How do I install the Xiaolai skill?

Run npx skillmds@latest add shengdabai/xiaolai 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.

Is Xiaolai safe to use?

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.

Which AI agents work with Xiaolai?

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.

Is Xiaolai free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Xiaolai?

shengdabai (@shengdabai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Xiaolai by shengdabai — Agent Skill

Name: Xiaolai
Author: shengdabai

Xiaolai

Xiaolai's Claude tools collection. Use when user types /xiaolai. Routes to: (1) claude-agent-sdk — Agent SDK reference for building autonomous AI agents, or (2) nlpm — Natural-Language Programming Manager for scanning, scoring, and fixing NL artifacts.

shengdabai 8fe7114 61 files · 3.8 MB Updated Sep 17, 2026

File contents

Xiaolai's Claude Tools

You have two tools available. Ask the user which one they want to use:

Available Tools

1. Claude Agent SDK (`/xiaolai sdk` or `/xiaolai agent`)

Build autonomous AI agents with Claude Agent SDK (TypeScript v0.2.96 / Python v0.1.56). Covers: query(), hooks, subagents, MCP, permissions, sandbox, structured outputs, sessions.

Use when: building AI agents, configuring MCP servers, setting up permissions/hooks, using structured outputs, troubleshooting SDK errors, or working with subagents.

2. NLPM (`/xiaolai nlpm`)

Natural-Language Programming Manager — scan, lint, and score NL artifacts with Claude-native quality scoring.

Commands:

/nlpm:ls — discover NL artifacts
/nlpm:score — 100-point quality scoring
/nlpm:check — cross-component consistency
/nlpm:fix — auto-fix mechanical issues
/nlpm:trend — track score history
/nlpm:test — run NL-TDD specs
/nlpm:init — configure project
/nlpm:security-scan — scan plugin for security risks

Routing Logic

If the user typed /xiaolai with no argument, show the menu above and ask which tool to use.
If the user typed /xiaolai sdk or /xiaolai agent — read claude-agent-sdk/SKILL.md and follow its instructions.
If the user typed /xiaolai nlpm — read nlpm/CLAUDE.md and follow its instructions. For specific nlpm commands, read the corresponding file under nlpm/commands/.
If the user's context makes it obvious which tool applies (e.g. they're building an agent → sdk, they want to score/lint NL artifacts → nlpm), route directly without asking.

File Locations

All files are relative to this skill's directory (~/.claude/skills/xiaolai/):

SDK entry: claude-agent-sdk/SKILL.md
- TypeScript details: claude-agent-sdk/SKILL-typescript.md
- Python details: claude-agent-sdk/SKILL-python.md
- Agent templates: claude-agent-sdk/templates/
- Agent rules: claude-agent-sdk/rules/
NLPM entry: nlpm/CLAUDE.md
- Commands: nlpm/commands/*.md
- Agents: nlpm/agents/*.md
- Skills/knowledge: nlpm/skills/nlpm/

Auto-Update

Both repos are git clones. To update, run:

cd ~/.claude/skills/xiaolai/claude-agent-sdk && git pull
cd ~/.claude/skills/xiaolai/nlpm && git pull

---name: xiaolaidescription: Xiaolai's Claude tools collection. Use when user types /xiaolai. Routes to: (1) claude-agent-sdk — Agent SDK reference for building autonomous AI agents, or (2) nlpm — Natural-Language Programming Manager for scanning, scoring, and fixing NL artifacts.---# Xiaolai's Claude ToolsYou have two tools available. Ask the user which one they want to use:## Available Tools### 1. Claude Agent SDK (`/xiaolai sdk` or `/xiaolai agent`)Build autonomous AI agents with Claude Agent SDK (TypeScript v0.2.96 / Python v0.1.56).Covers: `query()`, hooks, subagents, MCP, permissions, sandbox, structured outputs, sessions.**Use when:** building AI agents, configuring MCP servers, setting up permissions/hooks, using structured outputs, troubleshooting SDK errors, or working with subagents.### 2. NLPM (`/xiaolai nlpm`)Natural-Language Programming Manager — scan, lint, and score NL artifacts with Claude-native quality scoring.**Commands:**- `/nlpm:ls` — discover NL artifacts- `/nlpm:score` — 100-point quality scoring- `/nlpm:check` — cross-component consistency- `/nlpm:fix` — auto-fix mechanical issues- `/nlpm:trend` — track score history- `/nlpm:test` — run NL-TDD specs- `/nlpm:init` — configure project- `/nlpm:security-scan` — scan plugin for security risks---## Routing Logic1. If the user typed `/xiaolai` with no argument, show the menu above and ask which tool to use.2. If the user typed `/xiaolai sdk` or `/xiaolai agent` — read `claude-agent-sdk/SKILL.md` and follow its instructions.3. If the user typed `/xiaolai nlpm` — read `nlpm/CLAUDE.md` and follow its instructions. For specific nlpm commands, read the corresponding file under `nlpm/commands/`.4. If the user's context makes it obvious which tool applies (e.g. they're building an agent → sdk, they want to score/lint NL artifacts → nlpm), route directly without asking.## File LocationsAll files are relative to this skill's directory (`~/.claude/skills/xiaolai/`):- **SDK entry:** `claude-agent-sdk/SKILL.md` - TypeScript details: `claude-agent-sdk/SKILL-typescript.md` - Python details: `claude-agent-sdk/SKILL-python.md` - Agent templates: `claude-agent-sdk/templates/` - Agent rules: `claude-agent-sdk/rules/`- **NLPM entry:** `nlpm/CLAUDE.md` - Commands: `nlpm/commands/*.md` - Agents: `nlpm/agents/*.md` - Skills/knowledge: `nlpm/skills/nlpm/`## Auto-UpdateBoth repos are git clones. To update, run:```bashcd ~/.claude/skills/xiaolai/claude-agent-sdk && git pullcd ~/.claude/skills/xiaolai/nlpm && git pull```

Frequently asked questions