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 3 hours ago
3,223 skills
- 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↓ —
- 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↓ —
- 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↓ —
- test-designnahid-sparktales/agent-dispatcherWrite unit and integration tests that fail for the right reason — behaviour-level assertions, boundary values, the smallest honest double, deterministic setup and teardown. Use when adding tests for new code, pinning a bug before fixing it, or repairing tests that stay green while the code is broken. Not for deciding what to test or at which level, not for browser journeys, and not a way to call a change verified.TestingNo warnings★ 59↓ —
- experimentationnahid-sparktales/agent-dispatcherDesign an A/B test that can answer its question — hypothesis, randomization unit, power, duration, pre-registered analysis — and read the result honestly, including a null. Use when someone proposes testing a change, asks how long a test must run or whether a result is real, when a test is about to be stopped early, or when a flat result is being read as "no difference". Not for defining the metric itself (product-analytics), not for a change too small or too rare to power, and not for authorizing a rollout.TestingNo warnings★ 59↓ —
- regression-testingnahid-sparktales/agent-dispatcherTurn a fixed bug into a test that fails on the old code and passes on the new one. Assert behavior at the cheapest useful level and compare old behavior without reverting unrelated work or leaving scratch files. Use after a fix or when recurring defects lack coverage; not for a new feature's test strategy or an environmental/cosmetic failure.TestingNo warnings★ 59↓ —
- source-evaluationnahid-sparktales/agent-dispatcherJudge whether a source can carry the weight you are about to put on it — trace it upstream to something primary, check its date and version, name who benefits if you believe it, test whether corroboration is actually independent, and cite it so a reader can reopen exactly what you read. Use before relying on a claim that changes a decision, when two sources disagree, when a number arrives without its method, or when writing citations. Not for running the overall investigation, and not for deciding between products.TestingNo warnings★ 59↓ —
- release-verificationnahid-sparktales/agent-dispatcherProve a deployment is healthy rather than merely finished — the revision actually serving asked of the running system, every instance moved, smoke paths walked against the real environment, error rate and latency compared to a pre-deploy baseline. Use after any deploy to a shared environment, before a release is called good, or when checking someone else's claim that it went fine. Not for planning the rollout (deployment) or executing a revert (rollback); it never accepts a green pipeline, a 200 from a health endpoint, or a passing test suite as proof.TestingNo warnings★ 59↓ —
- openai-compatible-imagegenSyh1906/openai-compatible-imagegenGenerate, edit, annotate, and deliver images in Codex App through the configured API Key or ChatGPT subscription route, and open a focused canvas from a concrete image result. Use for generation, reference edits, mask edits, transparent delivery, batches, version inspection, exact sizing, grid splitting, preview boards, deterministic QA, and continued work on historical images.TestingNo warnings★ 58↓ —
- Openhookagentskillexchange/skillsCreates webhook inboxes, receives callbacks, and forwards events for AI agents with Openhook. Use when testing local webhook integrations, inspecting external callbacks, or waiting for asynchronous events through MCP.TestingNo warnings★ 58↓ —
- Browserbase MCP Serveragentskillexchange/skillsBrowserbase MCP Server gives agents cloud browser control through Browserbase and Stagehand, with both hosted HTTP and self-hosted stdio options. It suits teams that want MCP-based browser automation but prefer Browserbase sessions and Stagehand’s action model instead of running Playwright locally.TestingNo warnings★ 58↓ —
- Proofed Completion Gateagentskillexchange/skillsUses the Proofed CLI and current-subject completion receipts to reject unsupported coding-agent completion claims, rerun repository-configured tests, and detect stale PASS evidence after code changes.TestingNo warnings★ 58↓ —
- Jenkins Pipeline Monitoragentskillexchange/skillsMonitors Jenkins CI pipelines via the Jenkins REST API (/api/json) and Blue Ocean REST endpoints. Tracks build queue times, stage durations, and test result trends using JUnit XML parsing.TestingNo warnings★ 58↓ —
- Playwright Test Recorderagentskillexchange/skillsCurated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.TestingNo warnings★ 58↓ —
- Microsoft Playwright MCPagentskillexchange/skillsMicrosoft Playwright MCP exposes Playwright browser automation through the Model Context Protocol, giving agents structured page access instead of screenshot-only workflows. It is a strong fit when you want dependable navigation, form filling, DOM inspection, and test-like automation inside an MCP-compatible client.TestingNo warnings★ 58↓ —
- Pytest Fixture Generatoragentskillexchange/skillsCurated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.TestingNo warnings★ 58↓ —
- playwright-browserAndyShiu/claude-skill-playwright-browserHeadless, reproducible browser automation with Playwright for any project — screenshots of web pages or local dev servers (desktop/tablet/mobile, full page or one element, single page or every page/menu of an app in one batch), frontend audits (console errors, failed requests, broken images/links, responsive overflow, axe accessibility, LCP/CLS performance), before/after visual comparison, scripted E2E flows (log in, click, fill, page through, assert), and logged-in pages via saved sessions. Use this whenever the user wants to screenshot or visually check a site, find frontend bugs, see how a page looks on mobile, compare the UI before and after a CSS/code change, reproduce a bug from an issue or ticket and capture evidence images for it, verify a UI flow works, or run/write a browser test — even if they never say "Playwright" or "browser". If Claude in Chrome could also do the job, briefly ask which to use (with a recommendation) instead of silently picking.TestingNo warnings★ 51↓ —
- lazy-catalbertobarnabo/lazy-catKeeps code changes as small as the problem allows. Use before writing or changing code, including small fixes, single functions and quick scripts, and especially before generating data, fixtures or seed records, or hand-writing something a stdlib call, package, public API or open dataset already provides (validation, parsing, auth, dates, currency, geo). Checks for that cheaper path first, then writes only what was asked: no unrequested error handling, tests, docstrings, flags, abstractions or refactors. Not for infra/terraform/k8s or database queries.TestingNo warnings★ 51↓ —
- test-case-reviewfishzjp/qa-skillsReview existing test cases (legacy, others', AI) for coverage and executability: build a testable-points baseline, assess independently, revise in place with records. Not for: writing cases from scratch (test-case-writing), pipeline. 审查已有用例（存量/他人/AI 产出）的覆盖与可执行性：先建基准再独立评估，修订留审查记录。不用于：从零写用例、写时自审、流水线。TestingNo warnings★ 50↓ —
- testing-strategyshinpr/agentic-codeSelects the narrowest sufficient test boundary from requirements, repository evidence, and maintenance cost. Use when deciding integration or E2E coverage.TestingNo warnings★ 50↓ —
- automated-e2e-testingfishzjp/qa-skillsTurn manual cases into Playwright E2E automation run in a browser: page objects, helpers, bug evidence, reports. Not for: API tests, exploratory sessions, bug root-cause. 将手动用例转为 Playwright E2E 自动化并真实执行；含写自动化前的业务熟悉踩点、Page Object/Helper、Bug 证据与报告条目。不用于：API 接口测试、独立探索会话（exploratory-testing）、Bug 根因。TestingNo warnings★ 50↓ —
- backup-restore-test-evidenceNewbetter-isms/grcskillsUse this skill when a restore test is due, an auditor or customer asks for proof that backups can be recovered, or someone says "plan a restore test", "prove we can recover in time", "our backups succeed but we never restored", "test our RTO and RPO", "write up the disaster recovery test" or "document the backup restore for the audit". Picks what to restore, writes a test plan with success criteria set before the test, records timings against the recovery objectives, and produces a signed-off test record with the issues found and their owners.TestingNo warnings★ 51↓ —
- ai-act-risk-classificationNewbetter-isms/grcskillsUse this skill when a company must work out where each of its AI systems sits under the EU AI Act, and asks "is this high-risk", "classify our AI systems", "AI Act risk tier", "are we a provider or a deployer", "does Annex III apply to us", "is this a prohibited practice", "what does the AI Act mean for our chatbot" or "which AI Act obligations do we have". Tests each system, one at a time, for scope, role, prohibited practices, the two high-risk routes, the narrow exemption, transparency duties and general-purpose models, and writes a reasoned classification record per system plus a summary table of resulting obligations to confirm with whoever owns legal interpretation.TestingNo warnings★ 51↓ —
- test-case-writingfishzjp/qa-skillsWrite manual test cases (markmap) from docs, bugs or code — code-first: review code for bugs first; extracts machine-readable schema. Not for: requirement-analysis / test-strategy / test-case-review / automation. 从 PRD/API 文档、Bug 或代码写手动用例（markmap）——代码优先：先查代码找 bug 再写，抽 Schema。不用于：需求建模、策略、评审、自动化。TestingNo warnings★ 50↓ —