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.
- specby kashzodStructured specification process: explores code, generates user stories with testable acceptance criteria, resolves…
- track-applicationsby kasovyTrack the user's job applications and prepare for interviews with NeverApply. Use when the user asks about application…
- arenaby katouryuujiSpawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
- claude-handoffby kaustubhapundirHand the current conversation off to a fresh background agent that picks up the work immediately.
- intel-competeby kavins06Analyze companies, competitors, industries, market entry, positioning, and strategic options using value-chain…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- benchmark-checklistby kavyanagariyaVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
- kgg-project-statusby kayus24Keep substantive KGG/Vibe coding runs enrolled in project-status telemetry and correlate ChatGPT sessions without…
- verify-deliverableby kcvs2002Verify an implemented analysis, script, API, web interface, or document against concrete requirements. Use after a…
- figmaby kearrilImport Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections →…
- debug-failed-jobby keboolaFind out why a Keboola job failed and propose a fix. Use when the user says a Keboola job, extractor, transformation,…
- recommendations-apply-gitopsby kedifyApply existing Kubernetes CPU and memory recommendations to the owning GitOps repository and create a pull request. Use…
- codex-insightsby keelimExtract evidence-backed engineering insights from current or recent Codex and Claude sessions, produce concise…
- gherkin-step-scaffoldby kennygGenerate skeleton step definition files from Cucumber/Gherkin feature files. Use when the user wants to scaffold step…
- civic-researchby kerryhatcherUse when researching Civic Pulse organizations, people, elections, candidates, ballot questions, articles, calendars,…
- search-zhaopin-jobsby kerwin-kSearch, screen, draft and apply to jobs on 智联招聘 / Zhaopin using configurable keywords, cities, expectation pools and…
- councilby kevglynnConvene a council of diverse AI voices to analyze a task from multiple perspectives using different models. Each voice…
- stm32-debugby keysking诊断 STM32 启动失败、HardFault、中断或 DMA/外设异常，以及 FreeRTOS 任务卡死等运行问题，使用 GDB、ST-Link 和板端证据定位并验证修复。
- accessibility-audit-androidby khadinakbarlabsRun Android accessibility audit: TalkBack, contrast, touch targets, content descriptions. Use when the user says 'a11y…
- browserby khairmOpen, navigate, screenshot, read, click, and type in web pages from an agent. Use when the user asks to open a URL,…
- agents-debugby khasa1996Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads…
- awesome-api-designby khaskyDesigns or reviews an HTTP API's shape before code: resources, versioning, pagination, idempotency, filtering. Use when…
- automate-meby khoinguyenpham04Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a…
- telegram-backup-restoreby kiarosamaCreate and verify authorized Telegram content backups and rehearse restoration with explicit fidelity limits. Use for…
- cost-optimizationby kiliczshEstimate, compare and audit Wiro generation spending without inventing prices.
- architectby kimpersSketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use…
- aeonby kimzhang375-bitThis skill should be used for time series machine learning tasks including classification, regression, clustering,…
- explain-codeby kinwisenz-devopsUse when someone asks what this code, error, change or command means, or asks for it in simple words. Explains code,…
- study-due-cardsby kirill-markinRun a conversational spaced-repetition study session with existing Nibomo cards. Use when the user asks to study,…
- agent-plugins-referenceby kirodotdevReference documentation for the Agent Plugins v1.0.0 specification. Use when you need to understand plugin structure,…
- create-domain-mocby kittychiuCreate or revise one domain Map of Content (MOC) for a file-based PKM knowledge graph. Use when defining a new…
- automate-meby kksatUse for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a…
- klank-ceoby klankworkRun a Klank community as its CEO: work the attention queue, author and plan tasks, assign and dispatch, decide winners,…
- agb-darlehen-finanzierungby klotzketteGestaltet Darlehens- und Finanzierungsbedingungen mit Prüfung von Bearbeitungsentgelten, Pflichtangaben, Zinsänderung…
- knock-lifecycle-opportunitiesby knocklabsScan a product codebase for activation, engagement, and retention moments and recommend lifecycle messaging…
- audit-mcpby koda-ai-studioAudit MCP server configurations with agent-bom for risky setups - credentials written into config, unpinned launchers,…
- superior-architectureby kodekateamDesign, implement, or assess project structure, module ownership, dependency boundaries, and safe file or folder…
- delegationby kolbyhalcombHow to split work across agents — the planner/worker/judge separation, one ticket per fresh context, parallel agents…
- code-reviewby kolodziejczakmReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code…
- stackkits-catalogby kombifyioUse when browsing or evaluating StackKits definitions, kits, and catalog facts through the selected local StackKits…
- local-hand-reconcileby kongbu0621对 Local Hand 原作业的 UNKNOWN、副作用或丢失回执进行固定只读来源核对；在重取某轮核对结果、明确启动新观察或停止准确核对轮次时使用。
- best-practice-researchby kongpediaResearch current best practices, technical reference implementations or version-sensitive guidance using primary…
- init-generic-templateby konradcinkuszUse when starting a brand-new repository from nothing - the repo name is passed and the repo is empty. Scaffolds the…
- evalby konstantinosbotonakisRun the Context Diet decision corpus and report false drops, replacement rate, compression and cost. Use when the user…
- domain-modelingby kontouraiBuild and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md,…
- manage-prby konvoulgarisUse for any work on a pull request — writing or rewriting its title and description when creating or editing a PR, and…
- examineby koryaReview a code change rigorously — a PR, branch, commit range, or the working tree. Confirm the problem is real, sketch…
- atlas-discipline-do-your-research-deepby kosif199022-jpgFan out verification over a typed full inventory of the session's claims (assumptions, facts, specifics, premises,…
- setupby krambertechGuide a learner from connecting Lymi to their first review. Use after install or first connection, or when they ask to…
