Provides local documentation for the Claude Agent SDK (formerly Claude Code SDK).
Use this skill to answer questions about building AI agents with the Agent SDK,
including Python and TypeScript API usage, built-in tools, hooks, subagents, MCP,
sessions, permissions, structured outputs, hosting, deployment, and more.
When to use
When the user asks about Claude Agent SDK development, API, or configuration
When developing code that imports claude_agent_sdk or @anthropic-ai/claude-agent-sdk
When the user mentions "agent sdk", "claude agent sdk", or "claude code sdk"
When building AI agents using the Agent SDK
When NOT to use
General Claude API questions that don't involve the Agent SDK
Claude Code CLI usage questions (use claude-code-guide agent instead)
Instructions
Read the documentation index at skills/agent-sdk/docs/INDEX.md to understand the available docs
Based on the user's question, read the relevant doc file(s) from skills/agent-sdk/docs/
Answer the question using the documentation content, providing code examples when appropriate
Always include both Python and TypeScript examples when available in the docs
Documentation update
When the user says "update agent sdk docs" or "更新 agent sdk 文档":
Run the update script: python3 skills/agent-sdk/scripts/update-docs.py
Report how many pages were updated successfully
Key documentation files
Topic
File
Overview & getting started
docs/overview.md
Quickstart tutorial
docs/quickstart.md
Agent loop internals
docs/agent-loop.md
Claude Code features
docs/claude-code-features.md
Sessions & context
docs/sessions.md
Streaming input
docs/streaming-vs-single-mode.md
Streaming output
docs/streaming-output.md
MCP servers
docs/mcp.md
Custom tools
docs/custom-tools.md
Tool search
docs/tool-search.md
Permissions
docs/permissions.md
User input & approvals
docs/user-input.md
Hooks
docs/hooks.md
File checkpointing
docs/file-checkpointing.md
Structured outputs
docs/structured-outputs.md
Hosting
docs/hosting.md
Secure deployment
docs/secure-deployment.md
System prompts
docs/modifying-system-prompts.md
Subagents
docs/subagents.md
Slash commands
docs/slash-commands.md
Skills
docs/skills.md
Cost tracking
docs/cost-tracking.md
Todo lists
docs/todo-tracking.md
Plugins
docs/plugins.md
TypeScript SDK ref
docs/typescript.md
TypeScript V2
docs/typescript-v2-preview.md
Python SDK ref
docs/python.md
Migration guide
docs/migration-guide.md
1---2name: agent-sdk3description: Claude Agent SDK4---5# Claude Agent SDK67Provides local documentation for the Claude Agent SDK (formerly Claude Code SDK).8Use this skill to answer questions about building AI agents with the Agent SDK,9including Python and TypeScript API usage, built-in tools, hooks, subagents, MCP,10sessions, permissions, structured outputs, hosting, deployment, and more.1112## When to use1314- When the user asks about Claude Agent SDK development, API, or configuration15- When developing code that imports `claude_agent_sdk` or `@anthropic-ai/claude-agent-sdk`16- When the user mentions "agent sdk", "claude agent sdk", or "claude code sdk"17- When building AI agents using the Agent SDK1819## When NOT to use2021- General Claude API questions that don't involve the Agent SDK22- Claude Code CLI usage questions (use claude-code-guide agent instead)2324## Instructions25261. Read the documentation index at `skills/agent-sdk/docs/INDEX.md` to understand the available docs272. Based on the user's question, read the relevant doc file(s) from `skills/agent-sdk/docs/`283. Answer the question using the documentation content, providing code examples when appropriate294. Always include both Python and TypeScript examples when available in the docs3031### Documentation update3233When the user says "update agent sdk docs" or "更新 agent sdk 文档":34351. Run the update script: `python3 skills/agent-sdk/scripts/update-docs.py`362. Report how many pages were updated successfully3738### Key documentation files3940| Topic | File |41|-------|------|42| Overview & getting started | `docs/overview.md` |43| Quickstart tutorial | `docs/quickstart.md` |44| Agent loop internals | `docs/agent-loop.md` |45| Claude Code features | `docs/claude-code-features.md` |46| Sessions & context | `docs/sessions.md` |47| Streaming input | `docs/streaming-vs-single-mode.md` |48| Streaming output | `docs/streaming-output.md` |49| MCP servers | `docs/mcp.md` |50| Custom tools | `docs/custom-tools.md` |51| Tool search | `docs/tool-search.md` |52| Permissions | `docs/permissions.md` |53| User input & approvals | `docs/user-input.md` |54| Hooks | `docs/hooks.md` |55| File checkpointing | `docs/file-checkpointing.md` |56| Structured outputs | `docs/structured-outputs.md` |57| Hosting | `docs/hosting.md` |58| Secure deployment | `docs/secure-deployment.md` |59| System prompts | `docs/modifying-system-prompts.md` |60| Subagents | `docs/subagents.md` |61| Slash commands | `docs/slash-commands.md` |62| Skills | `docs/skills.md` |63| Cost tracking | `docs/cost-tracking.md` |64| Todo lists | `docs/todo-tracking.md` |65| Plugins | `docs/plugins.md` |66| TypeScript SDK ref | `docs/typescript.md` |67| TypeScript V2 | `docs/typescript-v2-preview.md` |68| Python SDK ref | `docs/python.md` |69| Migration guide | `docs/migration-guide.md` |
Run npx skillmds@latest add lldxflwb/agent-sdk in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Claude Agent SDK It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
lldxflwb (@lldxflwb) published this skill. Their other Agent Skills are listed on their SkillMD profile.
lldxflwb