В каталоге 183 730 навыков в 14 категориях.
Diagnoses .NET Framework CLR activation issues using CLR activation logs (CLRLoad logs) produced by mscoree.dll. Use whe...
Data structures and algorithms reference based on CLRS. Use this skill when implementing, discussing, or choosing data s...
Use when a clue is detected too rarely or too often, when adding or editing a clue (holder, topic, fact, anchors, calibr...
Reference system prompt and tool schemas for Cluely. Use when imitating, comparing, or analyzing Cluely's prompting styl...
Skill for the Cluster_98 area of Securacy. 3 symbols across 2 files.
Master Kubernetes cluster administration, from initial setup through production management. Learn cluster installation,...
Complete Platform Agent Swarm — A coordinated multi-agent system for Kubernetes and OpenShift platform operations. Incl...
Full cluster state audit. Use when asked for cluster status, health check, or infrastructure audit. Produces comprehensi...
Automated content similarity and grouping analysis. Groups related documents by topic, purpose, or content similarity.
· Check Kubernetes cluster health with read-only diagnostics. Triggers: 'cluster health', 'health check', 'cluster statu...
Check Kubernetes cluster health and fix common issues. Use when: (1) User asks to check the cluster, check health, or "w...
This skill should be used when the user asks to "inspection", "inspect cluster", "health check", "patrol", "cluster revi...
Detect which HPC cluster you are on and load the correct job submission instructions. Use when the user asks to submit,...
This skill should be used when the user asks to "list clusters", "show clusters", "cluster overview", "list projects", "...
Monitor and manage Proxmox cluster nodes, resources, and infrastructure health. Track node status, cluster quorum, and r...
Layer 6 of the keyword research pipeline. Organizes the vetted keyword queue into money clusters (from clusters.md), pic...
Cluster planning guide: hardware profiles, deployment tiers, and roadmaps. Use cluster-advisor MCP to analyze survey dat...
Detect skills that may belong to a different cluster based on description, trigger, and script patterns. Trigger: /clust...
Show GKE cluster health dashboard — nodes, agents, app pods, ingress, certs, analytics. Use when user asks about cluster...
Plan, run and roll back a Kubernetes minor-version upgrade, EKS first. Finds removed APIs in Git, rendered Helm charts a...
Dimensionality reduction and clustering for single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for running PC...
This skill enables Claude to execute clustering algorithms on datasets. It is used when the user requests to perform clu...
Cluster data using K-Means, DBSCAN, hierarchical clustering. Use for customer segmentation, pattern discovery, or data g...
Finds differentially expressed genes (markers) for clusters of T/B cells using Seurat's FindMarkers function. Performs s...
Finds marker genes for clusters of ALL cells before T/B cell selection. This process identifies differentially expressed...
Use this skill to run deterministic local custom enrichment with Bioconductor clusterProfiler and user-supplied TERM2GEN...
Multi-cluster reference data for troubleshooting across EMEA, APAC, NAM. Contains kubectl contexts, ArgoCD cluster names...
CLUTCH v3 — Claude Layered Unified Team Coordination Hub. Resilient multi-phase orchestration with fail-fast guards, con...
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, a...
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture transforms scattered ses...
End-to-end ad conversion tracking: Meta Pixel+CAPI, TikTok Events API, Google Ads Enhanced Conversions, GTM, attribution...
用户明确说“规格已确认，开始实现”或要求按已审批 CM specs 开发时使用。新任务默认由 JS workflow 驱动 N1-N8，完成开发、独立审查、QA 与文档同步；模糊点子、未审规格和单独一句“继续”不能触发编码批准。
Comprehensive publishing automation skill bridging AI agents (OpenClaw, Manus, Claude) to the Content Factory Router. Us...
Easy-to-use conversational CLI (Claude Code style) for non-technical users to spawn parallel AI tasks supervised by a vi...
后端 API 工程师 Skill，执行服务端 API 层开发（路由、业务逻辑、鉴权中间件、缓存、队列），自动适配语言和框架
Fallback local Playwright daemon for real-browser visual QA / screenshots / smoke. Use ONLY when the host platform has n...
用户要求推敲已有方案、三轮对抗分析、挑战假设，或用 grill me 追问计划与取舍时使用。给出有依据的建议和必要问题；不替代点子转 PRD、正式独立审查、测试或实现，不自动执行建议。
用户说“检查工作流是否安装正确”“为什么找不到 cm 命令”时使用。默认查询 npm 稳定版，有新版自动升级已管理的 CM 安装，再检查插件、核心 Skills、兼容包装与模板引用；不测试或修改业务代码。
Code hygiene gate — detect and eliminate dead code, duplicates, naming mess, and code smells. TRIZ-powered. Run after fe...
Full review lifecycle — request reviews, handle feedback with technical rigor, and complete branch integration. Use when...
Unified code intelligence — routes to Skeleton Index, CodeGraph, Architecture Diagram, or Smart Context Builder based on...
Working memory protocol — routes to session protocol, memory audit, MCP/URI integration, or storage details based on the...
智能合约工程师 Skill，执行合约开发、测试、部署，自动适配 EVM/Solana/Move 等链和开发框架
[Deprecated] both visualize project state. Use `cm-status` instead.
数据库工程师 Skill，执行数据模型设计、migration、查询优化，自动适配 ORM 和数据库类型
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Optional power-up — detects oversized codebases/docs and suggests tobi/qmd for local semantic search. Bridges cm-continu...
Ultimate Design System Intelligence. Manage, extract, replicate, and improve UI design systems. Extracts design tokens...
发布/运维工程师 Skill，执行 staging 部署、冒烟验证、发布记录与生产发布待决清单编制，自动适配部署栈；生产发布与基础设施变更强制人工确认
文档同步 Skill，开发完成后自动更新 README、.claude/ 配置、specs CHANGELOG，保持文档与代码一致
Knowledge systematization engine — analyze codebases, generate Personas, JTBD, Process Flows, technical docs, SOP user g...
A template demonstrating the universal format compatible with Antigravity, Claude, Cursor, and OpenClaw.
Use when executing approved implementation plans. Routes to 1 of 6 execution modes (batch/subagent/parallel/RARV/TRIZ/pa...
金融专家 Skill，覆盖 Web3 与证券/资产/交易领域的正确性审核、营销合规红线识别、合规问题清单生成、业务验收协同；把关型角色，只举旗不定性
用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归；尚未确认的问题先用 cm-test，新功能和架构重设计转交 cm-prd。
前端工程师 Skill，执行前端开发任务，自动适配项目技术栈（React/Vue/Svelte/Next.js 等），支持 Figma/Stitch 设计稿还原
Google App Script form-to-sheet integration with auto-retry, toast notifications, and Zalo/contact fallback. Reusable ac...
Bottom-sheet and popup growth system: booking CTAs, calendars, lead capture, surveys, re-engagement, with CRO tracking h...
Complete guide to vibe coding with CodyMaster — from idea to deploy. Read this first if you are new.
用户说“我有个点子”“帮我梳理产品”或需要先聊清目标时使用。通过逐题访谈整理为可交给 cm-prd 的 PRD；已有明确需求文档时改用 cm-prd，不写代码、不拆开发任务。
Verify and lock project identity before ANY git push, Cloudflare deploy, or Supabase operation. Essential when working w...
用户说“第一次接管这个项目”“分析仓库并生成项目规则”时使用。分析已有代码并生成 Codex AGENTS.md 与 CM/Claude 兼容规则；仅适用于非空存量项目，不创建脚手架、不承接普通代码修改。
Customer discovery framework using Jobs-To-Be-Done theory — uncover the functional, social, and emotional jobs customers...
微信小程序开发工程师 Skill，执行小程序开发任务，自动适配项目技术栈（原生小程序/Taro/uni-app 等），支持 Figma/Stitch 设计稿还原与云开发
Sync high-value dev knowledge (skills, decisions, lessons) into Google NotebookLM for cloud recall, podcasts, and flashc...
用户要查看或切换 CM 卡住/结束/等待提醒推到哪里（Bark 或 pushplus）、检查密钥是否填好、发一条测试推送或关闭提醒时使用。同一时刻只开一个渠道；只管理提醒设置，不索要、不接收、不显示任何密钥。
You MUST use this before any creative work or multi-step task. Explores intent and writes execution-ready plans before c...
用户说“把需求拆成可开发规格”“变更现有功能需求”或要求整理方案、任务和验收时使用。支持新项目、存量二开与需求变更；完成后停在人审规格，不直接编码。
产品经理 Skill，负责需求分析、用户故事与验收标准编写、歧义清单生成、变更影响分析、业务验收走查；把关型角色，不做技术设计与技术测试
QA 工程师 Skill，执行功能测试、E2E 测试、可视化回归、验收标准核验，自动适配项目测试框架
Use before any deployment or completion claim. Enforces test gates, evidence-based verification, and frontend safety che...
Strategic codebase re-direction when requirements change, architecture doesn't fit, or tech debt blocks progress. TRIZ-p...
Turn any website into an audio-enabled experience. Covers TTS reading mode (SpeechSynthesis API), pre-recorded MP3 audio...
用户明确要求“只整理结构，不改变行为”时使用。执行边界分流、行为判官、分批重构和独立审查；缺陷修复转交 cm-fix，新增或变化的业务行为转交 cm-prd。
Use at end of sprint to append operational learnings as structured JSONL to the project retro log.
用户要查看或切换 CM 自动派发偏好、单/双 AI 声明、谁写谁审，或修改用户级运行时默认时使用。只管理运行时声明，不安装工具、不测试配额、不接管正在运行的任务。
Use when setting up deployment infrastructure or enforcing a gated release path. Routes to deploy gates, setup, or rollb...
Safe i18n: multi-pass batching, parallel-per-language dispatch, 8 audit gates, HTML integrity. Use for translating or ma...
用户运行 cm-security，或要求代码安全扫描、漏洞检查、密钥泄露排查、依赖漏洞检查时使用。默认检查当前分支相对主分支及已跟踪未提交修改，结合业务地图复核；--all 检查全部已跟踪文件。只报告问题，不自动修复、安装、升级或发布。安装...
Skill Chain Engine — compose skills into automated pipelines. One task triggers multi-skill workflows with progress trac...
Progressive Disclosure skill index — efficient skill loading in 3 layers. Layer 1 (index, ~100 tokens) always loaded. La...
Use to run the full sprint pipeline: brainstorm → plan → design → tdd → build → review → qa → security → ship → monitor...
Start the CM Workflow to execute your objective from idea to production code.
View a quick progress summary of current tasks.
Use when implementing any feature or bugfix. Routes to the core Red-Green-Refactor loop, test quality guidance, rational...
Use when running ANY terminal command - enforces clear progress logging, output reading, and error-stop behavior so term...
用户直接运行 cm-test、要求分析当前分支相对主分支的业务影响，或说“测试已有功能”“根据代码生成用例”“用浏览器走查”时使用。无参数分析已提交差异、单测覆盖率与回归重点；明确说“补齐单测”时连续补测并重跑、审查。显式目标保留原模式，不...
UI 还原工程师 Skill，把已确认的设计基准像素级还原为生产代码（token 先行、原子顺序、按交付形态量化验收：Web 用 BackstopJS、App 用 Maestro+模拟器截图）；有基准才出场，不做业务逻辑
Ultimate UI/UX design intelligence: an Anti-Slop layer that kills AI tells (em-dash, AI purple glow, generic names, temp...
Configure Campaign Manager 360 Floodlight activities and upload offline conversions. Use when the user asks about Floodl...
Build the Campaign Manager 360 object hierarchy and traffic a campaign end to end so it serves, tracks, and clicks throu...
Measure and report viewability and ad verification in Campaign Manager 360 using Active View against the MRC standard, a...
Create comparative market analysis reports. TRIGGERS - Use when user needs help with cma-report related tasks.
CMake build system skill for C/C++ projects. Use when writing or refactoring CMakeLists.txt, configuring out-of-source b...
Use when writing CMakeLists.txt, out-of-source builds, target_link_libraries, target properties, find_package/FetchConte...
查询招商银行外汇牌价（中间价）
Use when integrating, porting, configuring, or debugging CmBacktrace on Cortex-M faults, stack traces, firmware metadata...
Cheat sheet for Windows Command Prompt commands.
Use this skill when creating or modifying command entrypoints under cmd/.
Create ServiceNow CIs and cmdb_rel_ci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align...