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.
- kademi-coding-standardsby kademiKademi's house coding standards, the review that checks code against them, and how to confirm a change actually works…
- hyperframesby kalajar2000Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or…
- adaptyvby kalarislabsHow to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval.…
- obsidian-cliby kalebcoleInteract with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and…
- master-stack-syncby karanzing1992Share and verify new capabilities, technology changes, integrations, vulnerabilities, version upgrades or deployments…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- labelby karch4162Name a graph mirror's communities vault-side — no repo checkout, no resync. Reads graphify/<repo>/graph.json, names…
- loreby karloowsHave the AI add or fix code comments and docstrings across a diff or file so they match this repo's lore policy, in…
- arclith-deployby karned-agencyPackage and deploy an Arclith service with its generated Docker runtime, probes, configuration, secrets, Compose, or…
- adaptyvby kashvatsHow to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval.…
- benchmark-checklistby katouryuujiVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
- new-clientby kauneongaSet up a new answering service client from scratch - the account and its owner, phone lines, numbers, call script,…
- codebase-designby kaustubhapundirShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
- benchmark-checklistby kavyanagariyaVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
- kgg-supervisorby kayus24Coordinate a small KGG ticket across the shared goal, source-of-truth documents, Fresh Main, and the UI-Lab test loop…
- hyperframesby kearrilMandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or…
- recommendations-getby kedifyRetrieve Kubernetes CPU and memory recommendations through Kedify MCP, a local kedr scan, or a Kedify Dashboard JSON,…
- eli5by keelimExplain a topic for a beginner as a standalone visual HTML page, using ASD-STE100-inspired clarity principles while…
- github-hardenby kennygAudit the security settings of public GitHub repos and apply a hardened baseline. Use when the user asks to audit,…
- civic-user-adminby kerryhatcherUse when a Civic Pulse administrator wants to find registered accounts, list users, check account roles, or promote an…
- graybeard-auditby kevglynnWhole-repo audit for over-engineering. Like graybeard-review, but scans the entire codebase instead of a diff: a ranked…
- stm32-firmwareby keysking实现 STM32 应用功能、移植外设驱动或编写 FreeRTOS 任务，按实际 HAL1/HAL2/LL 和工程结构开发并验证代码。用于功能开发、驱动集成与固件维护。
- account-deletion-flow-androidby khadinakbarlabsImplement Google Play required account deletion: in-app AND on website. Use when the user says 'account deletion…
- aws-blocksby khasa1996Guides building full-stack applications with AWS Blocks — an Infrastructure-from-Code framework. Applies when creating…
- awesome-bug-fixby khaskyFixes a bug through a runnable reproduction and its root cause. Use for errors, crashes, failing tests or builds, flaky…
- telegram-bot-reconstructionby kiarosamaReconstruct an authorized Telegram bot or user-account automation surface from exact observable text, commands, glass…
- model-discoveryby kiliczshFind, filter, compare and select Wiro models using live schemas and current prices.
- blast-radiusby kimpersFind what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
- plain-docsby kinwisenz-devopsUse when asked to write, rewrite or review a README, guide, how-to, tutorial, reference page or explanation. Writes…
- migrate-pluginby kirodotdevMigrate an existing POWER.md-based Kiro Power to the Agent Plugins v1.0.0 specification. Use when converting a power…
- blast-radiusby kksatFind what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
- klank-workerby klankworkRun the Klank worker loop: find communities and tasks that fit, then inbox, assignment, workspace, checkpoint,…
- agb-haftung-maengelby klotzkettePrüft Haftungsausschlüsse, Gewährleistung und Verjährung nach Vertragsart und Kundenkreis. Erstellt verständliche…
- knock-migrate-to-knockby knocklabsInvestigate existing messaging infrastructure in a codebase and recommend how it maps to Knock. Use when migrating from…
- bomby koda-ai-studioGenerate an AI-BOM (CycloneDX or SPDX) with agent-bom for this machine's agents and MCP servers, a project, a container…
- superior-commentsby kodekateamAdd, revise, or remove source-code comments while preserving executable behavior. Use for comment-only cleanup,…
- create-verification-skillby kolodziejczakmGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or…
- code-review-excellenceby kongpediaMaster effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing…
- reference-architectureby konradcinkuszUse when designing a new service or judging an existing repo against the estate's architecture. The 15 numbered…
- statsby konstantinosbotonakisShow Context Diet usage statistics for this machine. Use when the user asks how much Context Diet saved, how many…
- grill-with-docsby kontouraiA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
- polishby konvoulgarisRun a code review with autofix, then a simplification pass, then commit the result. Use when the user runs /polish, or…
- rebaseby koryaRebase a work-in-progress or completed branch onto a new base, ensuring the rebased changes still satisfy their…
- atlas-llm-evaluation-engineering-build-llm-judgeby kosif199022-jpgDesign, calibrate, and bias-audit an LLM-as-judge so its scores track human judgment: named criteria with anchored…
- weekly-check-inby krambertechSummarise how the learner's week in Lymi went and suggest what to do next. Use when the learner asks how they are…
- detect-ai-smellsby krokokoAssess whether a codebase has gates to detect AI-generated code smells and recommend what to add. Trigger phrases:…
- doc-coauthoringby kru-offyGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation,…
- researcherby krzysztofdudekUse when user wants to optimize or tune something measurable through repeated experiments — "make X faster", "improve…
- teach-it-backby kuliko-incRun a Feynman-style teach-back session grounded in Kuliko resources and the learner's quiz/review evidence. Let the…
