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.
- setupby tightknitaiConnect this client to the Tightknit MCP server, authenticate with OAuth, and verify the connection by listing the…
- compose-performance-auditby till-tusDiagnose Compose jank, excessive recomposition, slow lists and startup regressions by connecting code findings to…
- monday-control-planeby timoygeroinGovern multiple task-local MondayID cells as one organism. Use when a task spans multiple worldlines/roles, Dima asks…
- tinyfish-websearchby tinyfish-ioFree web search and page reading with TinyFish search and fetch_content. Use for any question needing current web…
- charter-architecture-simplificationby tiziano-aiArchitecture simplification before building or refactoring: use suitable native, standard or upstream primitives to…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- howby tlogbenExplains how a part of the codebase works, at the level a senior engineer needs to start working in it: runtime flow,…
- revid-product-description-to-adby tmakersasTurn a product description (free-form text — no URL needed) into a punchy 15–30 second AI-generated ad with hooks, CTA,…
- vue-feature-checkby tobiaswaeldeVerify changed Vue/Nuxt feature behavior, interaction states, accessibility, responsive layout, and supported locales…
- rust-benchmark-ciby tobyhedeThis skill should be used when the user asks to "add benchmarks", "set up criterion", "add a benchmark gate to CI",…
- agentifyby tokencanopyBeta — Deploy the autonomous-repo feedback loop into a GitHub repo. Scaffolds the lane workflows, the runtime skill,…
- quality-interviewby tollens-aiHear what matters to someone about a software project's quality, and what worries them, in their own words before any…
- feedbackby tomikngCollect and submit feedback about Superset (bug reports, feature requests, or general feedback) privately to the…
- better-accessibilityby tommyc10Review and fix keyboard, focus, ARIA, forms, and screen-reader behavior against WCAG 2.2. Use when the user asks about…
- creating-a-sequenceby topo-ioAuthor a new Topo outreach sequence from a name and ordered steps, clone an existing one, or replace the copy of a…
- correctby torus403Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types,…
- mba-essay-guideby tough-tongueResearch an MBA program's application essays (written prompts, video essays, optional and reapplicant essays) across…
- outreach-briefby tractionbdUse when the user wants to prepare for reaching out to someone: the angle, what to say, the last interaction. Gets and…
- reg-intelby transitrixCollect regulatory-source changes in practice — the operational counterpart to the methodology's codex / SEGMENT /…
- trip-readiness-checkby travelaisolutionReview an upcoming traveler.md trip for missing, unresolved, contradictory, or time-sensitive pieces before departure.…
- three-kingdoms-focus-musicby travisebillCreate Three Kingdoms-inspired music release packages for listening, publishing, and archival reuse. Use when the user…
- mcp-devby travnieDesign, build, test and ship MCP servers and MCP Apps for Claude and ChatGPT/Codex: deployment choice, tool design,…
- chinese-documentationby treasuregooldove中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。
- orca-peer-refactorby treflebonbon明示依頼された元候補を Orca の native orchestration と read-only peer で改善・検証し、独立レビューと報告まで進める。
- recs-subagent-driven-developmentby trevokeUse when executing implementation plans with independent tasks in the current session — for projects that keep records…
- codebase-onboardingby trikitrokBuild a fast, evidence-backed mental model of an unfamiliar repository.
- diataxis-write-docsby trogonstackDraft or revise project documentation for the reader's purpose using Diataxis. Use for writing tutorials, how-to…
- user-passthroughby truerowingBuilds app features that act as the signed-in person in another system through Greenlight's user passthrough…
- derivative-resourcesby truinorvaTRIZ Derivative Resources Analysis — takes the resources a system already has and transforms them into derivative…
- frontend-designby tryhand-co-ltdGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with…
- terra-routesby tryterraPush GPS routes to users' fitness devices with Terra API Routes (pre-release). Use when creating GPS courses or…
- product-senseby tryvetoChoose Veto product priorities, first features, surfaces, or scope. Use for an unsettled product decision; not a…
- product-requirementsby tsadoqTurns a written discovery into testable requirements at docs/product/<slug>/requirements.md: one EARS sentence per…
- swe-improve-maintainabilityby tsharpFind and prioritize maintainability improvements with a visual HTML report. Use for reducing change cost, improving…
- 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-test-caseby tuistCompares a single test case's behavior across two branches, analyzing pass/fail status, duration, flakiness, and…
- offerby turboofficeIn TurboOffice, an offer on a property — from our buyer, or written up on the caller's own listing — "offer on 155 Main…
- create-n-day-planby tushar2708Create a chronological, sprint-based N-day development plan from a project specification. Use only when the user…
- tuturuuu-cli-tasksby tutur3uCapture, organize, and verify Tuturuuu tasks and templates through ttr.
- drafting-issuesby tvnaUse when the user -- or the current workflow itself, mid-task -- needs to open, file, or draft a brand-new GitHub issue…
- workspace-methodologyby twyd-aiApply the shared Nemeda methodology to cross-repository or client-project work: confirm exact target, preserve dirty…
- tkstack-principlesby tyler-r-kendrickApply tkstack's personal engineering principles when designing, implementing, or reviewing code, skills, hooks, rules,…
- decision-partnerby tylerakinsClarify goals and challenge consequential assumptions through focused questions and evidence. Use when asked to…
- debugby tyronerossInvestigate and repair code failures by tracing causal mechanisms, consulting incident memory when available and…
- academic-writing-harnessby u9401066Cross-agent workflow for evidence-grounded manuscripts, proposals, reports, student papers, and preprints with…
- make-agentby uashogeschoolutrechtCreate a custom HU agent with a narrow role and an explicit tool allowlist. Use when a reusable role needs its own tool…
- setup-visual-testingby uiverifySet up UI Verify visual regression testing in a repo end to end — pick the capture path the same way the one-line setup…
- bragby ulises-jeremiasTurn the current project website into a short, polished, shareable launch video using Hyperframes. Use when someone…
- git-protectby ulyssesleolee保护分支;/git-protect [BRANCH] [--release|--status] [--lang <language>] [--help].