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 14 hours ago
3,223 skills
- compose-featureMeet-Miyani/compose-skillAdds, changes, or reviews a screen, sheet, dialog, or destination slice (endpoint to repository to ViewModel to UI to navigation to DI to tests) in a Compose or CMP project. Use when adding a screen, building a new feature, adding a ViewModel or destination, wiring list/detail or a form screen, scaffolding a slice, or reviewing a feature change. Covers Contract.kt, launchGuarded wiring, SavedStateHandle drafts, the state matrix, and new-feature.sh. Do NOT use for routing or architecture (compose-architecture), pure refactors, Gradle work (compose-project), recomposition or styling (compose-ui), repository or persistence work (compose-data), or expect/actual splits (compose-platform).TestingNo warnings★ 306↓ —
- sealeap-taowu-amazon-fba-fbm-margin-estimatexjli360/sealeap-amazon-skillsEstimate per-unit profit and margin for a candidate product before the first purchase order using Amazon's fee calculator with the seller's own price, landed cost, packaging, inbound freight and fulfillment assumptions, then compare FBA against FBM and test the result against a pre-set margin floor and a demand estimate. All inputs are recorded with source and date so the sheet can be re-run when fees change. Use for 利润率怎么算、FBA 费用计算器怎么用、FBA 和 FBM 哪个划算、下单前算毛利、头程分摊到单件、目标利润率定多少. Do not use to make a final sourcing decision without verifying current fee schedules, and do not treat third-party sales estimates as facts.TestingNo warnings★ 323↓ —
- sealeap-baize-amazon-paid-organic-attributionxjli360/sealeap-amazon-skillsAssess paid-versus-organic Amazon order contribution with whole-ASIN economics, cannibalization tests, query relevance, and time-window controls instead of subtracting attributed ad orders mechanically. Use for 广告单挤占自然单、关广告会不会掉单、哪些词可停、自然订单怎么算、整体广告盈利.TestingNo warnings★ 323↓ —
- sealeap-luduan-amazon-red-ocean-usp-miningxjli360/sealeap-amazon-skillsMine differentiation angles for a saturated Amazon category by tracing how a best-seller spawned derivative shapes, testing color and style fit with target-market home aesthetics, and extracting soft selling points such as production ethics and material claims from competitor bullets, then turning candidates into a factory-feasibility and claim-verification list. Produces hypotheses to test, not guaranteed winners. Use for 红海类目怎么找卖点、同质化产品差异化、爆款衍生款、卖点从哪里来、软性卖点、五点卖点怎么写才有区别. Do not use to copy competitor designs or to make unverifiable ethical, material or origin claims.TestingNo warnings★ 323↓ —
- sealeap-amazon-keyword-ranking-experimentxjli360/sealeap-amazon-skillsDesign Amazon keyword-ranking experiments that identify promising terms from relevance, conversion, current organic visibility, and placement performance, then sequence long-tail, mid-tail, and head-term tests. Use when the user asks which keywords to push, what an ad position may reveal about order potential, or why organic rank stalls despite paid orders. Do not equate sponsored placement with organic rank or guarantee movement.TestingNo warnings★ 323↓ —
- sealeap-baize-amazon-breakout-case-auditxjli360/sealeap-amazon-skillsReverse-engineer an Amazon breakout case by testing competing explanations across product innovation, brand, keyword breadth, organic visibility, timing, variants, promotions, returns, and compliance. Use for 爆款案例复盘、为什么突然增长、是不是站外、能不能复制、成功因素拆解.TestingNo warnings★ 323↓ —
- simulink-test-sequence-from-earsmatlab/agent-skills-playgroundGenerate Simulink Test Sequence blocks and harnesses from EARS requirements. Use when asked to create a test case from a requirement, generate tests from a .slreqx file, or verify a Simulink model with requirement-based tests.TestingNo warnings★ 191↓ —Also in 1 other repo
- matlab-generate-grader-assessmentsmatlab/agent-skills-playgroundGenerate MATLAB Grader assessment item sets. Use when the user asks to create MATLAB Grader assessment items, generate MATLAB assessment materials, build MATLAB homework assessment items, QTI 3 portable assessment items, or mentions "grader assessment items". Produces complete assessment item folders with description, solution, template, tests, Function call blocks, and optional QTI 3 interchange files.TestingNo warnings★ 191↓ —
- sealeap-baize-amazon-organic-rank-testxjli360/sealeap-amazon-skillsDesign a compliant Amazon organic-rank experiment around relevant high-converting queries, variant fit, controlled ad support, and incremental-profit checks. Use for 推关键词自然排名、选择推词变体、自然第一后是否停广告、精准词放量. Do not use artificial orders.TestingNo warnings★ 323↓ —
- managing-configurationancoleman/ai-design-componentsGuide users through creating, managing, and testing server configuration automation using Ansible. When automating server configurations, deploying applications with Ansible playbooks, managing dynamic inventories for cloud environments, or testing roles with Molecule, this skill provides idempotency patterns, secrets management with ansible-vault and HashiCorp Vault, and GitOps workflows for configuration as code.TestingNo warnings★ 525↓ —
- sealeap-amazon-listing-optimizerxjli360/sealeap-amazon-skillsAudit, diagnose, rewrite, creatively brief, test, and safely prepare updates for Amazon product detail pages using live marketplace and product-type requirements, verified product facts, Brand Analytics, Search Query Performance, Ads search terms, customer feedback, competitor observations, and optional third-party estimates. Use when asked to improve or evaluate Amazon titles, bullets, descriptions, backend search terms, attributes, images, video, A+ Content, Brand Story, variations, indexing, CTR, CVR, return prevention, ad-to-listing relevance, or to prepare an approval-ready Listings Items API PATCH. Default to draft and review; never invent product facts, copy competitors, manipulate reviews, or silently publish changes.TestingNo warnings★ 323↓ —
- tool-design-sprint-test-and-scoreproduct-on-purpose/pm-skillsDay 5 (Friday) sprint-closing move of a Design Sprint that produces the bundled Friday artifact covering per-customer interview observations, best quotes, scorecard grid (sprint questions by customers), observed patterns, hot takes from each team member, and the Decider summary (build, iterate, pivot, or stop, plus highest-confidence learning, most important revision, and next artifact). Use Friday after Thursday's prototype passes trial run and during/after the 5 customer interviews. The sprint's payoff artifact.TestingReview first★ 760↓ —
- define-hypothesisproduct-on-purpose/pm-skillsDefines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptions to test or aligning a team on what success looks like, before any experiment is designed. To design the A/B test or experiment that will validate the hypothesis, use measure-experiment-design.TestingReview first★ 760↓ —
- auditorQinghongLin/data2story-skillDetect and fix layout issues in generated HTML using visual rendering tests. Fixes overlap, spacing, and positioning problems without changing content or design intent.TestingNo warnings★ 158↓ —
- sparring-partnerQinghongLin/data2story-skillThis skill should be used whenever the user wants to develop, refine, or stress-test an idea, plan, design, research direction, product/business concept, argument, or any decision with more than one reasonable path — i.e. whenever they want a thinking partner rather than a quick answer. Trigger it when the user says things like "let's brainstorm", "help me think through this", "poke holes in my idea", "be my devil's advocate", "roast this idea", "challenge my assumptions", "sanity-check my plan", "what am I missing?", "I have a rough idea for…", or shares a half-baked concept and wants to make it better — even if they never use the word "brainstorm". It makes Claude a rigorous, anti-sycophantic sparring partner that researches just-in-time, drives the idea through Frame → Diverge → Converge → Pressure-test → Decide, asks sharp questions, and refuses to rubber-stamp. Do NOT use it for simple factual lookups, well-defined tasks with one correct answer, or when the user just wants direct execution of a clear insTestingNo warnings★ 158↓ —
- red-teamsuboss87/FDEOpsStress-test a plan, brief or delivery claim against evidence and plausible failure modes. Use when the user asks for a red team or preparation for a consequential decision.TestingReview first★ 940↓ —
- tracking-verifyjtrackingai/analytics-tracking-automationUse when the user wants preview QA, failure interpretation, release readiness, or an explicit publish handoff.TestingNo warnings★ 145↓ —
- test-scenarioInfrasity-Labs/dev-gtm-claude-skillsGenerates structured usability test scenarios with realistic tasks, success criteria, and facilitation notes — ready to run with real participants or in a moderated session.TestingNo warnings★ 144↓ —Also in 1 other repo
- click-test-planInfrasity-Labs/dev-gtm-claude-skillsDesign click/first-click tests to evaluate navigation and information findability.TestingNo warnings★ 144↓ —
- ab-testingInfrasity-Labs/dev-gtm-claude-skillsWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.TestingNo warnings★ 144↓ —Also in 1 other repo
- swift-iosericrisco/rsc-harnessUse when building native iOS and Apple-platform apps in Swift with SwiftUI and modern Swift concurrency — observable view models, Swift 6 strict data-race diagnostics, async/await and actors, SwiftData persistence, NavigationStack, and Swift Testing. NOT cross-platform Dart (that is `flutter`), NOT React Native (that is `react-native`), NOT native Kotlin for Android (that is `kotlin-android`), NOT shared KMP code across both OSes (that is `compose-multiplatform`).TestingNo warnings★ 272↓ —
- fixavibebuilder/claude-primeFix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.TestingNo warnings★ 120↓ —
- testavibebuilder/claude-primeUse when the user wants to know if something works — the answer requires running code, not analyzing it. Output is a verdict backed by evidence: passed, failed, or broken. Primary triggers: 'run the tests', 'does X still work after my change?', 'did the merge break anything?', 'verify the fix worked', 'check if the endpoint returns X', 'confirm nothing regressed', 'run tests/unit/test_foo.py', 'let me know the results', 'make sure my changes didn't break anything'. Hard stops — do NOT use for: reviewing test code for quality/coverage gaps, debugging why test infrastructure/databases/seed scripts are misbehaving, writing or fixing tests, diagnosing root causes of unexpected behavior. The deciding question: is the user asking for the result of executing something, or asking for help understanding/analyzing/improving something? If it's the latter, use diagnose or review-code instead.TestingNo warnings★ 120↓ —
- tddaiskillstore/marketplaceTest-Driven Development workflow - write tests first, then implementationTestingNo warnings★ 444↓ —