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.
- swe-improve-architectureby tsharpFind architecture improvement candidates, generate a visual before/after report, and explore the selected design. Use…
- pmx-process-miningby tteschonProfile event logs and discover process models using the pmx CLI. Use when the user has an event log (.xes, .xes.gz, or…
- compare-gradle-buildsby tuistCompares two Gradle build runs to identify duration regressions, cache changes, and task outcome differences. Can be…
- migrateby turboofficeIn TurboOffice, a whole deal coming over from another system with its paper, live or already over — "here is the…
- create-n-day-planby tushar2708Create a chronological, sprint-based N-day development plan from a project specification. Use only when the user…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- tuturuuu-cli-resourcesby tutur3uQueue heavy local Tuturuuu validation and diagnose competing CPU or RAM workloads with ttr resources.
- drafting-an-adrby tvnaUse when a decision affecting architecture (structure, non-functional characteristics, dependencies, interfaces, or…
- workspace-doctorby twyd-aiDiagnose whether Nemeda Agent Kit is correctly configured for the current repository, including config validity,…
- code-reviewby tylerakinsReview local diffs, branches, implementation plans, or GitHub pull requests against requirements and repository…
- debugging-memoryby tyronerossConsult stored debugging incidents before fresh investigation when the bundled memory MCP is available; validate past…
- academic-debateby u9401066學術辯論與觀點比較框架。 LOAD THIS SKILL WHEN: debate、辯論、pro/con、正反方、devil's advocate、挑戰假設、counter-argument、反駁、compare…
- hu-knowledgeby uashogeschoolutrechtFind and apply reviewed HU-wide knowledge before making development decisions, especially for HU terminology,…
- playwright-visual-testingby uiverifyMake @uiverify/playwright (archive-replay) captures deterministic so real-page visual tests stop coming back "changed"…
- uizze-uiby uizzeThe official Uizze skill for building and improving UI/UX. Work with your project's code and assets, and use uizze.com…
- blast-radiusby ulises-jeremiasFind what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
- company-work-logby unboxerscorpRecord Unboxers work actions, changes, decisions, verified outcomes, and handoffs in the connected company GBrain…
- pm-releaseby unbraindUse when preparing a pm release, reviewing its gates, publishing, or verifying the released artifact. Keep source,…
- uniform-editor-experience-reviewby uniformdevAudits and fixes Uniform frontend components in the Canvas visual editor (Next.js App Router and Page Router). Resolves…
- outreachby unifygtmOutreach with Unify, create email sequences, generate per-prospect drafts, enroll prospects, and manage rep tasks…
- modernize-toolchainby unionalReplace a TypeScript library's build, lint, test and dependency stack in one pass — tsdown for the build, biome for…
- kobana-inboxby universokobanaOperate Kobana Autonomous Inbox through the kobana-inbox MCP server. Use for inboxes that receive e-mails and the AI…
- specful-planby unkos-devUse when a change needs a persistent implementation plan, unresolved design choices must be settled before planning, or…
- use-unpitchby unpitchUse Unpitch naturally to read workspace data, find business context, save or update typed Documents, inspect evaluation…
- add-multi-writer-syncby unstoppable-stackManaged collaborative JSON data, or advanced Autobee integration for existing schema-based stores.
- upstash-box-pyby upstashWork with the upstash-box Python SDK for sandboxed cloud containers with AI agents, shell, filesystem, git, cron…
- handoffby uraxiiCompact the current conversation into a handoff document for another agent to pick up.
- shipby urban233Decide whether a change is ready to hand to a human, and open the pull request when it is. Use once the work is done…
- linear-triageby useopencompanyTriage a Linear issue queue into clear priorities, owners, and next actions without silently changing issues.
- writ-http-functionsby usewritBuild browserless API functions in Writ from a site's real network requests or its server-rendered HTML, so a saved…
- otel-guidesby using-systemCurated map of the official OpenTelemetry documentation by language. Use when planning or implementing OpenTelemetry…
- planning-implementationsby uw-ssecUse when a feature, refactor, or multi-file change needs to be designed before coding. Triggers: plan X, design the…
- helloby uze-shGreets the world. Only the person can invoke it, never the model on its own.
- freecad-fem-checkby v0v1kkkBuild or audit reproducible preliminary FreeCAD FEM checks with explicit solver capability detection, analytical…
- update-zotero-recordsby vagishhemmigeUse when adding publications or book chapters to a configured Zotero library, reviewing publication candidates from…
- broby vagusxRestate the last message in plain human language, with no jargon.
- broby vahaahRestate the last message in plain human language, with no jargon.
- vaiz-helpby vaizcomAnswer "how does Vaiz work" questions from the built-in knowledge base — search help articles, FAQs, and tutorials,…
- similarby valency-ossUse when the user wants to find papers similar to a specific paper, asks 'what's related to this paper', 'find me more…
- valcraft-honeby valzavRefine an existing prompt artifact — inline prompt text, markdown prompt files (system prompts, agent instructions,…
- release-controlby vamsimarripudiAudit, merge and deploy code only when the exact release candidate is verified green end to end.
- calculate-business-caseby vamtaknebudeCheck calculation readiness for one exact Uprali Case Revision and run the confirmed complete calculation command. Use…
- evidence-output-reviewby vassiliylakhoninReview agent-produced claims against caller-supplied evidence before a human decides whether to relay the output.
- evals-traceby vatsa10Instrument or inspect actual model, retrieval, tool and agent traces for the requested application.
- seating-from-rsvpsby vayllon301Build or finish a seating plan on Tu Día de Blanco for a couple or wedding planner, including groups, Table capacity,…
- content-plannerby venilkukadiya52Build a varied evidence-backed content plan without forcing a daily posting calendar. Use on /CSplan or /CSseries.
- vne-frameby vertexnovaName the frame inputs (camera, lights, per-pass GPU struct, bindings, target texture) before editing a pass, shader,…
- ce-compound-refreshby vib795Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, consolidating,…
- googledriveby vibetaskingWorking composio googledrive action names and shapes, the four upload actions, upload verification, metadata field…
