Skylv Skill Quality Assurance

Analyzes and scores OpenClaw skill quality across 5 dimensions. Detects missing frontmatter, weak descriptions, poor examples, and actionable improvement rec...

Security Scan

The skill's code, documentation, and runtime instructions are internally consistent with its stated purpose of scoring SKILL.md files; nothing requests unrelated credentials or installs arbitrary code from the network.

Purpose & Capability

Name/description match the delivered artifacts: SKILL.md and a Node.js engine that reads SKILL.md/README.md files and scores them. No unexpected environment variables, binaries, or cloud credentials are requested.

Instruction Scope

SKILL.md instructs running node engine.js against a local skill path and the engine reads SKILL.md/README.md files in whatever directory you supply. SKILL.md mentions a companion auto-fix script (fix_skill_md.cjs) but that file is not present in the package — minor incoherence (documentation references non-existent helper).

Install Mechanism

No install spec is provided and there are no external downloads. The package is instruction-only plus a single local engine.js file and uses only built-in Node modules (fs, path). No network fetches or archive extraction are present.

Credentials

The skill requires no environment variables, credentials, or config paths. The engine operates on files under the user-specified target directory, which is appropriate for a documentation linter/QA tool.

Persistence & Privilege

always is false; the skill does not modify other skills or system-wide agent settings. It only reads local files and prints reports to stdout; no persistent agent changes or elevated privileges are requested.

Assessment

This skill appears coherent and safe to inspect/run. Before executing: (1) review engine.js locally (done here) and confirm you are comfortable running Node code; (2) note that the engine will read SKILL.md and README.md files in whatever directory you pass it — avoid pointing it at directories containing sensitive secrets or private keys; (3) SKILL.md refers to a fixer script (fix_skill_md.cjs) that's not included — don't expect an auto-fix capability unless you supply or review that script; (4) run the tool under an unprivileged account or inside a disposable container if you want extra caution. Confidence in this assessment is high given the provided files and lack of network or credential access.

Skill Quality Assurance

Automatically analyze and score OpenClaw skill documentation quality. Identifies critical issues and provides actionable fixes.

Overview

This skill runs a multi-dimensional quality analysis on any OpenClaw skill's SKILL.md file, scoring it across:

• Clarity — Structure, headings, sentence length
• Completeness — Required fields, install/usage sections
• Actionability — Step-by-step guides, commands
• Discoverability — Keywords, description, categories
• Examples — Code examples, before/after, use cases

Usage

Analyze a single skill

Analyze the skill at: C:\path\to\skills\my-skill

Analyze all skills in a directory

Run: node engine.js C:\path\to\skills

Interpretation

Score	Grade	Meaning
8-10	A	Production-ready
6-7	B	Needs minor improvements
4-5	C	Needs significant work
<4	F	Rewrite recommended

Scoring Dimensions

1. Clarity (20%)

Checks for: headings hierarchy, sentence length, filler words, markdown formatting

2. Completeness (20%)

Checks for: name, description, keywords, install section, usage section

3. Actionability (25%)

Checks for: numbered steps, runnable commands, configuration guides

4. Discoverability (15%)

Checks for: keywords (5+), description length (50+ chars), category/tags

5. Examples (20%)

Checks for: code blocks (3+), before/after cases, use case descriptions

Quality Thresholds

For ClawHub publication:

• Overall score ≥ 7.0 required
• No dimension below 5.0
• Must have keywords field
• Must have description ≥ 50 chars

Auto-Fix

The companion script fix_skill_md.cjs automatically fixes:

• Missing description field
• Missing keywords field
• Missing Install section
• Missing Usage section

node fix_skill_md.cjs

Example Output

# Skill Quality Report

Analyzed: 34 skills

## Overall Rankings
 1. ✅ skylv-browser-automation-agent   9.4/10
 2. ✅ skylv-openclaw-evomap-connector   9.3/10

Average score: 8.1/10
Grade A (7+): 29
Grade B (5-6): 5
Grade C (<5): 0

MIT License © SKY-lv