Browse the registry

Every entry, alphabetically — 81,496 in total. Page 220 of 326.

• kevinnft-to-issuesBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bulle
• kevinnft-to-prdTurn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wa
• kevinnft-triageTriage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage i
• kevinnft-ubiquitous-languageExtract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and propo
• kevinzai-mintlifyBuild and maintain documentation sites with Mintlify. Use when
• key-assumptions-checkUse when an analysis, plan, estimate, or forecast rests on things being taken for granted, and the user wants
• key-relationship-healthMonitors the health of the executive's most important relationships — key customers, partners, advisors, and s
• keyboardLoad this skill for every project containing interactive UI elements — buttons, links, modals, dropdowns, slid
• keyboard-ext-axAccessibility snapshots and tap coordinates for active third-party iOS keyboards in Simulator.
• keyboard-layout-decoderDecode garbled Russian/English wrong-keyboard-layout text (ЙЦУКЕН/QWERTY).
• keyboard-shortcutsUIキーボードショートカットを「公式基準（W3C APG / WCAG）＋プラットフォーム規約（Apple HIG / Fluent UI）＋デファクトスタンダード（GitHub・Gmail・Slack等）」に沿って設計
• keychain-managerManages secrets and API keys in the macOS Keychain using the security CLI. Triggered when a user asks to store
• keycloak-mcpMCP server for KeyCloak Admin REST API via Service Account
• keyframe-mcpAnimate 2D skeletons in Keyframe.it; rig, animate and export pixel-art sprites in Sprite Puppeteer.
• keyhunterOperator playbook for the keyHunter CLI — FOFA discovery, product fingerprinting, weak-credential panel login,
• keymemAssociative key-graph memory for LLM agents — recall by association, not vector similarity.
• keynote-harvest-mcpHarvest Keynote and PDF slide decks into previews, text, image assets, and a manifest for agents.
• keyshot-mcpControl local KeyShot scenes, cameras, environments, and renders through headless scripting.
• keystone-verify-proxy-mcpVM-side verify proxy for keystone attestations
• keystore-mcp-serverEncrypt/decrypt Ethereum keystore JSON V3 with scrypt/PBKDF2 for secure cold storage
• keyword-clusterBuild a pillar+spokes content cluster plan from seed keywords — SERP-overlap clustering via keyword_cluster.py
• keyword-cluster-builderBuilds keyword clusters, topic groups, and content maps for SEO programs. Use when the user asks for keyword g
• keyword-clusteringCluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "grou
• keyword-deep-diveUse when planning to rank for a specific keyword. The agent Googles it, reads the top 10, classifies intent, r
• keyword-expansionExpand and refine search keywords (synonyms, acronyms, exclusions) and update `queries.md`. **Trigger**: keywo
• keyword-extractor-ai-mcpKeyword Extractor Ai MCP Server by MEOK AI Labs
• keyword-graph-viewExtract exactly 8 context-sensitive keywords from Chinese, English, or mixed text and turn them into a distrib
• keyword-optimizerOptimize app title, subtitle, and keywords for maximum App Store discoverability. Use when launching a new app
• keyword-researchExpand a seed keyword into a clustered keyword universe using Keywords Everywhere MCP — grouped by search inte
• keyword-research-thkeyword research หา intent + volume + competition | สำหรับ นักการตลาด ครีเอเตอร์ฟรีแลนซ์ . Triggers when user
• keyword-researcherResearch keywords — intent mapping, competition analysis, long-tail opportunities, and cluster groupings.
• keywordsResearch high-intent TikTok and Instagram search keywords using ScaleBrick's framework. Returns categorized ke
• kgQuery and maintain a per-project knowledge graph (`./.kg/graph.db`) of non-derivable codebase context — archit
• kg-builderDesigns and builds knowledge graphs from documents — ontology modeling with domain/range constraints, entity/r
• khaitrang1995-ciGenerate a CI/CD pipeline — build, test, security scan, deploy. Supports GitHub Actions, GitLab CI, Bitbucket
• khaitrang1995-monitorGenerate monitoring config — Prometheus alert rules, Grafana dashboard JSON, ServiceMonitor.
• khalaCross-session knowledge sharing via filesystem. Multiple concurrent Claude Code sessions become collectively s
• khaledsaeed18-brainstormingTurn a rough idea into a fully formed, written design through collaborative dialogue — exploring intent, requi
• khaledsaeed18-changelogGenerate a changelog or release notes from Git history, grouped by change type, written in user-facing languag
• khaledsaeed18-create-skillAuthor a new skill for this repository end to end by choosing its category, writing trigger-friendly frontmatt
• khaledsaeed18-dependency-auditAudit a project's dependencies for outdated and vulnerable packages and surface breaking-change notes for upgr
• khaledsaeed18-git-commitCommit work the right way by gathering full repo state, respecting the project's commitlint/pre-commit/branch
• khaledsaeed18-grill-with-docsStress-test a plan against the project's existing domain model by challenging terminology, surfacing contradic
• khaledsaeed18-handoffCompact the current conversation into a handoff document for another agent to pick up. Use when ending a sessi
• khaledsaeed18-owasp-securityReview code being written or modified against the OWASP Top 10:2025 and ASVS secure-coding requirements, catch
• khaledsaeed18-pr-descriptionGenerate a clear, reviewer-friendly pull-request description from a diff, covering what changed, why, risk, an
• khaledsaeed18-webapp-testingVerify a web application works correctly in a real browser using Playwright. Covers page navigation, form subm
• khayden73-changelogadd details for the current branch to a project CHANGELOG for developer reference
• khazix-writer数字生命卡兹克（Khazix）的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于：写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。
• KhazP/vibe-coding-prompt-templateTemplates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
• khiipCapture the web, keep your copy as plain Markdown, and recall it by meaning. Local-first daemon.
• khwan-mcpDurable AI memory: recall distilled facts in a later session or subagent, and remember new ones.
• kiaaccess-mcpKia Access MCP server for Claude — developed and maintained by AI (Claude Code)
• kiakun-skillsKiakun 的 AI Agent Skills 集合。包含小红书自动化、B站视频总结、文件夹向量化知识库、中文优先对话、Claude Code 第三方 API 配置、GPT Image 2 异步容错 API 生图、图片
• kibana-dashboardSpec a Kibana dashboard — panels, KQL filters, on-call layout. No auto NDJSON export to prod.
• kiben-check相手の発言・議論ログ・自分の主張が詭弁かどうかを、詭弁の特徴のガイドライン19条＋論理学の誤謬で即判定し、「本来の論点」と「論点に戻す一言」まで返す。「詭弁チェック」「これ詭弁？」「詭弁かどうか見て」「論点ずれてない？」
• kicad-copilot-mcpFile-oriented MCP server for KiCad schematics, PCB placement, routing, and pours.
• kicad-libraryLibrary management workflow for KiCAD — creating symbols, footprints, and managing libraries via MCP tools. Tr
• kicad-manufactureManufacturing and fabrication workflow for KiCAD projects via MCP tools. Triggers on: "send to fab", "order bo
• kicad-mcp-pronpm wrapper for the KiCad MCP Pro Python package.
• kicad-pcbWorkflow skill for KiCAD PCB layout and routing via MCP tools. Triggers on: "layout the board", "route traces"
• kicad-reviewDesign review and validation workflow for KiCAD projects via MCP tools. Triggers on: "review my design", "chec
• kicad-schematicWorkflow skill for KiCAD schematic design via MCP tools. Triggers on: "design a circuit", "add a component", "
• kickoffInitialize a new project by analyzing source documents and generating requirements.md and design.md
• kickoff-phaseBuild ONE scoped phase of an existing multi-phase plan in a fresh session — re-verify the plan against the liv
• kickoff-prepPrepares the onboarding kickoff — agenda, stakeholder map, success criteria to confirm, and a proposed milesto
• kids-robot-safetyUse when designing, coding, or reviewing any robot that children (under 14) will touch, hold, or operate — toy
• kielelliset-oikeudet-ja-velvoitteetKielelliset oikeudet ja viranomaisen kielelliset velvoitteet Suomessa (kielilaki 423/2003 ja perustuslaki 731/
• kiinteistokauppaKiinteistön kauppa Suomessa maakaaren (540/1995) mukaan. Käytä tätä skilliä, kun käyttäjä valmistelee tai tark
• kika-design-systemUse when building or modifying SwiftUI views, settings windows, menu-bar UIs, or any surface for the KIKA app
• kiko197-code-review系统化地进行代码审查或自我审查。当需要审查一个 PR/改动、输出结构化评审意见、按严重程度分类问题、检查安全/性能/可维护性/正确性等维度的隐患时使用。
• kiko197-debugging系统化地定位和解决软件问题。当遇到 bug、崩溃、异常、性能或行为不符合预期的问题，且原因不明、需要按证据推理、缩小范围并验证修复时使用。
• kiko197-git-workflow规范化、可追溯的 Git 工作流。当需要创建功能分支、编写规范的提交信息、整理/清理提交历史、平滑 rebase 或合并、解决冲突、回滚错误提交，或在团队协作中保持 git 历史清晰可读时使用。
• kilawatt-mcp-serverKilawatt Cloud MCP Server for AI Agent GPU Orchestration
• kilimo-mcpMCP server for agriculture coordination in East Africa (kilimo = farming)
• kill-dev-processKill orphaned dev servers, browsers, and port-hogging processes spawned during development. Use when ports are
• kill-slopAudit a file or draft for AI slop and off-voice lines against the author's bound voice, report findings with i
• kill-stale-mcpKill stale/orphaned MCP server processes leaked by ended sessions — npx-launched servers (chrome-devtools-mcp,
• kill-test-first[决策:预注册] Pre-registration audit for new research directions, quant strategies, or thesis topics: falsifiable h
• kill-the-standupReads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done
• killbottleneck-mcpMCP server for killBottleneck — connect your AI assistant (Claude Desktop, Claude Code, …) to your killBottlen
• KillerStrike17/A2A-Agent2Agent-Protocol-demo
• kiln3dKiln MCP server for agents: design, slice, print, monitor, and recover physical objects safely.
• kilonova-mcpPersistent local knowledge for AI coding agents with structured records, search, and DOT context.
• kilpailu-complianceKilpailuoikeudellinen compliance ja viranomaistarkastuksiin varautuminen Suomessa. Käytä tätä skilliä, kun org
• kilpailunrajoituksetKiellettyjen kilpailunrajoitusten ja määräävän markkina-aseman väärinkäytön arviointi Suomen ja EU:n kilpailuo
• kilter-mcpRead-only access to your Kilter Board logbook: sessions, sends, projects and grade stats
• kimchiTurn a raw product idea into build-ready docs — one doc per EPIC with locked decisions, exact API contracts, a
• kimi-cli-runtimeInternal helper contract for calling the kimi-companion runtime from Claude Code
• kimi-delegateDelegate a coding task to the Kimi Code CLI (`kimi`) as a background implementer, then review its diff and lan
• kimi-k2-promptingHow to write effective prompts for Kimi K2.7 when delegating
• kimi-peer-writerPeer-сессия DP.SC.154 где Kimi = писатель, Claude = напарник. Запускается простой фразой. Включает ОРЗ Opening
• kimi-webbridgeControl the user's real browser through the local Kimi WebBridge daemon. Use when an AI agent needs to open UR
• kimsungwhee/apple-docs-mcpMCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objecti
• kindesunterhaltPrüfung und Berechnung des Kindesunterhalts – Verwandtenunterhalt §§ 1601 ff. BGB, gesteigerte Erwerbsobliegen
• kindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.
• kindle-coverGenerate a full-wrap paperback cover PDF for Amazon KDP (front + spine + back in one file). Use this skill whe
• kindlepubEnd-to-end Amazon KDP self-publishing pipeline for a finished book manuscript. Builds the reflowable Kindle EP
• kindlesmsSend SMS, manage approved sender IDs, and check credits via KindleSMS.
• kinetiKineti: spend cap, undo, and test proof for AI coding agents
• kinetic-typographyThis skill should be used when the user asks to "animate a headline", "make a kinetic typography video", "do a
• king-crimson-mcpKing Crimson discography and live-performance history with a curated line-up-era model.
• kinocutGuardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.
• kio-orzeczenia-mcpMCP server for Krajowa Izba Odwolawcza (KIO) rulings from orzeczenia.uzp.gov.pl.
• kiosk-marketplaceBuild a Sui NFT marketplace with the Kiosk standard, transfer policy, royalties. Use when the user wants a Sui
• kip-mcp-serverAn MCP server that reads your boat's Signal K data and helps AI assistants design and install KIP dashboards.
• kiprio-mcp23 API tools for Claude Code — email, DNS, SSL, NLP, scraping. Free tier included.
• kira-mcpSkills and Scars for AI agents - your agent records its failures and never repeats them.
• kiriyaDeveloper tools for files, git, ports, processes and more, the same on Windows, Linux and macOS
• kiro-debugInvestigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, veri
• kiro-discoveryEntry point for new work. Determines the best action path or work decomposition (update existing spec, create
• kiro-guideUse when configuring Kiro IDE or CLI v3 hooks, command actions, or agent actions. Triggers on .kiro/hooks JSON
• kiro-implImplement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tas
• kiro-project-setupHelps users set up a complete Kiro project structure with steering files, skills directory, and proper configu
• kiro-reviewReview a task implementation against approved specs, task boundaries, and verification evidence. Use after an
• kiro-spec-batchCreate complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent di
• kiro-spec-designCreate comprehensive technical design for a specification
• kiro-spec-initInitialize a new specification with detailed project description
• kiro-spec-quickQuick spec generation with interactive or automatic mode
• kiro-spec-requirementsGenerate comprehensive requirements for a specification
• kiro-spec-statusShow specification status and progress
• kiro-spec-tasksGenerate implementation tasks for a specification
• kiro-steeringManage {{KIRO_DIR}}/steering/ as persistent project knowledge
• kiro-steering-customCreate custom steering documents for specialized project contexts
• kiro-steering-porterConvert any Claude Skill’s SKILL.md into Amazon Kiro steering files (.kiro/steering/). Extract goals, stack, s
• kiro-validate-designInteractive technical design quality review and validation
• kiro-validate-gapAnalyze implementation gap between requirements and existing codebase
• kiro-validate-implValidate feature-level integration after all tasks are implemented. Checks cross-task consistency, full test s
• kiro-verify-completionVerify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works,
• kirok-mcpPersistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation
• kish21-design-systemPhase 2 (Development) of product-playbook — design the product's UI BEFORE building screens. Turns "I don't kn
• kitGenerate a lead magnet content kit — ebooks, worksheets, checklists, prompt libraries, ICP templates, and land
• kit-grpcgRPC with Go Kit. gRPC services.
• kit-lang/packages/kit-mcpMCP (Model Context Protocol) server library for Kit — stdio and Streamable HTTP transports
• kitbag-mcpZero-config MCP server bundling 50+ utility tools: converters, OCR, scraping, and formatters.
• kitchensink4pptPowerPoint (.pptx) MCP server: editable vector diagrams, tables, budgeted reads, render-to-verify
• kitchensink4webBrowser MCP server: budgeted page reads, honest unread accounting, structured extraction.
• kitchensink4wordWord (.docx) MCP server: 222 operations, live editing, tracked changes, citations, mail merge.
• kitchensink4xlExcel (.xlsx) MCP server: calculated/cached/missing labels on every value, formulas, verified writes
• kith-mcpQuery the KITH catalog (kith.com, NYC): search streetwear and sneakers, newest arrivals by type, enriched prod
• kitsu-mcpSearch anime on Kitsu. No key required.
• kitsune-mcpThe shape-shifting MCP hub — shapeshift() into 130,000+ MCP servers at runtime. One entry point, no restarts,
• kiwi-cicd-debuggingUse when a deploy.yml run fails on Kiwi's prod CI/CD pipeline, bootstrap-cicd.sh fails against real GCP, or yo
• kiwi-mcpMCP server for Kiwi.com flights: search, airlines. Needs a free API key.
• kiwoom-mcpKiwoom Securities REST API for Korean markets — 236 endpoints, streaming, gated order execution
• kiwoom-mcp-serverRead-only MCP server for the Kiwoom Securities REST API: market data, account inquiry, ISA tax tool
• kiyas-cliAI design fidelity — compare Figma designs or screenshots against rendered UI. No API keys.
• kk-exhibition-planner-skill展览策划工作助手，覆盖从项目启动到输出展览大纲的完整流程。适用于企业展厅、博物馆/文化馆、文旅/主题展馆三类项目。当用户需要策划展览、撰写展陈大纲、确定展览主题、梳理展览叙事逻辑、整理甲方资料时使用此 skill。
• kklimuk-commitCreate well-structured git commits from the current working tree. Use when the user says 'commit', 'save my wo
• kklimuk-security-reviewReview code for security vulnerabilities. Use when the user says 'security review', 'security audit', 'check f
• kktConstrained optimization workflow for ordinary coding requests. Use when a coding agent should capture user me
• kkt-deepDeep constrained optimization workflow for high-impact coding and product-engineering work. Use when a coding
• klaket-mcpLet AI agents watch videos: local transcripts, speakers, scenes, chapters and moment search
• klanex-mcpReliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
• klartextEntfernt KI-typische Schreibmuster aus deutschen Texten und macht sie menschlicher. Einsetzen wenn der Nutzer
• Klavis-AI/klavisKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
• klaviyo-automationAutomate Klaviyo tasks via Rube MCP (Composio): manage email/SMS campaigns, inspect campaign messages, track t
• klaviyo-webhooksReceive and verify Klaviyo webhooks. Use when setting up Klaviyo webhook handlers, debugging Klaviyo-Signature
• kleinanzeigen-mcpSearch Kleinanzeigen.de, Germany's largest classifieds site, for second-hand listings
• kleinanzeigen-readerRead, scrape, and analyze ANY listing from kleinanzeigen.de — cars, electronics, furniture, real estate, cloth
• kleos-cliCLI do Kleos: gere, agende e meça posts UGC do seu app pelo terminal ou por qualquer agente de IA. Cliente do
• klingThe generative-video producer for native 4K, multi-shot storyboarding, and motion-transfer (Kling-led). Use wh
• kling-aiWrite and improve prompts for Kling AI video generation, and pick the right Kling model for the job. Covers im
• kling-prompter生成符合 Kling 3.0（可灵 3.0，快手）规则的视频提示词。三种写法自适应：4 部分基础公式（短视频）/ 5 层进阶公式（剧情+音频）/ 图生视频专用（只描述运动）。Kling 是 2026 年中文理解最强、原生
• kling-studioFull-featured Kling 3.0 Omni video generation skill. Covers text-to-video, image-to-video, video editing (base
• klo-mcpMCP server for klo, the native Mac video editor you talk to. Gives Claude Code, Codex, Cursor, or any MCP clie
• klo-mobility-quote-mcpRoute options, fare estimates, ETA, and ride deeplinks via the KLO Mobility A2A agent.
• klypix-mcpActive state management for multi-agent coding: a shared, versioned project brain over MCP.
• kma-mcpKorean KMA forecasts: village, ultra-short, observations.
• kmpKotlin Multiplatform fundamentals - use for project setup, expect/actual patterns, source sets, and platform-s
• kmshihab7878-ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "
• kmshihab7878-algorithmic-artCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this wh
• kmshihab7878-auditScore the AI OS out of 100 across the Four Cs (Context, Connections, Capabilities, Cadence). Read-only by defa
• kmshihab7878-brand-guidelinesWhen the user wants to apply, document, or enforce brand guidelines for any product or company. Also use when
• kmshihab7878-claude-apiBuild apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`c
• kmshihab7878-councilHigh-stakes decision-making system with 5 advisors, anonymous peer review, and chairman synthesis. Activates o
• kmshihab7878-developerStory implementation and code development specialist
• kmshihab7878-doc-coauthoringGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documen
• kmshihab7878-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• kmshihab7878-interface-designThis skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for
• knack-installerInstall Knack on the user's machine. Load this skill when the user asks to install Knack, set up Knack, get st
• knack-interviewConduct the Knack 6-phase interview with a user to author a new skill. Load this skill when the user wants to
• knbnAlias for the kanban skill. Use when the user invokes or refers to Kanban as "knbn".
• kndl-memoryUse this skill whenever you persist a fact to a memory filesystem, read facts back, or answer a question that
• knmi-mcpKNMI open data: datasets, versions, files, downloads.
• knock-knockApply portable agent-to-human notification discipline: notify only from authoritative task state, suppress unk
• knock-webhooksReceive and verify Knock outbound webhooks. Use when setting up Knock webhook handlers, debugging x-knock-sign
• knosOne local memory every coding agent on this machine shares, with claims so they don't collide.
• know-if-its-workingMeasure GTM with the metrics that matter (net developer retention, DREAM funnel) instead of vanity numbers. Us
• know-your-customerGuide customer onboarding identification, due diligence, and profile maintenance under FINRA Rule 2090, the CI
• knowbe4Every KnowBe4 KMSAT reporting feature, plus a local SQLite store for the questions the console cannot answer.
• knowbe4-api-patternsKnowBe4 REST API fundamentals: Bearer token authentication, multi-region base URLs (US, EU, CA, UK, DE), pagin
• knowbe4-phishingKnowBe4 phishing simulations: campaign creation and lifecycle, security test management, recipient interaction
• knowing-what-you-know-nowDecide whether something already built and working is worth rebuilding the elegant way, knowing everything you
• knowledgeDisplay knowledge base status and recent learnings
• knowledge-agentDistill accumulated observations for a code area into a focused domain knowledge brief
• knowledge-auditReview and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate
• knowledge-baseProject-specific prompt optimization knowledge management. Use when storing or retrieving learned patterns fro
• knowledge-base-aiCreate a knowledge base ai with structured process, quality checks, and system integration
• knowledge-base-article-writingWrite clear, searchable help center articles and FAQ entries based on support data, product documentation, and
• knowledge-base-builderStructures internal knowledge bases with categories, article templates, and maintenance procedures for organiz
• knowledge-base-deskauthor and govern help center and internal knowledge base articles captured from resolved contacts, scoped to
• knowledge-base-from-vaultTurn a folder of Markdown notes (Obsidian vault, Notion export, plain repo docs) into a navigable static HTML
• knowledge-base-managementObsidian 知识库全生命周期管理：三层架构、素材入库(ABC分级)、健康检查、GBrain/GraphRAG/LLM Wiki 三件套集成、目录整理
• knowledge-build从开发文档构建或更新测试知识库（L0 架构索引 / L1 模块功能 / L2 需求变更），以灰盒测试人员视角提取可测试契约
• knowledge-captureTransform conversations and discussions into structured Notion documentation
• knowledge-cardTurns one course lesson, tutorial, documentation page, article, workshop, video, or transcript into a compact,
• knowledge-catalog-discoveryUse these skills when you need to discover and explore data assets in the Knowledge Catalog. It allows you to
• knowledge-catalog-discovery-agentAnalyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank th
• knowledge-compiler将知识材料编译为结构化 Wiki。AI 即编译器，Markdown-in Markdown-out，覆盖度追踪，增量编译。
• knowledge-consolidationBuild frameworks from scattered insights across all braindumps and notes
• knowledge-copilotUse when you need the Codex Copilot equivalent of Claude Copilot /knowledge-copilot: create, link, inspect, or
• knowledge-curationContext priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and
• knowledge-curatorUse when repeated lessons, pitfalls, or decisions should move from temporary session context into durable proj
• knowledge-distillationCompress large language models using knowledge distillation from teacher to student models. Use when deploying
• knowledge-doc-writingTurn self-study, research, conversation transcripts, or source material into a durable technical document with
• knowledge-graphThree-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Man
• knowledge-graph-creationBuild structured knowledge graphs from unstructured text by extracting entities, mapping relationships, genera
• knowledge-graph-managementCapture, validate, query, and sync architectural patterns and design decisions in the knowledge graph
• knowledge-graph-rdbmsA label property graph on SQLite/Postgres with multi-ontology routing and a gated MCP server.
• knowledge-managementCreate a knowledge management with structured process, quality checks, and system integration
• knowledge-opsUse when an Obsidian knowledge system needs classification, deduplication, retrieval, synchronization, debt qu
• knowledge-panel-entity-seoRun the plumbing that earns a Google Knowledge Panel — entity-clarity audit, Person schema JSON-LD with sameAs
• knowledge-primingLoad project-specific context -- tech stack, architecture overview, directory layout, trusted sources, and con
• knowledge-priming-refinerFacilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledg
• knowledge-railPersistent, evidence-backed project knowledge and task context for coding agents.
• knowledge-retrievalSemantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG)
• knowledge-reviewAudit the authority, freshness, and uncertainty of the sources and claims behind a decision, and reconcile con
• knowledge-searchSearch the knowledge base in [Notion](https://composio.dev/toolkits/notion) for answers to customer questions.
• knowledge-stackUse this skill whenever working inside any of Nick's repos (under ~/Developer/) or whenever a conversation tou
• knowledge-synthesisExtract insights from multi-agent interactions, identify patterns, and build collective intelligence through c
• knowledge-teacher系统性讲授知识点。当用户询问某个概念的定义、原理、推导时触发。 即使用户没有明确说"讲解"，只要意图是理解某个概念的本质和运作原理，也应使用此 skill。
• knowledge-wikiManage the personal knowledge wiki. Use when the user shares articles, documents, or asks to organize knowledg
• knowlet-code-reviewerAutomated code review that checks code quality, Clean Architecture compliance, DDD patterns, coding standards,
• knowlet-mutation-testing在單元測試通過後觸發。透過引入人工錯誤（Mutants）來「測試你的測試」，確保測試案例具有足夠的錯誤偵測能力，建立對驗證機制的信任（Trust the Verification）。
• knowlet-template-skillReplace with description of the skill and when Claude should use it.
• knowmindAI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.
• known-errorsUse when a OpenChatCut tool call fails or returns an unexpected shape.
• knownfixVerified fixes, professional reviews, and evidence-led apparel over MCP.
• knowsuchagency/mcp2cliTurn any MCP, OpenAPI, or GraphQL server into a CLI — at runtime, with zero codegen
• knowuswell-mcpHost the KnowUsWell friendship quiz: 16 behaviour questions, four-letter roles, 16 pair types.
• knoxhub-blogTransform any research material into SEO+GEO-optimized blog posts for Knox Hub. Takes any input (URL, article
• knuths-optimization-principleApply Knuth's Optimization Principle when someone wants to optimize code before establishing it's a bottleneck
• koan-data-modelingAggregate boundaries, relationships, lifecycle hooks, value objects
• kobotoolbox-mcp-serverMCP server for KoboToolbox: list forms, fetch submissions, and export field data.
• koda-verifyVerification and memory layer for coding-agent workflows.
• kodiak-mcpMCP server for Kodiak — verifiable fact-checking. Verify a factual claim and get a verdict, calibrated confide
• kogcat-mcpLocal-first judgment layer: counter-examples & blind spots from your own knowledge base.
• kogiqa-mcpThis web browser has been designed to help your agent debug and develop complex web applications.
• kojiru-agentkitKojiru Recourse Layer — agent credit primitives (ACS, stake, draw, anchor) live on Base mainnet