Parcourir le registre

Toutes les entrées, par ordre alphabétique — 81 198 au total. Page 65 sur 325.

• claims-chronology-builderUse when building a source-cited claim chronology from notices, correspondence, adjuster notes, pleadings, dem
• claims-extractorUse when a review workspace has manuscript text and needs a traceable claim ledger. **Trigger**: claims extrac
• claims-guideSchadenfall-Guide und Entscheidungslogik. Leitet Schritt fuer Schritt durch jeden Schadenfall (Unfall, Krankhe
• claims-mcpA claims memory for agents: assert beliefs, let them decay, surface contradictions.
• claims-verifierDecomposes a claim into checkable propositions, traces each through the citation chain to its primary source,
• claims-workflowAnalyze insurance claims workflow systems for intake optimization, adjudication rules, subrogation, litigation
• clap-reviewReviews CLAP plugin implementations for spec compliance, thread safety, and correctness. Use when the user ask
• claracars-mcpUsed & imported cars in Portugal: search stock, ISV/IUC tax calc, resale value, contact.
• clarifyPause before implementing — ask clarifying questions about the user's request after reading relevant code and
• clarify-goalAsk the user targeted clarifying questions about their research goal before the pipeline runs. Use when the re
• clarify-intentPin down what the user is actually building on Sui before any code. Use when the user wants to build, create,
• clarify-metamediumThis skill should be used when the user is building, planning, or strategizing and the key question is whether
• clarify-question-loopUse when a meta-agent request is too ambiguous to safely generate, package, publish, or adapt without one to f
• clarify-the-requestDecide whether a request is clear enough to act on, and if not, ask only the minimum necessary clarification q
• clarifying-requirementsUse when starting a new feature, component, or project whose requirements are underspecified or ambiguous — be
• claris-filemaker-proREFERENCE skill — FileMaker Pro script steps, calculation functions, and field types. Use for: syntax lookups,
• clarityWork-item review lens for evaluating unambiguous communication —
• clarity-editingEdit written text for clarity and conciseness — active voice, hedge and weasel-word removal, jargon strip, sen
• clarity-guideA professional psychological counseling companion skill that guides users through structured self-exploration
• clash-cultures-investment-speculation-bogleApply John Bogle stewardship capitalism logic to separate investing from
• clash-doctorClash Verge 诊断与配置管理。网络诊断、配置 AI 工具路由规则（Claude/Codex/Cursor/Warp）、查看/克隆订阅配置、切换配置文件。当用户遇到网络问题、要配置代理规则、切换订阅、查看 Cla
• clash-routes查看指定进程的代理线路。通过 Mihomo API 查询当前活跃连接，显示进程匹配的规则和代理链路。用于确认某个进程（如 claude、chrome）走的是哪条订阅线路
• class-brain교사가 Claude·Codex를 '우리 반 제2의 뇌'로 쓰도록, 반 맥락 파일(CLAUDE.md/AGENTS.md)과 자료 축적·불러오기 습관을 잡아준다. "우리 반 AI 세팅 도와줘"처럼 사용.
• class-diagramGenerates a Mermaid class diagram showing types, inheritance, and composition. Use when visualizing class hier
• classdojo-mcpUnofficial local-first MCP for ClassDojo roster imports and classroom skill synchronization.
• classic-asp-to-aspnet-mvcConventions and a working playbook for porting Classic ASP or Web Forms sites to ASP.NET Core MVC on net10.0:
• classic-to-default-syncInspect a given commit's web/classic changes and sync all features/fixes to web/default. Use when the user pro
• classical-poetry-peace-themeCompose classical Chinese poetry on peace themes using authentic imagery, perspective shifts, and the voice of
• classified-skill-listing-debug-telemetryEmit low-cost debug telemetry for skill-listing batches that records batch size, initial-vs-dynamic mode, and
• classify-changeClassify a proposed code change as Leaf Node or Core Code to decide how much AI usage and review rigor is appr
• classroom50Route Classroom50 (foundation50) instructor workflows through the course_hoanganhduc agent entrypoint: readine
• claud3D3.js data visualization skill based on Edward Tufte principles. Selects the right chart type from 80+ options
• claudeAnthropic Claude AI models for analysis and coding. Use for AI assistants.
• claude-3p-parityDiagnose and repair Claude Desktop Mac third-party inference / 3p / DeepSeek-style Claude Code setups for best
• claude-5-best-practiceRoute Claude 5 tiers (Haiku/Sonnet 5/Opus 5/Fable 5), effort, and subagents for cost-effective accepted result
• claude-advancedAdvanced for Claude: advanced patterns and techniques
• claude-agent-sdkThis skill provides comprehensive knowledge for working with the Anthropic Claude Agent SDK. It should be used
• claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, c
• claude-api-system-prompts-layoutsGuidelines and instructions for Claude API system prompts layouts
• claude-api-temperature-parameter-configsGuidelines and instructions for Claude API temperature parameter configs
• claude-authenticityDetect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 wei
• claude-automation-recommenderAnalyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use
• claude-basicsBasics for Claude: fundamentals and core concepts
• claude-batchRun large-scale batch processing with Claude API for bulk text analysis, classification, and generation
• claude-bionifyConfigure and control the claude-bionify bionic reading plugin. Use when the user asks about bionic reading se
• claude-blog-brainScaffold and operate Claude Blog Brain, a source-cited Obsidian brain for blog content creation, optimization,
• claude-chat-markdown-writerAlways trigger this skill when the user says "write a markdown", "write a document", "create a markdown", "gen
• claude-coachPersonal coach that teaches users to become Claude power users. Use this skill the FIRST time a user asks to "
• claude-codeUsing Claude Code CLI for autonomous development
• claude-code-account-risk反封号.skill — Claude Code 专用账号风险体检。用户说「测试一下我目前账号被封的可能性」「检查 Claude Code 封号风险」「账号被封帮我申诉」「检查 api.anthropic.com 路由」「
• claude-code-analyzerAnalyzes Claude Code usage patterns and provides comprehensive recommendations. Runs usage analysis, discovers
• claude-code-auditForensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not ma
• claude-code-bash-patternsComprehensive knowledge for using the Bash tool in Claude Code effectively. This skill should be used when orc
• claude-code-bridgeDurable local-first MCP relay for independent coding agents.
• claude-code-customizationCustomizing Claude Code with CLAUDE.md
• claude-code-debugTroubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loa
• claude-code-expert-handoff세션 종료·컨텍스트 압축 직전에 진행 상황을 specs/HANDOFF.md로 인계한다. 긴 작업의 연속성이 필요할 때 사용.
• claude-code-eyesLook at real hardware, screens, panels, and wiring on a desk or workbench through a camera, so Claude can SEE
• claude-code-guideUse when configuring Claude Code hooks, plugins, skills, settings, or managed configuration. Triggers on Sessi
• claude-code-headlessRun Claude Code programmatically without interactive UI. Triggers on: headless, CLI automation, --print, outpu
• claude-code-hooksClaude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script,
• claude-code-litellm-gatewayConfigure Claude Code to use an existing LiteLLM gateway safely, including both a low-risk wrapper path and an
• claude-code-masteryThe definitive Claude Code setup, configuration, and mastery skill. Use when setting up Claude Code for a new
• claude-code-meet-upSKILL.md for jira-snowflake-github workflow
• claude-code-mrgoonieGuidance on Claude Code, Anthropic's terminal-based agentic coding tool. Use when asked about Claude Code feat
• claude-code-plugin-referenceExplain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins.
• claude-code-projectUse this skill when the user wants to update their project's CLAUDE.md or AGENTS.md, verify their Claude Code
• claude-code-proxy-patternsClaude Code OAuth proxy patterns and anti-patterns for multi-provider model routing.
• claude-code-qaThe complete QA skill for Claude Code — turn Claude into an expert QA engineer that picks the right test type,
• claude-code-reverse对用户拥有或明确获授权的本机可执行文件、应用二进制和版本产物做只读静态逆向，包括 Claude Code 及其他 CLI、Mach-O、ELF、PE、Wasm 或打包应用。仅在用户明确要求“逆向、扒实现、查二进制字符串/
• claude-code-skillDevelopment conventions and architecture guide for the Claude Code CLI repository.
• claude-code-skillforgeGenerates highly optimized Agent Skills for both native Claude Code and the Antigravity system, according to o
• claude-code-smokeUse when asked to run the Claude Code smoke evaluation.
• claude-code-tasksReference for Claude Code's 6 Task Management tools — TaskCreate, TaskGet, TaskList, TaskUpdate (structured tr
• claude-code-teamsReference for Claude Code Agent Teams — lifecycle, messaging, spawning, orchestration, and hooks
• claude-code-templatesBoilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook
• claude-code-ultimate-guide-mcpSearch the Claude Code Ultimate Guide and machine-readable references from any MCP client.
• claude-code-usage[AUTO-INVOKE] MUST be invoked at the START of each new coding session. Covers context management, task strateg
• claude-code-usage-mcpMCP server exposing Claude Code token usage, estimated cost, and plan-limit data from local logs and Anthropic
• claude-code-workflowsAdvanced Claude Code workflows and automation
• claude-codex-bridgeBridge Codex and Claude for bidirectional execution review. Use when Codex should audit Claude handoffs, send
• claude-command-converterConvert Claude Code commands (.claude/commands/*.md) to standard Agent Skills (skills/*/SKILL.md). Use when mi
• claude-compaction-restoreUse when a Claude Code session has just compacted, is about to compact, reached context limit, resumed after /
• claude-configHow agents, skills, and commands work in Claude Code projects.
• claude-config-auditユーザーの ~/.claude グローバル設定を機械的に監査する（死 symlink・disabled なのにキャッシュ残存の plugin・MCP 重複登録・orphan commands を検出）。「設定を点検」「c
• claude-consultConsult Claude specialist agents during implementation for codebase understanding, pattern checking, security
• claude-contextSemantic code search via MCP. Indexes entire codebase, finds relevant code by natural language query. 40% toke
• claude-cost-tracker6 Claude Code skills for individual investors: options flow scanner (lottery-call filter), stop-loss monitor,
• claude-delegateDelegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then
• claude-designDesign one-off HTML artifacts (landing, deck, prototype).
• claude-design-card将任意文本、网页或 URL 生成符合 Claude/Anthropic 设计语言的 HTML 信息卡片，通过 Playwright 截图为 PNG。 支持 14 种格式：平台封面（公众号、视频号、B站、抖音）、图文内容卡
• claude-design-criticAudit a website or UI and de-AI it — find the patterns that make it look template-generated (in both design an
• claude-design-idea-to-readyTake a UI from a one-line idea to on-brand, shippable design with Claude, in the correct order — brand foundat
• claude-design-system-architectGenerate a complete, premium design system from a brand brief or an existing site — color tokens, type scale,
• claude-desktop-bridgeShared local knowledge vault MCP server for Claude Desktop (Chat + Code)
• claude-devfleetOrchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated
• claude-docsSearch and read locally-stored Claude documentation covering Claude Code CLI, Claude API (Messages, tool use,
• claude-docs-changelogGenerate a self-contained HTML changelog report showing recent documentation changes with interactive course g
• claude-docs-courseGenerate an interactive, self-contained HTML course on any Claude documentation topic. Use this skill when the
• claude-docs-validateCheck the health and freshness of locally-stored Claude documentation. Use this skill when the user asks about
• claude-env-setupУстановка и обновление рабочего окружения агента: скилы, правила и команды этого набора плюс связанные инструм
• claude-faf-mcpPersistent project context for Claude. IANA-registered .faf format.
• claude-for-safariControl the user's real Safari browser on macOS through AppleScript, page JavaScript, screenshots, and careful
• claude-git-branchingExpert Git workflow management for Claude Code sessions with branch naming conventions, push retry logic, conf
• claude-gladiatorContinuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with hist
• claude-handoffSession handoff for Claude Code: list sessions and build handoff docs another agent continues from.
• claude-handoffPassa a conversa atual para um background agent novo, que retoma o trabalho imediatamente.
• claude-headlessBuild custom UIs on top of Claude Code's headless mode. Covers spawning, NDJSON protocol, permission hooks, an
• claude-healthClaude Code config health check + plugin sync. Use when: auditing .claude/ structure, checking naming, verifyi
• claude-helperWraps internal tooling shortcuts for the team. Use when the user asks for the internal helper or mentions the
• claude-historianAutomatic history search — checks past sessions before web research, planning, and debugging, siblings deepen
• claude-history-ingestIngest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine the
• claude-html用 Anthropic / Claude 的简约视觉风格制作 HTML —— 象牙暖底 + 陶土橙（clay #D97757）克制点缀、无衬线主导 UI、衬线只用于大标题与长文、克制土色状态色、细边框低阴影、大量留白、零
• claude-humanizerMake Claude write and respond exactly like a real human — with personality, imperfection, opinions, rhythm, an
• claude-intercomTwo-way communication bridge between Claude Code sessions using the Channels API
• claude-jobsFind job openings at tech companies. Use when user asks about jobs, careers, openings, positions, roles, or sa
• claude-kvmMCP server — control remote desktops via VNC (MacOS)
• claude-landing-composerCompose a premium, animated landing page section by section in Next.js + Tailwind + Motion (Framer Motion) — b
• claude-managed-agentsBuild applications with the Claude Managed Agents API — Anthropic's managed infrastructure for running Claude
• claude-managed-agents-webhooksReceive and verify Anthropic Claude Managed Agents (CMA) webhooks. Use when setting up Claude Managed Agents w
• claude-mcp-bridgeMCP server that wraps Claude Code CLI for query, web search, structured output, and health checks
• claude-mdGénère ou met à jour le CLAUDE.md racine — analyse du codebase (stack, archi, commandes, conventions) + princi
• claude-md-and-skill-md-magicA curated collection of `CLAUDE.md` and `SKILL.md` files for AI-assisted development. Discover reusable prompt
• claude-md-bootstrapUse when the user wants to create or bootstrap a project-local CLAUDE.md - the auto-loading project context fi
• claude-md-dependency-rescanRe-detect this project's tech stack from package.json / requirements.txt / pyproject.toml / go.mod / Cargo.tom
• claude-md-directoryBrier-audited directory of 1000+ CLAUDE.md and skills/*.md files. Every entry has a public "does this skill ac
• claude-md-drift-auditAudit every CLAUDE.md in this project for drift against the last week of git history. Flags sections that refe
• claude-md-enhancerAnalyzes, generates, and enhances CLAUDE.md files for any project type using best practices, modular architect
• claude-md-forgeGenerate or optimize a CLAUDE.md and .claude/ infrastructure for a repository. Use when user says "create CLAU
• claude-md-generatorUse when the user asks to generate or update a project's CLAUDE or AGENTS context file from a codebase scan. W
• claude-md-improverAudit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix
• claude-md-link-checkVerify every @path chain import and every markdown link inside every CLAUDE.md in this project resolves to an
• claude-md-optimizerOptimize oversized CLAUDE.md files using progressive disclosure. Analyzes content tiers, detects encryption co
• claude-md-reviewAudit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files,
• claude-md-starterGenerates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json,
• claude-md-updaterScans the session for lessons and workflows, then proposes scoped CLAUDE.md edits. Use for save this lesson or
• claude-md-writerUse when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content or
• claude-memory-kitPersistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /
• claude-monitorClaude Code 原生悬浮窗通知 - 在 macOS 状态栏显示 Claude 的实时工作状态（思考中、执行工具、等待输入、任务完成）。当用户需要监控 Claude Code 运行状态、想知道 Claude 在做什
• claude-nameA skill whose name contains the reserved word 'claude'.
• claude-node-typescript-runtime-package-starterBuild your plugin once and easily export/install it to any AI agent, like Claude, Codex, Gemini or Cursor, wit
• claude-node-typescript-starterBuild your plugin once and easily export/install it to any AI agent, like Claude, Codex, Gemini or Cursor, wit
• claude-only-skillDemonstrates Claude Code-only skill features that do NOT port to Codex or Cursor. Use this fixture to see skil
• claude-opus-4-5-migration將提示詞和程式碼從 Claude Sonnet 4.0、Sonnet 4.5 或 Opus 4.1 遷移至 Opus 4.5。當使用者想要更新其程式碼庫、提示詞或 API 呼叫以使用 Opus 4.5 時使用。處理模型字
• claude-oracleUse when user asks "what exists for X?", before implementing custom MCP servers or plugins from scratch, or wh
• claude-oratorPrompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
• claude-paper-studyUse this skill when the user wants to read, study, analyze, or deeply understand a research paper (PDF).
• claude-paper-summaryUse this for a quick summary of a research paper's core ideas and key points. Use when you want to quickly und
• claude-paper-webuiStart the Claude Paper web viewer to browse and study papers
• claude-pentest-skillsStructured web application penetration testing with OWASP methodology, curated payload references, 6-gate vali
• claude-permissions-auditReview and reorganize Claude Code permission settings across all config files (global settings.json, project s
• claude-pm-skillsProduction-grade skills for product thinking, discovery, prioritization, and launch decisions. Covers the full
• claude-praetorianContext preservation with cross-session memory — hooks prompt compaction at high-impact moments, siblings enri
• claude-printRun a non-interactive Claude Code print-mode call from Codex. Use when the user asks to \"claude print\", \"as
• claude-promptsReusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
• claude-python-starterBuild your plugin once and easily export/install it to any AI agent, like Claude, Codex, Gemini or Cursor, wit
• claude-real-videoLet any LLM watch a video locally — and search everything it has ever watched.
• claude-reflectSelf-learning system that captures corrections during sessions and reminds users to run /reflect to update CLA
• claude-replaySession checkpoint & recovery for Claude Code: resume, search, tag, and export recorded sessions.
• claude-rescueUse when running under Codex CLI and stuck, wanting a second implementation or diagnosis pass, or handing a su
• claude-research-skillMulti-agent research orchestrator for Claude Code — decomposes any question into parallel workstreams, monitor
• claude-reviewUse the local Claude CLI as a second-opinion reviewer for briefs, plans, architecture, and code, then selectiv
• claude-runnerClaude/Codex CLI execution layer — prompt loading, stream-json parsing, file output extraction, path sanitizat
• claude-scientific-skillsComprehensive collection of 128+ ready-to-use scientific skills for Claude enabling research across biology, c
• claude-sdkBuild autonomous AI agents with the Claude Agent SDK — computer use, tool calling, MCP integration, and produc
• claude-sdk-deploymentDeploying Claude Agent SDK agents to production — wrapping the SDK in FastAPI with SSE streaming, session resu
• claude-sdk-expertBuild autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and produc
• claude-sdk-hooksHooks in the Claude Agent SDK — PreToolUse, PostToolUse, UserPromptSubmit, Stop event types, the HookMatcher s
• claude-sdk-mcp-integrationWiring external MCP servers into a Claude Agent SDK agent — stdio and HTTP transports, dict format, when to us
• claude-sdk-permissionsThe Claude Agent SDK permission model — allowed_tools, disallowed_tools, the six permission_mode values, and t
• claude-sdk-system-promptSystem prompts in the Claude Agent SDK — string vs file vs preset, the claude_code preset and its append field
• claude-sdk-tool-creationBuilding custom tools for Claude Agent SDK agents — the @tool decorator, schema dicts, return shape, error ret
• claude-securityThe Claude Security menu — pick a job: scan the codebase (the whole repository or a scoped part of it), scan c
• claude-security-reviewmy skill.md for security reviews in opus 4.5, enjoy!
• claude-seoSEO toolkit with 24 specialist sub-skills (upstream v2.0) — full site audits, technical SEO, content optimizat
• claude-session-handoffRecover working context from a prior Claude Code session by reading its JSONL conversation log and turning it
• claude-skillUse when work should be delegated to Claude Code CLI, especially headless `claude -p` runs, automation scripts
• claude-skill-orchestration-auditAudit skills for agentic orchestration quality. Checks subagent dispatch patterns, parallelism opportunities,
• claude-skill-prereq-auditScan skills for prerequisite tools, MCP servers, and auth requirements, then check if everything is installed
• claude-skill-routerUse when installing, configuring, troubleshooting, or extending a smart skill router for Claude Code that auto
• claude-skill-rustGuide for Rust development including code style, testing, building, and quality checks using cargo tools. Appl
• claude-skill-security-auditorClaude Code skill for running structured security audits with actionable remediation plans
• claude-skill-spec-auditAudit skill SKILL.md files for compliance with the agentskills.io specification and house conventions. Checks
• claude-skills-business-growth-customer-success-manager-customer-success-managerMonitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring m
• claude-skills-business-growth-sales-engineer-sales-engineerAnalyzes RFP/RFI responses for coverage gaps, builds competitive feature comparison matrices, and plans proof-
• claude-skills-marketing-skill-ad-creative-ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write
• claude-skills-marketing-skill-churn-prevention-churn-preventionReduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequ
• claude-skills-marketing-skill-cold-email-cold-emailWhen the user wants to write, improve, or build a sequence of B2B cold outreach emails to prospects who haven'
• claude-skills-marketing-skill-content-strategy-content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to co
• claude-skills-marketing-skill-copy-editing-copy-editingWhen the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit
• claude-skills-marketing-skill-copywriting-copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pa
• claude-skills-marketing-skill-marketing-ideas-marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use w
• claude-skills-marketing-skill-marketing-psychology-marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also
• claude-skills-marketing-skill-pricing-strategy-pricing-strategyDesign, optimize, and communicate SaaS pricing — tier structure, value metrics, pricing pages, and price incre
• claude-spec-skillA skill demonstrating all Claude Code spec fields.
• claude-system-promptOperational rules, safety instructions, reasoning guidelines, and behavioral patterns from the Claude 3.7 Sonn
• claude-thinking-mode-parameter-setupsGuidelines and instructions for Claude Thinking mode parameter setups
• claude-to-agyOffloads heavy, token-intensive reasoning and search tasks to Antigravity CLI (agy) via MCP. MANDATORY delegat
• claude-to-codexConverts any Claude skill into a Codex-compatible skill. Searches the Claude skill marketplace by name, fetche
• claude-to-imBridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat
• claude-to-kimi当需要把 `.claude`、`.claude-plugin`、`.codex-plugin` 或共享 `.agents` 资源迁移到 Kimi 的 `.agents`、`.kimi-code` 或 `kimi.plug
• claude-to-trae当需要把 Claude Code、Codex、ZCode 等工程化配置迁移为 Trae 标准目录时使用此 Skill。适用于新建迁移、增量适配、结构规范化与迁移诊断。 触发场景： - 需要把 `.claude/`、`.
• claude-to-zcode当需要把 `.claude`、已有 `.zcode`、或 `.claude-plugin/.codex-plugin/.zcode-plugin` 的工程化配置迁移为符合 ZCode 规范的工作区资源或插件包时使用此技能
• claude-transferUse when the developer says '/claude-transfer', 'close this session', 'hand off to a new session', 'continue t
• claude-unpinned-pip-git-install-commit-pinned-safeOffline-first, precision-first security linter for SKILLS, MCP, plugins, configs and other AI infrastructure.
• claude-vigilFile checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollba
• claude-vs-openai-pr-reviewBattle template comparing Claude and OpenAI on the same code review task using a four-axis rubric.
• claude-wireframe-skillGenerates 5 UX design approaches as interactive prototypes — 1 safe design-system extension and 4 exploratory
• claude2figmaFour-skill enforcement layer for design system compliance in Figma: ensures components are instances of master
• claudeclear-mcpRemove the Claude text watermark by rewriting text, and strip C2PA/EXIF metadata from images.
• claudedesignskills22-skill package across 5 bundles covering Three.js, GSAP ScrollTrigger, React Three Fiber, Framer Motion, Bab
• claudekit-aesthetic-uiA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• claudemap-runtimeInternal ClaudeMap runtime for turning a repository into a live architecture map and driving that map during w
• claudemd-architectGenerate production-grade CLAUDE.md project reference documents for Claude Code. Use when a user wants to crea
• claudemd-reviewUse right after being corrected on something a CLAUDE.md file should already have told you, when explicitly as
• clauder-mcpConnect RStudio to AI assistants for interactive R coding and data analysis.
• claudeshrinkAutomatically compress large natural text or log files before processing. Trigger when the user pastes massive
• claudexorRoute coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
• ClaudiaYao/mcp_a2a_agent_system
• claudii-exploratoresOSINT investigation toolkit. Use when the user wants to investigate or gather open-source intelligence on an i
• clauseReviewing legal documents for Terms of Service, Privacy Policy, and Tokushoho compliance. Detects clause gaps
• clausekeeper-mcpScan website legal docs for missing or stale compliance clauses. Rule-based, no LLM.
• clavio-data-mcpReal-time data resolver for agents. 200 countries, 169k cities, FX, weather, Africa/MENA.
• claw-releaseRelease automation for Claw skills and website. Guides through version bumping, tagging, and release verificat
• claw3d-print-workflowA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• clawbrowserUse when the agent needs to drive a browser through the Microsoft Playwright CLI (`playwright-cli`) for naviga
• clawd-animationClawd 像素风动画生成器。根据用户的自然语言描述，生成自包含的 HTML 像素风动画文件，主角是 Claude Code 的吉祥物 Clawd（像素风小螃蟹）。当用户提到 clawd、clawd 动画、像素动画、pi
• clawd-animation-liteClawd 像素风动画生成器（轻量版）。根据用户的自然语言描述，生成1-3秒的简短clawd动画，当用户的需求的互动场景较为具体和单一，请采用轻量版本生成token消耗少、生成速度快的HTML像素风动画文件。主角是 Cl
• clawdbot-release-checkCheck for new OpenClaw releases and notify once per new version.
• clawdcursorLocal MCP server that gives any AI agent safe cross-OS desktop control — the fallback execution layer for when
• clawddocsClawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, a
• clawdtmClawdTM skills for OpenClaw agents -- search, install, and review skills with security awareness.
• clawhubUse the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need t
• clawifiAgent-native internet gateway: typed search, fetch, scrape, crawl, and extract via the Clawifi API.
• clawkPost, reply, like, and engage on Clawk — Twitter for AI agents.
• clawpod-app-code-reviewReview code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this be
• clawpod-app-debugStructured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack t
• clawpod-app-design-systemAudit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded value
• clawpod-app-email-sequenceDesign and draft multi-email sequences with full copy, timing, branching logic, exit conditions, and performan
• clawpod-app-interview-prepCreate structured interview plans with competency-based questions and scorecards. Trigger with "interview plan
• clawpod-app-seo-auditRun a comprehensive SEO audit — keyword research, on-page analysis, content gaps, technical checks, and compet
• clawpod-app-tech-debtIdentify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what s
• clawpod-app-user-researchPlan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability
• clawringPhone calling skill for OpenClaw: agent makes real outbound phone calls to users for alerts, briefings, remind
• clawsec-clawhub-checkerClawHub reputation checker for clawsec-suite. Adds a standalone reputation gate before guarded skill installat
• clawsec-feedSecurity advisory feed package for OpenClaw-related threats and vulnerabilities. The upstream feed is updated
• clawsec-nanoclawUse when checking for security vulnerabilities in NanoClaw skills, before installing new skills, or when asked
• clawsec-scannerAutomated vulnerability scanner for agent platforms. Performs dependency scanning (npm audit, pip-audit), mult
• clawsec-suiteClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-g
• clawteam-directors-orchestratorClawTeam导演智囊团——基于ClawTeam多智能体框架的世界著名导演协同创作系统。 整合31位全球顶级导演的风格思想，通过多智能体协作机制（顺序链、辩论投票、主席团模式） 辅助剧本创作、影像风格设计和叙事决策。