Back to Details

skill-reviewer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill Reviewer

Skill Reviewer

审计 Claude Code skills 的质量和兼容性。作为编排器，委托已有工具处理结构/质量检查，自身专注兼容性审计。
Audit the quality and compatibility of Claude Code skills. As an orchestrator, it delegates existing tools to handle structure/quality checks, while focusing on compatibility audits itself.

Prerequisites

Prerequisites

ToolTypeRequiredInstall
writing-skillsskillNo
npx skills add https://github.com/obra/superpowers --skill writing-skills
(for deep quality audit)
Do NOT proactively verify these tools on skill load. If a command fails due to a missing tool, directly guide the user through installation and configuration step by step.
ToolTypeRequiredInstall
writing-skillsskillNo
npx skills add https://github.com/obra/superpowers --skill writing-skills
(for deep quality audit)
Do NOT proactively verify these tools on skill load. If a command fails due to a missing tool, directly guide the user through installation and configuration step by step.

审计流程

Audit Process

Step 1: 结构校验（委托）

Step 1: Structure Validation (Delegated)

运行 skill-reviewer 自带的校验脚本，汇总 YAML frontmatter、name 格式、description 格式等结果：
bash
bash <skill-reviewer-dir>/scripts/validate.sh
若脚本不可用（如未通过 npx skills 安装），手动检查每个 SKILL.md 的 YAML frontmatter：name（hyphen-case，≤64 字符）、description（无尖括号，≤1024 字符）。
Run the built-in validation script of skill-reviewer to compile results for YAML frontmatter, name format, description format, etc.:
bash
bash <skill-reviewer-dir>/scripts/validate.sh
If the script is unavailable (e.g., not installed via npx skills), manually check the YAML frontmatter of each SKILL.md file: name (hyphen-case, ≤64 characters), description (no angle brackets, ≤1024 characters).

Step 2: 内容质量（委托，推荐）

Step 2: Content Quality (Delegated, Recommended)

推荐执行：若已安装 
writing-skills
，调用该 skill 进行深度质量审查（token 效率、渐进式披露、反模式、TDD 方法论等）。
若未安装，提示用户可选安装：
bash
npx skills add https://github.com/obra/superpowers --skill writing-skills
跳过此步骤时应明确告知用户，避免静默省略。
Recommended Execution: If 
writing-skills
is installed, invoke this skill for in-depth quality review (covering token efficiency, progressive disclosure, anti-patterns, TDD methodology, etc.).
If not installed, prompt the user to optionally install it using:
bash
npx skills add https://github.com/obra/superpowers --skill writing-skills
If this step is skipped, clearly inform the user to avoid silent omission.

Step 3: 兼容性审计（自身核心）

Step 3: Compatibility Audit (Core Function)

按 
references/compatibility-checklist.md
逐项检查目标 skill 的所有文件（SKILL.md + scripts/ + references/）：
3a. 跨平台兼容性 — 扫描平台锁定模式（macOS-only 命令、Windows 不兼容项等）。
3b. 跨 Agent 兼容性 — 检测 Claude Code 专属工具引用和 MCP 依赖。
3c. npx skills 生态兼容性 — 校验 marketplace.json 注册、symlink 可用性、跨 skill 依赖。
3d. 工具引用规范 — 检查是否保留了 Claude Code 工具术语并提供了其他环境的 fallback 备注。详见 checklist 的 "Tool Reference Best Practices" 部分。
3e. Prerequisites 声明 — 检查 SKILL.md 是否声明了外部依赖：
  • 如果 skill 使用了外部 CLI 工具（
    git
    , 
    gh
    , 
    reminders-cli
    等）、MCP 服务器、或其他 skill，MUST 有 
    ## Prerequisites
    章节
  • Prerequisites 必须是 body 中第一个 
    ##
    章节
  • 章节内 MUST 包含 4 列表格：Tool / Type / Required / Install
  • Type 列 MUST 使用标准值：
    cli
    , 
    mcp
    , 
    skill
    , 
    system
  • 表格后 MUST 有被动检查说明（blockquote），明确要求在执行失败时直接引导用户完成安装配置，而非指向外部文档
  • 需要配置的工具（如 MCP 服务器、需要 auth 的 CLI）SHOULD 在 Install 列提供可执行的安装命令和配置步骤，或引用 skill 自带的 references/ 文档
  • 无外部依赖的 skill 不需要此章节
详见 
references/compatibility-checklist.md
。
Check all files of the target skill (SKILL.md + scripts/ + references/) item by item according to 
references/compatibility-checklist.md
:
3a. Cross-Platform Compatibility — Scan for platform-locked patterns (e.g., macOS-only commands, Windows incompatibilities, etc.).
3b. Cross-Agent Compatibility — Detect references to Claude Code-exclusive tools and MCP dependencies.
3c. npx Skills Ecosystem Compatibility — Validate marketplace.json registration, symlink availability, and cross-skill dependencies.
3d. Tool Reference Standards — Check if Claude Code tool terminology is retained and fallback notes for other environments are provided. Refer to the "Tool Reference Best Practices" section in the checklist for details.
3e. Prerequisites Declaration — Check if SKILL.md declares external dependencies:
  • If the skill uses external CLI tools (e.g., 
    git
    , 
    gh
    , 
    reminders-cli
    ), MCP servers, or other skills, it MUST include a 
    ## Prerequisites
    section
  • The Prerequisites section MUST be the first 
    ##
    section in the body
  • The section MUST include a 4-column table: Tool / Type / Required / Install
  • The Type column MUST use standard values: 
    cli
    , 
    mcp
    , 
    skill
    , 
    system
  • A passive check note (blockquote) MUST follow the table, clearly stating that if execution fails, the user should be guided through installation and configuration step by step instead of directing them to external documentation
  • For tools that require configuration (e.g., MCP servers, CLI tools requiring auth), the Install column SHOULD provide executable installation commands and configuration steps, or reference the documentation in the skill's built-in references/ directory
  • Skills with no external dependencies do not need this section
For details, see 
references/compatibility-checklist.md
.

Step 4: 输出报告

Step 4: Output Report

使用以下格式输出统一报告：
markdown
undefined
Output a unified report using the following format:
markdown
undefined

Skill Review: {skill-name}

Skill Review: {skill-name}

总览

Overview

维度状态方式
结构与元数据PASS / FAILvalidate.sh
内容质量建议使用 writing-skills委托
平台兼容性PASS / FAIL (N issues)自查
Agent 兼容性PASS / FAIL (N issues)自查
npx skills 生态PASS / FAIL (N issues)自查
Prerequisites 声明PASS / WARN / N/A自查
DimensionStatusMethod
Structure & MetadataPASS / FAILvalidate.sh
Content QualityRecommended to use writing-skillsDelegated
Platform CompatibilityPASS / FAIL (N issues)Self-checked
Agent CompatibilityPASS / FAIL (N issues)Self-checked
npx Skills EcosystemPASS / FAIL (N issues)Self-checked
Prerequisites DeclarationPASS / WARN / N/ASelf-checked

Critical

Critical

  • [维度] 问题描述 当前: ... 建议: ...
  • [Dimension] Issue description Current: ... Recommendation: ...

High

High

...
...

Medium / Low

Medium / Low

...

严重度分级：

- **Critical** — 功能不可用或分发失败，必须修复
- **High** — 显著影响可用范围，建议修复
- **Medium** — 可改进项，不影响核心功能
- **Low** — 建议性改进
...

Severity Levels:

- **Critical** — Functionality is unavailable or distribution fails; must be fixed
- **High** — Significantly affects usability scope; recommended to fix
- **Medium** — Improvement item; does not affect core functionality
- **Low** — Suggested improvement