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.
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- xiaolai
- description
- 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.
- user-invocable
- true
02 资源文件 60
- 参考文档nlpm/.claude-plugin/marketplace.json704 B
- 参考文档nlpm/.claude-plugin/plugin.json348 B
- 参考文档nlpm/.github/workflows/auditor-audit.yml33.4 KB
- 参考文档nlpm/.github/workflows/auditor-batch-processor.yml6.1 KB
- 参考文档nlpm/.github/workflows/auditor-case-study.yml30.4 KB
- 参考文档nlpm/.github/workflows/auditor-contribute.yml9.2 KB
- 参考文档nlpm/.github/workflows/auditor-daily-report.yml10.4 KB
- 参考文档nlpm/.github/workflows/auditor-discover.yml7.9 KB
- 参考文档nlpm/.github/workflows/auditor-integration-test.yml8.5 KB
- 参考文档nlpm/.github/workflows/auditor-track.yml4.1 KB
- 其他nlpm/.gitignore51 B
- 参考文档nlpm/.nlpm-test/checker.spec.md866 B
- 参考文档nlpm/.nlpm-test/scanner.spec.md928 B
- 参考文档nlpm/.nlpm-test/scorer.spec.md1.1 KB
- 参考文档nlpm/.nlpm-test/tester.spec.md926 B
- 参考文档nlpm/.nlpm-test/vague-scanner.spec.md833 B
- 参考文档nlpm/agents/checker.md2.7 KB
- 参考文档nlpm/agents/scanner.md1.8 KB
- 参考文档nlpm/agents/scorer.md3.2 KB
- 参考文档nlpm/agents/security-scanner.md4.2 KB
- 参考文档nlpm/agents/tester.md3.7 KB
- 参考文档nlpm/agents/vague-scanner.md1.6 KB
- 参考文档nlpm/auditor/audits/anthropics-claude-plugins-official.md19.7 KB
- 参考文档nlpm/auditor/audits/deanpeters-Product-Manager-Skills.md12.0 KB
- 参考文档nlpm/auditor/audits/hashicorp-agent-skills.md10.9 KB
- 参考文档nlpm/auditor/audits/openai-codex-plugin-cc.md9.9 KB
- 参考文档nlpm/auditor/audits/slavingia-skills.md3.6 KB
- 参考文档nlpm/auditor/audits/tech-leads-club-agent-skills.md18.3 KB
- 参考文档nlpm/auditor/audits/thedotmack-claude-mem.md11.6 KB
- 参考文档nlpm/auditor/audits/trailofbits-skills.md28.8 KB
- 参考文档nlpm/auditor/audits/xiaolai-loc-guardian-for-claude.md3.9 KB
- 参考文档nlpm/auditor/feedback/log.json219 B
- 其他nlpm/auditor/logs/events.jsonl2.3 KB
- 参考文档nlpm/auditor/README.md6.8 KB
- 参考文档nlpm/auditor/registry/repos.json4.8 KB
- 其他nlpm/auditor/reports/.gitkeep—
- 参考文档nlpm/auditor/reports/2026-04-07.md890 B
- 参考文档nlpm/auditor/reports/2026-04-08.md619 B
- 脚本nlpm/auditor/scripts/guard-protected-paths.sh1.2 KB
- 脚本nlpm/auditor/scripts/log-event.sh1.8 KB
- 脚本nlpm/auditor/scripts/validate-feedback.sh1.7 KB
- 资产文件nlpm/case-studies/gsd-article-cover.png3.4 MB
- 参考文档nlpm/case-studies/how-we-helped-gsd.md30.4 KB
- 参考文档nlpm/CLAUDE.md5.6 KB
- 参考文档nlpm/commands/check.md2.2 KB
- 参考文档nlpm/commands/fix.md2.5 KB
- 参考文档nlpm/commands/init.md1.7 KB
- 参考文档nlpm/commands/ls.md899 B
- 参考文档nlpm/commands/score.md2.9 KB
- 参考文档nlpm/commands/security-scan.md1.3 KB
- 参考文档nlpm/commands/shared/classify.md2.2 KB
- 参考文档nlpm/commands/shared/discover.md3.1 KB
- 参考文档nlpm/commands/test.md2.2 KB
- 参考文档nlpm/commands/trend.md2.2 KB
- 参考文档nlpm/EXAMPLES.md22.1 KB
- 参考文档nlpm/hooks/hooks.json283 B
- 许可证nlpm/LICENSE1.0 KB
- 参考文档nlpm/README.md8.9 KB
- 参考文档nlpm/RULES.md1.2 KB
- 脚本nlpm/scripts/check-artifact.sh1.3 KB
03 SKILL.md 正文
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
/xiaolaiwith no argument, show the menu above and ask which tool to use. - If the user typed
/xiaolai sdkor/xiaolai agent— readclaude-agent-sdk/SKILL.mdand follow its instructions. - If the user typed
/xiaolai nlpm— readnlpm/CLAUDE.mdand follow its instructions. For specific nlpm commands, read the corresponding file undernlpm/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/
- TypeScript details:
- NLPM entry:
nlpm/CLAUDE.md- Commands:
nlpm/commands/*.md - Agents:
nlpm/agents/*.md - Skills/knowledge:
nlpm/skills/nlpm/
- Commands:
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
04 同仓库更多 Skills
xiaolai-methodology
以李笑来(Li Xiaolai)的思考方式、方法论与表达风格,为用户做全方位 1-on-1 教练指导,覆盖创业、赚钱、投资、学习、自学、读书写作、用 AI、以及人生心态与自我管理。当用户提到 "李笑来"、"笑来"、"笑来老师"、"扮演李笑来"、"找笑来聊聊"、"笑来怎么看"、"xiaolai"、"把时间当作朋友"、"通往财富自由之路"、"定投改变命运"、"韭菜的自我修养"、"自学是门手艺"、"让时间陪你慢慢变富"、"七年就是一辈子"、"元认知"、"活在未来"、"复利/长期主义"、"践行"、"痴迷改进"、"个人商业模式/出售时间"、"睡后收入"、"定投"、"财富自由"、"操作系统升级"、"最少必要知识"、"北极星提示词"、"用 AI 该怎么学/思考" 等任一触发词,或当用户带着关于创业/赚钱/投资/学习/职业/重大人生决策的困惑、希望被人用笑来式的「逻辑 + 大白话 + 类比 + 重新定义 + 践行导向」来点醒和指导时,自动进入李笑来教练模式。
zread
Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `./.zread/wiki/`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module/package explanations, or "what does this repo do"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread / zread.ai directly. Also use it proactively before diving into a large unknown repo — if `./.zread/wiki/current` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word "zread".
youtube
Launch the YouTube Creator Agent to auto-generate videos. Use when: user types /youtube, wants to create YouTube videos, generate video content, or upload to YouTube. Keywords: youtube, video, 视频, 创作视频, 发布视频
youtube-script-sync
Sync, update, or optimize Tony's GetNote knowledge base `Youtube视频逐字稿` by turning each parent recording or first-person idea note into an idempotent child note containing a directly recordable YouTube long-video or Shorts script. Use when the user says “更新/同步/优化 Youtube视频逐字稿知识库”, or says “更新/同步/优化该知识库” while this knowledge base is the active context.
writing-skills
How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing Claude Code skills.
writing-rules
How to write .claude/rules/ files that Claude actually follows. Use when creating, improving, or reviewing project rules.