精选 Skills 索引（第 39 页）
按质量分排序的前 8,000 个 Skills，每个都有可收录的独立页面。需要全库 15.8 万条检索时，请使用 Skills 目录。
- ck:google-adk-python
Build AI agents with Google ADK Python. Multi-agent systems, A2A protocol, MCP tools, workflow agents, state/memory, callbacks/plugins, Vertex AI deployment, evaluation.
- clarify-spec
| Signal | Beispiele | Warum problematisch | |--------|-----------|---------------------| | Kurzer Auftrag (<25 Woerter) | Mach den Export besser | Zu wenig Kontext | | Keine Dateinamen/Pfade | Optimiere die Performance | Scope unklar | |…
- Claude Code X - Autonomous Execution Subagent
Execute Claude Code autonomously in the background for well-defined tasks, enabling parallel execution of up to 5 concurrent sessions while the user continues other work.
- claude-allow-stop
Return to normal stop behavior. Use PROACTIVELY after completing all tasks in continuous work mode, when work is committed and tests pass, or when reaching natural stopping point. User can invoke with /claude-allow-stop.
- claude-get-session-info
Shared utility script for getting Claude PID and Session ID. Source this in other scripts to access CLAUDE_PID and SESSION_ID variables.
- claudisms
Claude Code plugin enforcing operational guidelines, terse responses, sequential execution, and no destructive operations without confirmation.
- coding-agent
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs…
- Context
To maintain the integrity of audit logs, we must ensure that agents use their real identities in worklogs, rather than blindly copying "codex" from templates.
- Convex Agents Files
Handles file uploads, image attachments, and media processing in agent conversations. Use this when agents analyze images, process documents, or generate files.
- convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
- core-actionbook
Pre-computed action manuals for browser automation. Agents receive structured page information instead of parsing entire HTML.
- core-agent-browser
For fetching Rust/crate information, use this priority order: 1. **rust-learner skill** - Orchestrates actionbook + browser-fetcher 2. **actionbook MCP** - Pre-computed selectors for known sites 3. **agent-browser CLI** - Direct browser au…
- create-subagents
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
- creating-opencode-agents
Use when creating OpenCode agents - provides markdown format with YAML frontmatter, mode/tools/permission configuration, and best practices for specialized AI assistants
- creating-subagents
Guide for creating custom Claude Code subagents (Task tool agents). Use when building specialized autonomous agents for specific domains or workflows. Covers agent definition, frontmatter options, tool restrictions, and spawning patterns.
- deep-agents-core
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
- deep-agents-memory
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
- document-lessons-as-snippets
When you make a mistake or discover a better approach, immediately suggest creating an Agent Beha... Use when configuring AI agent workflows and patterns. Agent Behavior category skill.
- email-agent
Processes incoming emails for Unite-Hub. Extracts sender data, identifies communication intents, links to CRM contacts, analyzes sentiment, and updates contact records with AI insights.
- erpnext-code-interpreter
Intelligent agent for interpreting vague ERPNext development requests and producing concrete technical specifications. Use when receiving unclear requirements like 'make invoice auto-calculate', 'add approval workflow', 'sync with external…
- expertise-file-design
Design YAML expertise file structures for agent experts. Use when creating mental models for domain-specific agents, defining expertise schema, or structuring knowledge for Act-Learn-Reuse workflows.
- explain-decisions
Always explain your reasoning before making changes Use when configuring AI agent workflows and patterns. Agent Behavior category skill.
- female_therapist_roleplay
Roleplay as a kind, female therapist who corrects user grammar, avoids self-disclosure, and offers advice only when explicitly asked.
- general-purpose
General-purpose agent for researching complex questions and executing multi-step tasks. Versatile problem-solver that combines research capabilities, analytical thinking, and systematic task execution. Use for complex research projects, mu…
- google-adk-python
Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.
- harness-coder
Main coding agent for autonomous harness system. Continues work from previous sessions, implements one feature per session, coordinates with testing and review skills, and maintains clean handoffs via Archon. This is the workhorse of the h…
- headless-cli-agents
Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD integrations, multi-agent orchestration, or programmatic Claude interactions. Covers CLI flags (-p, --output-for…
- headless-mode
Guide for using Claude Code programmatically via CLI flags and SDKs. Use for automation, CI/CD pipelines, scripting, and building tools on top of Claude Code. Covers --print mode, output formats, session management, and SDK integration.
- hive
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive-* skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
- hive-concepts
Core concepts for goal-driven agents - architecture, node types (event_loop, function), tool discovery, and workflow overview. Use when starting agent development or need to understand agent fundamentals.
- hive-patterns
Best practices, patterns, and examples for building goal-driven agents. Includes client-facing interaction, feedback edges, judge patterns, fan-out/fan-in, context management, and anti-patterns.
- hook-creator
创建和配置 Claude Code 钩子以自定义代理行为。当用户需要以下操作时使用：(1) 创建新钩子，(2) 配置自动格式化、日志记录或通知，(3) 添加文件保护或自定义权限，(4) 设置工具执行前后的操作，(5) 询问钩子事件如 PreToolUse、PostToolUse、Notification 等。
- hook-development
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous…
- hook-event-architecture
Design hook-based event systems for ADW observability. Use when implementing real-time event broadcasting, creating hook pipelines, or building agent activity monitoring.
- hosted-agents
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal…
- hosted-agents-v2-py
Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based agents in Azure AI Foundry.
- ilya-sutskever
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na…
- implementing-agent-modes
Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what conditions. Achieve better results using your plan mode.
- incremental-commits
Commit code after each logical unit of work is complete Use when configuring AI agent workflows and patterns. Agent Behavior category skill.
- kagent
Kubernetes-native AI agent framework for building, deploying, and managing AI agents on Kubernetes. This skill should be used when deploying AI agents as Kubernetes resources, analyzing cluster health with AI, and automating complex K8s op…