OpenClaw

skill-reviewer

Review and audit agent skills (SKILL.md files) for quality, correctness, and effectiveness. Use when evaluating a skill before publishing, reviewing someone else's skill, scoring skill quality, identifying defects in skill content, or improving an existing skill.

gitgoodordietrying0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install gitgoodordietrying/skill-reviewer

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Skill Reviewer

Audit agent skills (SKILL.md files) for quality, correctness, and completeness. Provides a structured review framework with scoring rubric, defect checklists, and improvement recommendations.

When to Use

Reviewing a skill before publishing to the registry
Evaluating a skill you downloaded from the registry
Auditing your own skills for quality improvements
Comparing skills in the same category
Deciding whether a skill is worth installing

Review Process

Step 1: Structural Check

Verify the skill has the required structure. Read the file and check each item:

STRUCTURAL CHECKLIST:
[ ] Valid YAML frontmatter (opens and closes with ---)
[ ] `name` field present and is a valid slug (lowercase, hyphenated)
[ ] `description` field present and non-empty
[ ] `metadata` field present with valid JSON
[ ] `metadata.clawdbot.emoji` is a single emoji
[ ] `metadata.clawdbot.requires.anyBins` lists real CLI tools
[ ] Title heading (# Title) immediately after frontmatter
[ ] Summary paragraph after title
[ ] "When to Use" section present
[ ] At least 3 main content sections
[ ] "Tips" section present at the end

Step 2: Frontmatter Quality

Description field audit

The description is the most impactful field. Evaluate it against these criteria:

DESCRIPTION SCORING:

[2] Starts with what the skill does (active verb)
    GOOD: "Write Makefiles for any project type."
    BAD:  "This skill covers Makefiles."
    BAD:  "A comprehensive guide to Make."

[2] Includes trigger phrases ("Use when...")
    GOOD: "Use when setting up build automation, defining multi-target builds"
    BAD:  No trigger phrases at all

[2] Specific scope (mentions concrete tools, languages, or operations)
    GOOD: "SQLite/PostgreSQL/MySQL — schema design, queries, CTEs, window functions"
    BAD:  "Database stuff"

[1] Reasonable length (50-200 characters)
    TOO SHORT: "Make things" (no search surface)
    TOO LONG:  300+ characters (gets truncated...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/gitgoodordietrying/skill-reviewer
Version: —
Commit: 08859c9382fc90cff556881462e44085104b69f7
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Skill Reviewer

Audit agent skills (SKILL.md files) for quality, correctness, and completeness. Provides a structured review framework with scoring rubric, defect checklists, and improvement recommendations.

## When to Use

- Reviewing a skill before publishing to the registry
- Evaluating a skill you downloaded from the registry
- Auditing your own skills for quality improvements
- Comparing skills in the same category
- Deciding whether a skill is worth installing

## Review Process

### Step 1: Structural Check

Verify the skill has the required structure. Read the file and check each item:

```
STRUCTURAL CHECKLIST:
[ ] Valid YAML frontmatter (opens and closes with ---)
[ ] `name` field present and is a valid slug (lowercase, hyphenated)
[ ] `description` field present and non-empty
[ ] `metadata` field present with valid JSON
[ ] `metadata.clawdbot.emoji` is a single emoji
[ ] `metadata.clawdbot.requires.anyBins` lists real CLI tools
[ ] Title heading (# Title) immediately after frontmatter
[ ] Summary paragraph after title
[ ] "When to Use" section present
[ ] At least 3 main content sections
[ ] "Tips" section present at the end
```

### Step 2: Frontmatter Quality

#### Description field audit

The description is the most impactful field. Evaluate it against these criteria:

```
DESCRIPTION SCORING:

[2] Starts with what the skill does (active verb)
    GOOD: "Write Makefiles for any project type."
    BAD:  "This skill covers Makefiles."
    BAD:  "A comprehensive guide to Make."

[2] Includes trigger phrases ("Use when...")
    GOOD: "Use when setting up build automation, defining multi-target builds"
    BAD:  No trigger phrases at all

[2] Specific scope (mentions concrete tools, languages, or operations)
    GOOD: "SQLite/PostgreSQL/MySQL — schema design, queries, CTEs, window functions"
    BAD:  "Database stuff"

[1] Reasonable length (50-200 characters)
    TOO SHORT: "Make things" (no search surface)
    TOO LONG:  300+ characters (gets truncated...

搜索