В каталоге 182 820 навыков в 14 категориях.
Run a non-interactive Claude Code print-mode call from Codex. Use when the user asks to "claude print", "ask claude", "r...
Anthropic official XML tag patterns and prompt engineering best practices. Document behavior control tags, system prompt...
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Us...
Self-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences
Restart Claude Code session to reload new skills, manage context, or start fresh. Use this skill when skills have been a...
Start fresh with cleared history after task completion. Use PROACTIVELY when user says "done"/"finished", all tasks comp...
Compact context at natural breakpoints to free tokens and continue working. Use PROACTIVELY at phase boundaries, after c...
Quick restart to reload configuration changes (skills, settings, hooks, MCP services). Use PROACTIVELY after modifying ....
Skills for the Claude Code model routing system — managing persistent subagents (haiku/sonnet/opus).
Build autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best...
(Renamed) Search, recover, and analyze sessions from Claude Code, AI Studio, and Gemini CLI — use /ar:ai-session-tools (...
Guides creation and improvement of Claude Code skills using Anthropic's official methodology. Use when user wants to "cr...
Speak text aloud using high-quality AI voice synthesis (Kokoro TTS on Apple Silicon). Use when user asks to vocalize, na...
Force Claude Code to work like a senior developer: plan before coding, work in isolation, write tests first, and review...
Synchronize Claude Code configuration files to existing codebases. Updates skills, CLAUDE.md, settings, and related conf...
Replace with description of the skill and when Claude should use it.
Comprehensive guide for AI agents on proper Claude-style tool calling with correct syntax, patterns, and examples
Discover and list all Claude Code skills, agents, plugins, MCP servers, and hooks available in this project
Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, impleme...
Claudeception is a continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /claude...
Optimize CLAUDE.md files based on Claude 4 best practices from Anthropic's official documentation. Use when reviewing or...
Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel...
Analyze and optimize prompts using 6-dimension quality assessment (Clarity, Efficiency, Structure, Completeness, Actiona...
Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style...
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch...
Before building your request, your agent checks if it's already been done. Faster results, less wasted effort.
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch ne...
ClaWHub skills marketplace: browse, search, install, rate, review skills. https://clawhub.com
clawhub
Phone calling skill for OpenClaw: agent makes real outbound phone calls to users for alerts, briefings, reminders, and u...
Multi-agent team orchestration CLI for spawning agents, managing tasks, and coordinating work through mailbox messaging...
ClawTeam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。 触发词：「导演智囊团...
Community incident reporting for AI agents. Contribute to collective security by reporting threats.
An elephant never forgets. Structured memory for OpenClaw agents.
Voice/audio cleanup step of the AI Video Editor pipeline — diagnose a video's background noise, pick the right denoise m...
Remove specified clutter from a room photograph with an AI-native contextual edit while preserving architecture, fixed f...
Safely flush context and resume fresh - distills session state before clearing
Manages context overflow by handing off to a fresh subagent at 80% usage. Use when context pressure is critical and work...
Expert guidance for ClearML, the open-source MLOps platform for experiment tracking, pipeline orchestration, data manage...
Participate in Council multi-agent collaboration sessions. Use when asked to join a council session, collaborate with ot...
Manage skills - reusable, parameterized prompts.
Assess client health from Littlebird evidence. Use for churn risk, scope creep, margin pressure, or weekly account revie...
Extracts medical entities (Diseases, Medications, Procedures) and patient outcome mentions with temporal anchoring from...
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matc...
Clones a STATIC IMAGE ad into finished ads for your own product, into a reusable prompt TEMPLATE, or both — the template...
Neural network training and deployment in Flow Nexus cloud. Use for distributed ML training, model inference, and neural...
Search cloud memory backup when local results are insufficient. Use when memory_search returns few/no results for a topi...
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, schedul...
Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.
Cloudflare AI Gateway for unified interface to AI providers with caching, rate limiting, and analytics
Cloudflare AI Search for semantic search and vector embeddings in Workers
Run LLMs and AI models on Cloudflare's GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1, Flux images,...
Run LLMs and AI models on Cloudflare's global GPU network with Workers AI. Includes Llama, Flux image generation, BGE em...
Production-ready knowledge domain for building AI-powered applications with Cloudflare Workers AI.
Reference system prompt and tool schemas for Cluely. Use when imitating, comparing, or analyzing Cluely's prompting styl...
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...
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, a...
A template demonstrating the universal format compatible with Antigravity, Claude, Cursor, and OpenClaw.
Use when asked 大模型备案怎么做, 生成式人工智能服务备案还是登记, 算法备案流程, AI 生成内容标识怎么加, 我们接了已备案的大模型还要备案吗, or prepare a generative AI product for...
查询 CNB 平台官方文档，覆盖代码托管、制品库、AI 助手、云原生构建等。
改写中文学术论文中被知网AIGC检测器标为"红色显著"的段落，目标是将AI率落出红色区间且不改变事实/数字/术语/引用。基于实战将20.6%降至10.1%（净降10.5个百分点）的工作流提炼。使用场景：用户提到"知网AIGC""降AI率""...
---name: cnv-caller-agent
---name: coagulation-thrombosis-agent
Invoke Elves Cobbler, the default orchestration model for fitted answers and agent routing. Use when the user types /cob...
Turn on Elves Cobbler Mode for the current Claude Code thread. Use when the user types /cobbler-mode or asks to keep cha...
Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology a...
研究 codex 使用 skill 生成 survey 這件事
This skill should be used when the CoBuilder Guardian needs to act as an independent guardian angel — designing PRDs wit...
Behavioral specification for the CoBuilder Heartbeat teammate. Loaded as prompt when spawning the Haiku work-finder agen...
Generates complex text-heavy and structured images by converting natural language descriptions into executable code that...
Generate code explanation cards with syntax highlighting for tutorials and education. Creates title cards and explanatio...
What is generated, what generates it, and the rules around generated code (proto, GraphQL SDL, Prisma) in this repo.
Code mode operational spec for the team lead. Returns lead identity, facilitator identity, mode-specific rules, suggest-...
Analyze your Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engi...
Use when working with code refactoring context restore
Revisione del codice scritto contro le regole presenti in .claude/rules/ del progetto. È un'integrazione del code review...
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code fo...
Multi-agent code review using the Pragmatic Quality framework. Orchestrates parallel review agents (CLAUDE.md compliance...
Prototype a video in code with an agent. Decides if a shot needs a 3D prototype at all and which tool fits (Three.js, Bl...
Reference system prompt and tool schemas for CodeBuddy. Use when imitating, comparing, or analyzing CodeBuddy's promptin...
codeck entry point. Scans local files for materials, shows pipeline dashboard with diagnostic intelligence, guides user...
Publisher role. Exports deck to PDF or PPTX with post-export QA. Use whenever the user says "export", "to PDF", "to PPTX...
Create a git commit following the team's Conventional Commit conventions. Use when the user asks to commit changes or cr...
Implement one phase of the plan specified by the user. Only implements a single phase per invocation, then stops for use...
Codebase haritasını güncelle. "/codemap-update" komutuyla veya her feature implementation sonrasında otomatik çalışır. C...
Run the Codex Optimized Development, Evaluation, and Remediation (CODER) Loop with an orchestration-only coordinator, no...
AI context persistence - tags in code = permanent memory across sessions
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "a...
Delegate narrow, mechanical coding tasks to OpenAI Codex Command Line Interface (CLI) — Claude orchestrates and judges,...
Codex CLI を read-only sandbox で実行し、OpenAI 側のセカンドオピニオンを得る。
Bridge to the OpenAI Codex CLI for high-reasoning tasks using gpt-5.3-codex.
Get alternative perspectives via OpenAI Codex on complex design decisions, architecture trade-offs, stuck debugging, or...
Execute tasks using the OpenAI Codex CLI (GPT-5.2). This agent MUST run codex exec for every request - it delegates work...
Orchestrates OpenAI Codex CLI from Claude Code via tmux. Use when delegating implementation tasks to Codex, running /cod...
Multi-AI second opinion via OpenAI Codex CLI. Three modes: Review (pass/fail gate), Challenge (adversarial edge-case fin...
Run OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI mo...