Skills
A skill is a folder of instructions a compatible client loads when it becomes relevant. Filter by what a skill ships and what its author declares, then read it before you install it.
Ordered one entry per publisher in turn, so a page shows as many publishers as it has rows. Every skill is listed.
- mstar-design-mdby btspoonyDESIGN.md 设计系统规范:创建/审计/维护 design tokens、三级完整性清单、light/dark 双主题(DESIGN.dark.md)。用户提到 DESIGN.md / design tokens / design…
- bugbug-tests-authoringby bugbug-ioCreates and maintains BugBug tests with AI agents from an approved plan. Use for creating tests, editing steps,…
- vpn-checkby bugrauluyurtVerify that all torrent and Soulseek traffic goes through the ProtonVPN tunnel and cannot leak to the home IP,…
- buildbetter-startby buildbetter-appConnect BuildBetter and choose a focused workflow for customer feedback, imported support tickets, recordings, surveys,…
- visual-recapby builderioTurn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries,…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- api-designerby buiphucminhtamDesigns production-grade APIs — REST, GraphQL, gRPC, and AsyncAPI patterns including pagination, versioning, error…
- content-repurposingby bulkpublishRepurpose a source article, newsletter, transcript, or announcement into a coordinated BulkPublish social content…
- eu-funding-finderby c-monganFinds EU cohesion-funded projects in Ireland (ERDF, ESF+, Just Transition Fund and others) by place, region or theme…
- cadenya-start-without-accountby cadenyaCreates a temporary Cadenya workspace for a user who has no Cadenya account, with no signup step. The `cadenya` CLI…
- code-contract-auditby calmtechltdReview selected code against contract specs and governing requirements. Run only when explicitly invoked or requested…
- market-researchby calven-aiBuilds a sourced market briefing from Calven: the trends shaping our market and their horizon, opportunities raised and…
- markingby cam-andersonExperimental rubric-first marking and feedback workflow for testing with synthetic work only. Validate a test rubric,…
- camunda-dmnby camundaUse this skill when the business, not developers, should own decision rules — eligibility, risk, routing, discounts —…
- candor-plan-a-goalby candorsystemsTurns what the person wants from their money into a plan Candor tracks: goals with a measure, a pace, and a next step,…
- canva-edit-designby canva-sdksMake edits to an existing Canva design — change or fix text, replace/insert/delete images and videos, reformat text…
- plate-decoderby carsxeDecode a license plate to VIN and basic vehicle info via the CarsXE MCP tool decode_license_plate. Use when the user…
- searchby cartesianioFind the Skills in the user's company catalog that fit one task or need the user names. Use when the user asks whether…
- entertainingby cashubskiPlan the menu, quantities and make-ahead schedule for a group. Use when the user is hosting a dinner party, feeding a…
- correctby caudraFind the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types,…
- heuristic-evaluation-usability-reviewby cd-uxReview an existing interface, prototype, dashboard, or workflow against usability heuristics; identify and…
- bom-slimmerby cdxgenReviews a codebase's direct dependencies and designs lightweight, low-risk, zero-dependency custom replacements using…
- ffmpeg-pipelinesby cecil-ia-labsDesign, validate, and execute deterministic Cecil-IA Labs FFmpeg Media Toolkit YAML pipelines and reusable presets…
- implement-validateby cedricfarinazzoSub-skill of agile-10-implement. The per-ticket gate: confirm the ticket targets the current repo, then score readiness…
- correctby celestia-milaraFind the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types,…
- verify-generationby cerredzUse on every generative step. Runs 3 to 5 verification rounds with the full suite (tests plus the matching verifier…
- svgator-motion-designby cfmoon-softwareArt-direct substantial SVGator asset creation or revision when composition, motion language, choreography, or…
- brandwell-automation-runsby chainai-orgRun and watch automations: list what exists and what is failing, read the runs, test a draft, start an active workflow…
- improve-auditby charlesjones-devAudit a codebase as an advisor and write implementation plans for another agent or a cheaper model to carry out. Maps…
- write-prdby chatprdWrite a product requirements document (PRD) from a feature idea, notes, transcripts, or codebase context, using…
- review-approachby chaychunInspect implementation choices for consequential shortcuts, loopholes, and brittle workarounds as the main agent or an…
- scheduled-peer-reviewby chaz-clarkSet up and validate the opt-in GitHub Actions scheduler for deterministic Canvas group peer-review pairing.
- economicsby checkwrightRuns Checkwright's post-iteration economics report on what the iteration cost. Run it only when the user asks for it.
- repair-sovereign-fast-bridgeby cheekyfellastefOperate and recover the existing iPad/cloud-to-Battle-Bridge Sovereign Commander fast carrier with exact immutable…
- yobiru-museby chekusuConnect Meta Muse to Yobiru. Prefer Muse's official Tailscale connector for outbound tracked requests; check the…
- stellaby cherryhqSelf-knowledge for stella, the self-hosted AI assistant. Use when users ask about configuration, setup, onboarding,…
- dt-case-generatorby cherryyang05使用CodeAgent生成DT(开发者自测试)用例。这是一个通用的的skill,指导用户通过思维链(CoT)的方式分步骤生成高质量的DT测试用例。当用户提到DT用例生成、测试用例生成、LLT测试等关键词时,应使用此skill。特别适用于大颗…
- score-catchupby chewcorpLoop dispatching parallel charter-scoring batches across every bundle a landscape sweep already tagged but no score…
- deslopby chiewoscarRemove AI-generated code slop from a branch or diff. Use when the user says "deslop", "remove AI slop", "clean up the…
- compose-state-and-effectsby chrisbanesUse when writing or reviewing Jetpack Compose state ownership, remember state, state hoisting, screen state holders,…
- promptby chrisblattmanOrganize rough requests into machine-facing prompts, refine existing prompts, and run the task when requested. Use for…
- ask-a-questionby chrisguidryAsk a person a question through transom and get the answer back: offer choices, a prompt for a typed answer, or both,…
- up-5-writing-use-case-specsby christianorralaWrites or revises one use case specification (docs/use_cases/UC-XXX-name.md) that a stakeholder can validate, an…
- sdd-implementby christianprzybulinskiSDD step 6 — task-by-task Red-Green-Refactor delivery. Use when a FEAT has ordered tasks. Not for completion verdicts…
- agents-optimizeby christopherbattlefrontlegalUse when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality…
- voice-likeness-evalby christos-antonoMeasure how much a cloned voice sounds like the real character, and whether a change really helped. Covers…
- covercount-find-placesby chriswillDiscover public CoverCount places and describe a selected venue, its menu, photos, contact details and hours. Use for…
- fix-broken-storiesby chromauiFinds the stories a Chromatic build could not capture, reads each capture error (render and interaction timeouts,…
- memory-leak-debuggingby chromedevtoolsDiagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM…