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.
- brainstormby happycatlabsCross-agent brainstorming and idea critique for early-stage decisions, architecture options, product/workflow design,…
- benchmark-checklistby hapwiVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
- review-highlightsby haqbaniReflect on a small read-only selection of saved WebstashAI highlights with source links, without creating review…
- glossaryby harlan-zwCreates, extends, or audits GLOSSARY.md, the record of what each product concept is called. Use whenever someone wants…
- sheet-designby harnessrouterHow to build a working sheet — the exact sheet.json contract, and how to design columns as a left-to-right pipeline…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- series-reviewby harperz9Use when the user asks to review several essays, posts or chapters together as a series, to check whether a set of…
- axby hasegamaUse the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or…
- decision-gateby hassan-mohiddinUse when proceeding would silently choose a consequential outcome for the user, or when accepted sources conflict in a…
- rethinkingby haydarrjrUse only when the user explicitly requests an OpenAI ReThinking/GPT-6 Astra audit or repair of repository instructions,…
- executive-technical-resumeby haziqmalikCreate a selective, human-facing one- or two-page senior or executive resume from the bundled Word template. Use when…
- clean-comments-and-guidanceby heapyAudit and reduce low-value code comments, KDoc, docstrings, CLAUDE.md, and AGENTS.md while preserving behavior and…
- composition-patternsby hectorluteroReact composition patterns that scale. Use when refactoring components with boolean prop proliferation, building…
- in-silico-perturbationby helicalaiRun an in-silico gene knockout, knockdown or overexpression screen with Helical foundation models by editing the…
- lintlang-auditby hermes-labs-aiAudit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or…
- git-workflow-and-versioningby hernandorUse when making code, documentation, tooling, or skill changes that should be committed, branched, reviewed, merged,…
- ci-debugby hernanjiangDiagnose a failing GitHub Actions check by reading the real logs and finding the first true failure.
- provenance-and-auditby herry423SHA-256 hashes, environment snapshot, and activity-aware Methods text. Use to attach a reproducibility sidecar to an…
- minimax-code-trajectoryby hetaobackendInspect or visualize privacy-aware timelines for local MiniMax Code sessions. Use when the user asks to show, draw,…
- general-videoby heygen-comAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow:…
- weekly-content-planby heymark-aiPlan a week of social media content for a HeyMark brand from its brand profile, recent results and what is already…
- watch-videoby heynagUse when the user asks to inspect a YouTube URL, local video, screen recording, tutorial, demo, UI bug video, or…
- review-changesby heyra-globalReview the uncommitted changes, the staged changes, or the current branch against a base branch for bugs, missing tests…
- auto-executionby hikari9Auto Office 3.0 reference spoke, not loaded by 3.1 runs (they use the office CLI). Internal Auto Office v3 execution…
- cluster-verifyby hiro8maKubernetes 上で動くサービスの変更を、PR を出す前にクラスタの実文脈（環境変数・Secret・クラスタ内 DNS・依存サービス）で検証する。mirrord…
- devkits-dev-from-specby hitechcloud-vietnamTurn a provider API specification (OpenAPI/Swagger, Postman collection, PDF or HTML docs) into a complete function map…
- duo-attention-budgetby hktitanTreat working memory as the binding constraint on every screen, session, and document — cap what competes for it, cut…
- matriceby hmkhallaProduit la matrice de référence d'un cours-année — les attendus du référentiel FWB et du programme SeGEC applicables,…
- inspect-historyby hoangsonwwInvestigate prior AI coding activity, commands, tool outcomes, files, sessions, and tests for an active continuity task…
- semctx-semanticby hoklimsCarry intent, invariants, decisions, evidence and unknowns through a non-trivial change using the semctx semantic…
- line-integrationby hondasportsLINE連携（webhook・リッチメニュー・連携mode・画像処理）の変更・操作をするときに使う。
- honeybadger-investigateby honeybadger-ioInvestigates a production problem with Honeybadger Insights events, faults, and deploys, and reports what happened,…
- cookie-debuggingby hong-enterprise-thoUses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and…
- hopper-speakby hopper-incTurn text into speech with Hopper text-to-speech: play it aloud, save a WAV file, or preview and pick a voice. Needs no…
- as-gyaruby hotaritobu通りがかりの、本質的で鋭いギャルとして一言言う。ユーザーが明示的に呼んだときだけ使う。
- team-deliberationby howareallwellCoordinate multiple Agents on a consequential question when the user requests team deliberation or a plan needs…
- hoyelam-modeby hoyelamOptional Hoye Lam preferences for scope, autonomy, delegation, and verified completion. Use when explicitly requested…
- compare-approachesby hranessCompare viable technical approaches against explicit constraints and evidence, producing a decision-ready…
- nestjs-trpcby hrida-aiBuild end-to-end type-safe tRPC APIs inside NestJS using the nestjs-trpc adapter —…
- self-reviewby huggingfaceUse before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the…
- talk-privatelyby hugo0Talk privately with another person's AI agent over SwarmMemo from Claude Code or Codex, in a DM or a group, optionally…
- meeting-prepby humantic-ai-incPrepares a seller for a specific sales meeting around the one outcome it has to produce, covering who is in the room,…
- hunter-company-listsby hunter-ioSaves companies and organizes them into Hunter company lists — save a company, add/remove companies to lists, create…
- comprehensive-analysisby huytieuDeep-dive 7-day analysis across all data sources for weekly reviews, board prep, and strategic planning
- ingestby hydra-dbIngest the workspace's markdown context into HydraDB now. Use for an immediate sync instead of waiting for auto-sync.
- code-reviewby hydrz用于代码评审（code review）、评审 PR，或检查一组提交和 diff。
- p34-submit-and-monitorby hyperc-aiUse when a prepared P34 request has to reach `/fit` and be followed to a result — validating it against the documented…
- agentic-code-designby hypnotoxChoose or review code structure for agreed behavior before dependent work, including ownership, state, contracts,…
- al-debugging-methodologyby hyzadanUse for unclear AL runtime defects, event/trigger failures, regressions, snapshot traces, or .alcpuprofile analysis.
