseai-org/agent-toolkitTurn a ticket or requirements document into a concise QA manual-test file a non-author can follow. Invoke manually only.TestingNo warnings★ 66↓ —
- run-nx-checkseai-org/agent-toolkitRun nx format, lint, typecheck, test, and build on affected or specified projects, then fix unambiguous failuresTestingNo warnings★ 66↓ —
- grill-meeai-org/agent-toolkitInterview the user relentlessly about a plan, design, or idea until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, validate an idea, get grilled on their design, or says "grill me".TestingNo warnings★ 66↓ —
- create-callVapiAI/skillsCreate one-off outbound phone calls, web calls, scheduled calls, and simple batch calls using the Vapi API. Use when making or testing individual calls or initiating a bounded /call request programmatically. Use create-campaign for a persistent multi-contact Campaign with lifecycle, reporting, cancellation, duplication, or campaign webhooks.TestingNo warnings★ 67↓ —
- create-callVapiAI/skillsCreate one-off outbound phone calls, web calls, scheduled calls, and simple batch calls using the Vapi API. Use when making or testing individual calls or initiating a bounded /call request programmatically. Use create-campaign for a persistent multi-contact Campaign with lifecycle, reporting, cancellation, duplication, or campaign webhooks.TestingNo warnings★ 67↓ —
- correctNewdsebban/skillsFind the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /skill:correct.TestingNo warnings★ 68↓ —
- create-sdi-runmatlab/simulink-agentic-toolkitImport data into the Simulation Data Inspector (SDI) from MAT, CSV, or Excel files, from workspace variables, or from a Simulink simulation. Use when the user wants to view a logged file in SDI, load a bench-test log, or verify what a just-completed `Simulink.sdi.createRun` or `sim(model)` produced. Covers the `'file'`, `'vars'`, and `'namevalue'` sources of `createRun`, the auto-populate behavior after `sim()`, and post-import verification. Not for comparing existing runs (use `Simulink.sdi.compareRuns`); not for streaming data live during a running simulation (use `Simulink.sdi.createRunOrAddToStreamedRun` — a separate API); and not for authoring Gherkin or Simulink Test test cases, assertions, or regression tests (use `testing-simulink-models`). Do not activate on test-authoring or verification prompts even when no test-authoring skill is available — say so and stop.TestingNo warnings★ 1.3K↓ —