В каталоге 182 820 навыков в 14 категориях.
恢复之前保存的会话上下文。列出所有待处理的 session，读取选定 session 的任务信息，更新进度，任务全部完成后删除文件。
Review CLAUDE.md files for quality, efficiency, and structure. Use when auditing LLM context files, checking documentati...
Save decision, bet, or learning to the context registry
Save session context to disk for seamless continuation in new chat sessions. This skill should be used when the user ask...
Split large CLAUDE.md into child files. Use when context files exceed line limits, are too verbose, or cover multiple di...
Show current context status and session health. Use to check how much context has been used, whether auto-compact is app...
Checks current context window usage and provides recommendations. Use when sessions feel slow, responses seem degraded,...
Propose writes back to the persistent background context layer — the non-issue-specific things learned in this workspace...
Master Claude Code's context primitives (Skill, Task, Command) and orchestration patterns. Use when designing agent work...
Update CLAUDE.md files to improve efficiency and structure. Use when optimizing LLM context files, implementing review r...
项目上下文自动更新器。当新增功能、重构代码、修改架构时触发，确保 project_context.md 保持最新。触发词：新功能, 重构, 架构变更, 新模块, 新系统, 完成实现。
Validate CLAUDE.md structure, formatting, and quality. Use when checking context files for compliance, ensuring proper s...
Expert guide for engineering and optimizing ultra-large context windows (2M+ tokens) across Gemini 4 Pro, Claude 5.5, an...
Assess the health of your current Claude session context and get a clear action recommendation — no technical metrics ne...
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use whe...
You're a context engineering specialist who has optimized LLM applications handling millions of conversations. You've se...
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot
コンテキストウィンドウの制約内で情報を最適整理するためのスキル。 トークン計測、優先順位付け、圧縮、検証の一連フローを提供する。 Anchors: • High Performance Browser Networking / 適用: 計...
Fetch up-to-date library documentation via Context7 REST API. Use when needing current API docs, framework patterns, or...
Patterns for using Context7 MCP for library documentation (v2.25)
This skill should be used when the user asks to "check documentation", "latest API", "library docs", "context7", or need...
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing...
Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when set...
Attach the newest context-transfer Markdown from the current project's ./.ccb/history/ into Claude using @file. Use when...
OpenClaw continuity kernel for fail-open llm_input injection, deterministic runtime contracts, and shadow-mode eval rece...
Create or update continuity ledger for state preservation across clears
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
Autonomous skill extraction from debugging discoveries. Activates when agents find non-obvious solutions through investi...
Continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /continuous-learning comma...
Automatically extract reusable patterns from Antigravity Code sessions and save them as learned skills for future use.
Capture, organize, and apply learned patterns across sessions. Run at the end of any session where you solved something...
This skill should be used when the user asks to 'extract patterns from this session', 'save what we learned', 'create a...
Voyager-inspired continuous learning system with Critic Agent, Reflection Agent, and Discord-based approval workflow for...
Extract and store reusable patterns, decisions, insights from coding sessions — project scoping, memory-hygiene procedur...
Protocol for the AI to self-analyze sessions and record 'instincts' (reusable patterns) for future improvement.
Instinct-based pattern learning with confidence scoring and auto-evolution
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and e...
Orchestrates a comprehensive multi-agent contract review that analyzes risk, plain-English translation, missing protecti...
Imported skill contributing from openai
Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or...
Market listener control.tick orchestrator
Monitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive...
当系统提示词需要定义 AI 如何分类用户意图、路由到不同处理流程、决定澄清策略和自主度级别时调用此 Skill。适用于多任务型 AI 助手、客服机器人、编程工具、研究助手等需要结构化对话管理的场景。不适用于：纯问答型系统（无任务执行）、单轮...
Fork the current conversation to safely explore an alternative approach without losing current progress
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory
Stateless conversation management with database-backed history, message persistence, and scalable architecture. Use when...
Design conversational AI with Rasa NLU, dialogue management, and LangChain memory patterns.
Convert AgentOps skill formats.
Build AI agents with persistent threads, tool calling, and streaming on Convex. Use when implementing chat interfaces, A...
Customizes what information the LLM receives for each generation. Use this to control message history, implement RAG con...
Troubleshoots agent behavior, logs LLM interactions, and inspects database state. Use this when responses are unexpected...
Sets up and configures Convex agents for chat-based AI interactions. Use this when initializing agent instances, creatin...
Integrates human agents into automated workflows for human-in-the-loop interactions. Use this when humans need to respon...
Sends, saves, retrieves, and manages messages within agent conversations. Use this when handling user messages, displayi...
Implements Retrieval-Augmented Generation (RAG) patterns to enhance agents with custom knowledge bases. Use this when ag...
Streams agent responses in real-time to clients without blocking. Use this for responsive UIs, long-running generations,...
Enables agents to call external functions, APIs, and database operations through tool definitions. Use this when agents...
Orchestrates multi-step agent operations with durable execution, automatic retries, and recovery from failures. Use this...
Set up Sentinel production error capture in your own Convex deployment.
This skill should be used when moving from design to implementation. Triggers on "let's build", "implement this", "looks...
Conserve AI context and API expense in long-running agent tasks through source-preserving checkpoints, targeted retrieva...
Invoke COORD_ENGINE for scheduling engine work
Coord context-aware self-respawn. Invoked by a Coord agent when context window reaches 80% threshold mid-L3. Saves mid-L...
Advanced multi-agent coordination with parallel dispatch and synthesis. Use for complex tasks requiring multiple special...
Coordinated Vulnerability Disclosure for mid-2026 — ISO 29147 (disclosure) + ISO 30111 (handling) + VDP + bug bounty + C...
Manage connections, handshakes, and protocol negotiation between agents (MCP, A2A, ACP).
Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, c...
AI-native agent coordination model — defines abstract operations (spawn, fork, merge, observe, convergence, prune), coor...
Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Cop...
Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot sp...
Expert guidance for Microsoft Copilot Studio development including custom copilots, topic design, trigger phrases, actio...
Build AI copilots, chatbots, and agentic UIs in React and Next.js using CopilotKit. Use this skill when the user wants t...
CopilotKit integration patterns for providers, runtime wiring, `useCoAgent`, `useCopilotAction`, `useLangGraphInterrupt`...
Copy an agent from Product Forge to user or project level
Copy a command from Product Forge to user or project level
Copy a skill from Product Forge to user or project level
Talk to Copywrite Experts about their expertise. Copywrite Experts provides authentic advice using their mental models,...
Identity, routing, communication style, memory protocol, task protocol, decision frameworks, and clarification for TARS
Personal AI Infrastructure core. AUTO-LOADS at session start. The authoritative reference for how the PAI system works,...
(ePost) Use when any agent modifies files, makes architectural decisions, or needs safety and documentation rules
Personal AI Infrastructure core. The authoritative reference for how PAI works.
Pre-computed action manuals for browser automation. Agents receive structured page information instead of parsing entire...
For fetching Rust/crate information, use this priority order:
Claude Code Setting
Core ML, Create ML, Vision framework, Natural Language framework, on-device ML integration. Use when user wants image cl...
Integrate and optimize Core ML models in iOS apps for on-device machine learning inference. Covers model loading (.mlmod...
Corporate Risk Radar. Professional enterprise agent for Corporate Risk Radar within the Corporate Strategy sector.
Performs addition correctly
When the user corrects a factual error, root-cause it immediately. Don't just note the correction — trace the error to i...
Composición y orquestación en cadena (Skill Chains) de múltiples habilidades CORTEX. Dispara con "componer skills", "ski...
Extracción, análisis e inspección de telemetría runtime y logs de transcripción (transcript.jsonl). Dispara con "telemet...
Enhanced mesh coordination with MeshResolver nodes for conflict detection, resolution strategies, and multi-agent file o...
Orchestrate multi-agent pipelines with SwarmCoordinator and AgentMonitor nodes for leader election, health monitoring, a...
Show cost tracking and ROI for this engagement.
Track real-time API cost accrual during LLM execution. Activate on 'cost tracking', 'token usage', 'API costs', 'budget...
Use when building an LLM-powered app that needs cost control via model routing, budget tracking, retry, and prompt cachi...
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and promp...
Break down Claude Code costs using the Agent Monitor pricing engine. Shows per-model costs (input, output, cache_read, c...
Legacy entrypoint; the uncalibrated code-volume and commit-based estimation method is retired.