Back to Details

skill-integrator

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill Integrator: Surface Skills Where They're Needed

Skill Integrator：在需要的地方呈现技能

You bridge the gap between installed skills and agent awareness. Your role is to analyze project context, score installed skills for relevance, and generate actionable trigger-based guidance that gets inserted into CLAUDE.md or AGENTS.md.
你负责搭建已安装技能与Agent认知之间的桥梁。你的职责是分析项目上下文，为已安装技能进行相关性评分，并生成可执行的、基于触发条件的使用指南，插入到CLAUDE.md或AGENTS.md文件中。

Core Principle

核心原则

Skills only help when agents know to reach for them. A hundred installed skills are useless if the agent doesn't know when each one applies. This skill transforms a silent inventory into active, contextual guidance.
**只有当Agent知道何时调用技能时，技能才能发挥作用。**如果Agent不知道每个技能的适用场景，即使安装了上百个技能也毫无用处。本技能将静态的技能清单转化为动态的、上下文相关的使用指南。

Quick Reference

快速参考

SituationCommand
First-time setup
/skill-integrator
→ generates full guidance section
After installing a skill
/skill-integrator <skill-name>
→ adds single skill
Guidance feels stale
/skill-integrator
→ regenerates with current inventory
Check what scripts do
--help
flag on any script
Pipeline:
bash
deno run --allow-read scripts/analyze-project.ts --json > /tmp/ctx.json
deno run --allow-read scripts/scan-skills.ts --json > /tmp/skills.json
deno run --allow-read scripts/generate-guidance.ts --project-context /tmp/ctx.json --skills /tmp/skills.json
场景命令
首次搭建
/skill-integrator
→ 生成完整的指南章节
安装单个技能后
/skill-integrator <skill-name>
→ 添加单个技能的指南
指南内容过时
/skill-integrator
→ 根据当前技能清单重新生成指南
查看脚本功能在任意脚本后添加
--help
参数
执行流程：
bash
deno run --allow-read scripts/analyze-project.ts --json > /tmp/ctx.json
deno run --allow-read scripts/scan-skills.ts --json > /tmp/skills.json
deno run --allow-read scripts/generate-guidance.ts --project-context /tmp/ctx.json --skills /tmp/skills.json

The States

状态划分

State SI0: No Integration

状态SI0：未集成

Symptoms: Project has skills installed in 
.claude/skills/
but CLAUDE.md/AGENTS.md has no skill guidance section. Agents work without awareness of available tools. Key Questions: How many skills are installed? What project type is this? Does CLAUDE.md even exist? Interventions: Run full analysis pipeline: analyze-project → scan-skills → generate-guidance. Generate comprehensive trigger-based section. Present to user for insertion.
症状： 项目在
.claude/skills/
目录下安装了技能，但CLAUDE.md/AGENTS.md中没有技能指南章节。Agent在工作时无法感知可用工具。 关键问题： 已安装多少技能？项目类型是什么？CLAUDE.md是否存在？ 处理措施： 运行完整的分析流程：analyze-project → scan-skills → generate-guidance。生成全面的、基于触发条件的指南章节，提交给用户确认后插入到文件中。

State SI1: Stale Integration

状态SI1：集成内容过时

Symptoms: A skill guidance section exists (look for 
<!-- Generated by skill-integrator
comment) but skills have been added or removed since it was last generated. Installed skill count doesn't match documented count. Key Questions: Which skills were added since last generation? Which were removed? Has the project type changed? Interventions: Run pipeline again with current state. Diff against existing section. Present changes for approval. Surgically update the marked section.
症状： 文件中存在技能指南章节（可通过
<!-- Generated by skill-integrator
注释识别），但自上次生成后，技能有添加或移除操作，已安装技能数量与文档记录的数量不匹配。 关键问题： 自上次集成后新增了哪些技能？移除了哪些技能？项目类型是否发生变化？ 处理措施： 根据当前状态重新运行流程，对比现有章节内容，提交变更内容供用户审批，精准更新标记的章节。

State SI2: Single Skill Addition

状态SI2：新增单个技能

Symptoms: User just installed one skill and wants it integrated into existing guidance. Or user invokes 
/skill-integrator <skill-name>
. Key Questions: What does this skill do? Which trigger category does it belong in? Where in the existing guidance should it go? Interventions: Run single-skill mode: scan the new skill, score against project context, generate a single guidance line with trigger category placement. Insert into existing section at the right location.
症状： 用户刚安装了一个技能，希望将其整合到现有指南中；或用户调用了
/skill-integrator <skill-name>
命令。 关键问题： 该技能的功能是什么？属于哪类触发场景？应插入到现有指南的哪个位置？ 处理措施： 运行单技能模式：扫描新技能，基于项目上下文评分，生成单条带触发场景的指南内容，并插入到现有指南的对应位置。

State SI3: Wrong Fit

状态SI3：适配不当

Symptoms: Guidance references irrelevant skills, wrong trigger categories, or generic descriptions that don't help agents decide when to use a skill. Skills are listed but not effectively surfaced. Key Questions: Are trigger categories appropriate for this project type? Are descriptions actionable or just echoing SKILL.md? Does the threshold need adjusting? Interventions: Re-run with adjusted threshold. Review trigger category assignments. Customize descriptions to project-specific contexts rather than generic skill descriptions.
症状： 指南中引用了不相关的技能、触发场景分类错误，或描述过于通用，无法帮助Agent判断何时使用技能。技能虽被列出，但未有效呈现。 关键问题： 触发场景分类是否适合当前项目类型？描述是否具备可操作性，还是仅重复SKILL.md的内容？是否需要调整相关性阈值？ 处理措施： 调整阈值后重新运行流程，检查触发场景分类是否合理，针对项目特定上下文自定义描述内容，而非使用通用的技能描述。

Diagnostic Process

诊断流程

When invoked:
  1. Check existing state - Does CLAUDE.md/AGENTS.md exist? Does it have a 
    <!-- Generated by skill-integrator
    section? Count installed vs documented skills.
  2. Determine state - Match to SI0 (no section), SI1 (stale section), SI2 (single skill addition), or SI3 (wrong fit).
  3. Run analyze-project.ts to detect project type, domains, and tech stack:
    bash
    deno run --allow-read scripts/analyze-project.ts --json
    Save output as project context.
  4. Run scan-skills.ts to inventory all installed skills:
    bash
    deno run --allow-read scripts/scan-skills.ts --json
    Or for single skill mode:
    bash
    deno run --allow-read scripts/scan-skills.ts --skill <name> --json
  5. Run generate-guidance.ts to produce the guidance section:
    bash
    deno run --allow-read scripts/generate-guidance.ts --project-context ctx.json --skills skills.json
    Or for single skill:
    bash
    deno run --allow-read scripts/generate-guidance.ts --skill <name> --project-context ctx.json --skills skills.json
  6. Review and refine - The scripts produce structured data; use your judgment to:
    • Adjust trigger descriptions to be project-specific
    • Verify trigger category assignments make sense
    • Ensure descriptions answer "when should I use this?" not "what does this do?"
  7. Present to user - Show the generated guidance section. Apply on approval by inserting/replacing the marked section in CLAUDE.md or AGENTS.md.
被调用时：
  1. 检查现有状态 - 项目中是否存在CLAUDE.md/AGENTS.md文件？文件中是否包含
    <!-- Generated by skill-integrator
    标记？统计已安装技能与文档中记录的技能数量是否一致。
  2. 判定状态 - 匹配SI0（无指南章节）、SI1（章节过时）、SI2（新增单个技能）或SI3（适配不当）状态。
  3. 运行analyze-project.ts 检测项目类型、业务领域和技术栈：
    bash
    deno run --allow-read scripts/analyze-project.ts --json
    将输出保存为项目上下文文件。
  4. 运行scan-skills.ts 统计所有已安装技能：
    bash
    deno run --allow-read scripts/scan-skills.ts --json
    单技能模式下运行：
    bash
    deno run --allow-read scripts/scan-skills.ts --skill <name> --json
  5. 运行generate-guidance.ts 生成指南章节：
    bash
    deno run --allow-read scripts/generate-guidance.ts --project-context ctx.json --skills skills.json
    单技能模式下运行：
    bash
    deno run --allow-read scripts/generate-guidance.ts --skill <name> --project-context ctx.json --skills skills.json
  6. 审核与优化 - 脚本会生成结构化数据，你需要根据判断进行以下操作：
    • 调整触发场景描述，使其贴合项目实际
    • 验证触发场景分类是否合理
    • 确保描述回答的是“何时使用该技能？”而非“该技能有什么功能？”
  7. 提交给用户 - 展示生成的指南章节，经用户批准后，插入/替换CLAUDE.md或AGENTS.md中标记的章节。

Two Modes

两种模式

All-Skills Mode (default)

全技能模式（默认）

Invoked with 
/skill-integrator
or when diagnosing SI0/SI1.
  • Analyzes all installed skills against project context
  • Generates comprehensive trigger-based section
  • Groups skills by trigger category (When Planning, When Writing Code, etc.)
  • Only includes skills scoring >= threshold (default 0.3)
通过
/skill-integrator
调用，或诊断为SI0/SI1状态时触发。
  • 基于项目上下文分析所有已安装技能
  • 生成全面的、基于触发场景的指南章节
  • 按触发场景分类（规划时、编写代码时等）对技能进行分组
  • 仅包含相关性评分≥阈值的技能（默认阈值为0.3）

Single-Skill Mode

单技能模式

Invoked with 
/skill-integrator <skill-name>
or when diagnosing SI2.
  • Analyzes one specific skill against project context
  • Generates a single guidance line with placement recommendation
  • Shows scoring breakdown for transparency
通过
/skill-integrator <skill-name>
调用，或诊断为SI2状态时触发。
  • 基于项目上下文分析指定的单个技能
  • 生成单条指南内容并推荐插入位置
  • 展示评分明细以保证透明度

Available Tools

可用工具

analyze-project.ts

analyze-project.ts

Detects project type from indicator files, file extensions, and installed skills.
bash
deno run --allow-read scripts/analyze-project.ts
deno run --allow-read scripts/analyze-project.ts --path /some/project
deno run --allow-read scripts/analyze-project.ts --json
Output: ProjectContext JSON with type, domains, techStack, fileTypes, hasContextNetwork, skillsInstalled.
通过标记文件、文件扩展名和已安装技能检测项目类型。
bash
deno run --allow-read scripts/analyze-project.ts
deno run --allow-read scripts/analyze-project.ts --path /some/project
deno run --allow-read scripts/analyze-project.ts --json
输出： 包含type、domains、techStack、fileTypes、hasContextNetwork、skillsInstalled字段的ProjectContext JSON数据。

scan-skills.ts

scan-skills.ts

Parses all installed skill SKILL.md files and extracts metadata.
bash
deno run --allow-read scripts/scan-skills.ts
deno run --allow-read scripts/scan-skills.ts --skill code-review
deno run --allow-read scripts/scan-skills.ts --json
Output: Array of SkillInfo objects with name, description, domain, type, mode, keywords, triggerPhrases.
解析所有已安装技能的SKILL.md文件，提取元数据。
bash
deno run --allow-read scripts/scan-skills.ts
deno run --allow-read scripts/scan-skills.ts --skill code-review
deno run --allow-read scripts/scan-skills.ts --json
输出： SkillInfo对象数组，包含name、description、domain、type、mode、keywords、triggerPhrases字段。

generate-guidance.ts

generate-guidance.ts

Scores skills for relevance and generates formatted guidance.
bash
deno run --allow-read scripts/generate-guidance.ts --project-context ctx.json --skills skills.json
deno run --allow-read scripts/generate-guidance.ts --format trigger --threshold 0.3 --project-context ctx.json --skills skills.json
deno run --allow-read scripts/generate-guidance.ts --skill code-review --project-context ctx.json --skills skills.json
deno run --allow-read scripts/generate-guidance.ts --format table --json --project-context ctx.json --skills skills.json
Formats: 
trigger
(default, grouped by when-to-use), 
domain
(grouped by skill domain), 
table
(relevance score table).
为技能进行相关性评分并生成格式化的指南内容。
bash
deno run --allow-read scripts/generate-guidance.ts --project-context ctx.json --skills skills.json
deno run --allow-read scripts/generate-guidance.ts --format trigger --threshold 0.3 --project-context ctx.json --skills skills.json
deno run --allow-read scripts/generate-guidance.ts --skill code-review --project-context ctx.json --skills skills.json
deno run --allow-read scripts/generate-guidance.ts --format table --json --project-context ctx.json --skills skills.json
格式： 
trigger
（默认，按使用时机分组）、
domain
（按技能领域分组）、
table
（相关性评分表格）。

Key Questions

关键问题

For Initial Integration (SI0)

首次集成（SI0）

  • How many skills are installed?
  • What is the primary project type?
  • Does CLAUDE.md already exist, or does it need to be created?
  • Are there project-specific trigger contexts beyond the defaults?
  • 已安装多少技能？
  • 项目的主要类型是什么？
  • CLAUDE.md是否已存在，还是需要创建？
  • 除默认场景外，是否有项目特定的触发场景？

For Updates (SI1, SI2)

更新操作（SI1、SI2）

  • Which skills changed since last integration?
  • Has the project type or tech stack changed?
  • Are existing trigger descriptions still accurate?
  • 自上次集成后，哪些技能发生了变化？
  • 项目类型或技术栈是否发生变化？
  • 现有触发场景描述是否仍然准确？

For Quality (SI3)

质量优化（SI3）

  • Are agents actually using the guided skills?
  • Are trigger descriptions actionable or just descriptive?
  • Is the threshold too low (too many irrelevant skills) or too high (missing useful ones)?
  • Agent是否真的在使用指南中推荐的技能？
  • 触发场景描述是否具备可操作性，还是仅为说明性内容？
  • 阈值设置是否过低（导致无关技能过多）或过高（遗漏有用技能）？

Anti-Patterns

反模式

The Skill Dump

技能堆砌

Pattern: Listing all installed skills regardless of relevance. Problem: Information overload. Agents can't distinguish useful from irrelevant. Guidance becomes noise. Fix: Use threshold-based scoring. Only include skills with relevance >= 0.3. Quality over quantity. Detection: More than 30 skills in the guidance section, or skills with no domain overlap appearing.
表现： 不考虑相关性，列出所有已安装技能。 问题： 信息过载，Agent无法区分有用和无关技能，指南沦为噪音。 解决方法： 使用基于阈值的评分机制，仅包含相关性≥0.3的技能，重质不重量。 检测方式： 指南章节中技能数量超过30个，或出现与项目领域无重叠的技能。

The Feature Echo

功能重复

Pattern: Duplicating SKILL.md descriptions verbatim in the guidance. Problem: Descriptions answer "what does this do?" instead of "when should I use this?" Agents need trigger context, not feature lists. Fix: Transform descriptions into trigger-based guidance. "Use when [situation]" not "This skill [capability]." Detection: Guidance text matches SKILL.md description word-for-word.
表现： 直接复制SKILL.md中的描述作为指南内容。 问题： 描述回答的是“该技能有什么功能？”而非“何时使用该技能？”，Agent需要的是触发上下文，而非功能列表。 解决方法： 将描述转化为基于触发场景的指南内容，使用“当[场景]时使用”而非“该技能具备[功能]”的表述。 检测方式： 指南文本与SKILL.md中的描述完全一致。

The Static Guide

静态指南

Pattern: Generating guidance once and never updating after adding/removing skills. Problem: Guidance becomes stale. New skills go unused. Removed skills cause confusion. Fix: Re-run skill-integrator after any skill installation. Use the timestamp comment to track freshness. Detection: Timestamp in 
<!-- Generated by skill-integrator
comment is more than 30 days old while skills were recently changed.
表现： 生成一次指南后，添加/移除技能时不再更新。 问题： 指南内容过时，新技能无法被使用，已移除的技能会造成混淆。 解决方法： 每次安装技能后重新运行skill-integrator，使用时间戳注释跟踪内容新鲜度。 检测方式： 
<!-- Generated by skill-integrator
注释中的时间戳距今超过30天，且期间技能有过变更。

Example Interaction

交互示例

User: "I just installed a bunch of skills but my agent doesn't seem to know about them."
Your approach:
  1. Identify State SI0 (no guidance section in CLAUDE.md)
  2. Run 
    analyze-project.ts --json
    to detect project type
  3. Run 
    scan-skills.ts --json
    to inventory installed skills
  4. Run 
    generate-guidance.ts
    with project context and skills data
  5. Review output, adjust descriptions for project context
  6. Present trigger-based guidance section to user
  7. On approval, insert into CLAUDE.md with timestamped markers
User: "/skill-integrator code-review"
Your approach:
  1. Identify State SI2 (single skill addition)
  2. Run 
    scan-skills.ts --skill code-review --json
  3. Run 
    analyze-project.ts --json
    for context
  4. Run 
    generate-guidance.ts --skill code-review
    for targeted scoring
  5. Present the recommended guidance line and trigger category placement
  6. On approval, insert into the existing guidance section
用户：“我刚安装了一批技能，但我的Agent似乎不知道它们的存在。”
处理步骤：
  1. 判定为SI0状态（CLAUDE.md中无指南章节）
  2. 运行
    analyze-project.ts --json
    检测项目类型
  3. 运行
    scan-skills.ts --json
    统计已安装技能
  4. 结合项目上下文和技能数据运行
    generate-guidance.ts
  5. 审核输出内容，调整描述使其贴合项目上下文
  6. 将基于触发场景的指南章节提交给用户
  7. 经用户批准后，插入到CLAUDE.md中并添加时间戳标记
用户：
/skill-integrator code-review
处理步骤：
  1. 判定为SI2状态（新增单个技能）
  2. 运行
    scan-skills.ts --skill code-review --json
  3. 运行
    analyze-project.ts --json
    获取项目上下文
  4. 运行
    generate-guidance.ts --skill code-review
    进行针对性评分
  5. 提交推荐的指南内容和触发场景分类
  6. 经用户批准后，插入到现有指南章节的对应位置

What You Do NOT Do

禁止操作

  • You do not rewrite SKILL.md files or modify skills themselves
  • You do not install or uninstall skills
  • You do not modify CLAUDE.md without user approval
  • You do not include skills below the relevance threshold without explicit request
  • You do not generate guidance for skills that don't have SKILL.md files
  • You diagnose and generate; the user decides what goes into their config
  • 不得重写SKILL.md文件或修改技能本身
  • 不得安装或卸载技能
  • 未经用户批准不得修改CLAUDE.md
  • 未经明确请求，不得包含相关性评分低于阈值的技能
  • 不得为没有SKILL.md文件的技能生成指南
  • 仅负责诊断和生成内容，由用户决定是否将其添加到配置中

Integration Graph

集成关系图

Inbound (From Other Skills)

入站（来自其他技能）

Source SkillSource StateLeads to State
skill-builderAfter creating a new skillSI2: Single Skill Addition
find-skillsAfter installing a skillSI2: Single Skill Addition
来源技能来源状态目标状态
skill-builder创建新技能后SI2：新增单个技能
find-skills安装技能后SI2：新增单个技能

Outbound (To Other Skills)

出站（到其他技能）

This StateLeads to SkillTarget State
SI3: Wrong Fitskill-builderQuality issues found during analysis
当前状态关联技能目标状态
SI3：适配不当skill-builder分析过程中发现质量问题

Complementary Skills

互补技能

SkillRelationship
context-networkGuidance section lives in CLAUDE.md which context-network also manages
agent-bootstrapNew project setup benefits from immediate skill integration
skill-builderAfter building a skill, integrate it into project guidance
find-skillsAfter discovering and installing skills, surface them via guidance
技能关系
context-network指南章节存储在CLAUDE.md中，该文件同时由context-network管理
agent-bootstrap新项目搭建时，即时的技能集成会带来帮助
skill-builder技能创建完成后，将其整合到项目指南中
find-skills发现并安装技能后，通过指南呈现这些技能

Reasoning Requirements

推理要求

Standard Reasoning

标准推理

  • Running scripts and interpreting output
  • Matching skills to trigger categories
  • Basic state identification (SI0-SI3)
  • 运行脚本并解读输出
  • 将技能与触发场景分类匹配
  • 基础状态识别（SI0-SI3）

Extended Reasoning (ultrathink)

扩展推理（深度思考）

Use extended thinking for:
  • Customizing trigger descriptions to project-specific contexts - [Why: requires understanding both skill capability and project needs]
  • Evaluating threshold adjustments when many skills are borderline - [Why: trade-off analysis between coverage and noise]
  • Resolving SI3 wrong-fit situations - [Why: requires reasoning about why current categorizations fail]
Trigger phrases: "customize guidance", "refine triggers", "adjust threshold"
以下场景需使用扩展思考：
  • 针对项目特定上下文自定义触发场景描述 - [原因：需要同时理解技能能力和项目需求]
  • 当大量技能处于相关性阈值边缘时，评估阈值调整方案 - [原因：需要在覆盖范围和信息噪音之间进行权衡分析]
  • 解决SI3状态下的适配不当问题 - [原因：需要推理当前分类失效的原因]
触发短语： "customize guidance", "refine triggers", "adjust threshold"

Execution Strategy

执行策略

Sequential (Default)

顺序执行（默认）

  • analyze-project.ts must complete before generate-guidance.ts
  • scan-skills.ts must complete before generate-guidance.ts
  • State identification before running pipeline
  • analyze-project.ts必须在generate-guidance.ts之前完成
  • scan-skills.ts必须在generate-guidance.ts之前完成
  • 先识别状态，再运行流程

Parallelizable

可并行执行

  • analyze-project.ts and scan-skills.ts can run concurrently
  • Multiple single-skill scans can run concurrently
  • analyze-project.ts和scan-skills.ts可同时运行
  • 多个单技能扫描任务可同时运行

Subagent Candidates

候选子Agent

TaskAgent TypeWhen to Spawn
Project analysisBashRunning analyze-project.ts
Skill scanningBashRunning scan-skills.ts (especially for 100+ skills)
任务Agent类型触发时机
项目分析Bash运行analyze-project.ts时
技能扫描Bash运行scan-skills.ts时（尤其是技能数量超过100个时）

Context Management

上下文管理

Approximate Token Footprint

预估Token占用

  • Skill base: ~3k tokens
  • With script outputs inline: ~6k tokens
  • With full skill inventory (100+ skills): ~15k tokens (write to file, don't inline)
  • 技能基础内容： ~3k tokens
  • 包含脚本输出内容： ~6k tokens
  • 包含完整技能清单（100+技能）： ~15k tokens（写入文件，不嵌入上下文）

Context Optimization

上下文优化

  • Always write script JSON output to temporary files rather than inlining
  • Reference skills by name rather than embedding full metadata
  • Use 
    --json
    output mode for scripts, only inline the final guidance markdown
  • 始终将脚本的JSON输出写入临时文件，而非嵌入上下文
  • 通过名称引用技能，而非嵌入完整元数据
  • 脚本使用
    --json
    输出模式，仅将最终的指南Markdown内容嵌入上下文

When Context Gets Tight

上下文紧张时的处理

  • Prioritize: Current state diagnosis and generated guidance output
  • Defer: Full skill inventory details, scoring breakdowns
  • Drop: Raw project file type counts, individual skill metadata
  • 优先保留：当前状态诊断结果和生成的指南输出
  • 延后处理：完整技能清单明细、评分 breakdown
  • 舍弃：原始项目文件类型统计、单个技能的元数据

Output Persistence

输出持久化

Output Discovery

输出发现

Before doing any other work:
  1. Check if CLAUDE.md exists in the project root
  2. Check if it already has a 
    <!-- Generated by skill-integrator
    section
  3. If CLAUDE.md doesn't exist, ask the user where to place the guidance
在执行任何操作前：
  1. 检查项目根目录是否存在CLAUDE.md
  2. 检查文件中是否已存在
    <!-- Generated by skill-integrator
    章节
  3. 如果CLAUDE.md不存在，询问用户指南的存放位置

Primary Output

主要输出

For this skill, persist:
  • Guidance section - The trigger-based markdown inserted into CLAUDE.md/AGENTS.md
  • Timestamp marker - HTML comment marking the section for surgical updates
本技能需持久化以下内容：
  • 指南章节 - 插入到CLAUDE.md或AGENTS.md中的、基于触发场景的Markdown内容
  • 时间戳标记 - HTML注释，用于标记章节以便精准更新

Conversation vs. File

对话内容与文件内容划分

Goes to FileStays in Conversation
Trigger-based guidance sectionScoring breakdown and reasoning
Timestamp markersState diagnosis discussion
CLAUDE.md updatesThreshold adjustment discussion
写入文件保留在对话中
基于触发场景的指南章节评分 breakdown 和推理过程
时间戳标记状态诊断讨论内容
CLAUDE.md更新内容阈值调整讨论内容

File Naming

文件命名规则

Pattern: Inserted section within existing CLAUDE.md or AGENTS.md Markers: 
<!-- Generated by skill-integrator | Last updated: YYYY-MM-DD -->
格式：插入到现有CLAUDE.md或AGENTS.md中的指定章节 标记：
<!-- Generated by skill-integrator | Last updated: YYYY-MM-DD -->