skills.rest
yaojingang
yaojingangCOMMUNITY
Explore all skills by this author →
Website𝕏@yaojingangGitHub

yao-interpreter-skill

Statically analyze Agent Skill packages and generate evidence-backed quality reports.

1.3k|146|Updated Apr 6, 2026
Search Tags:#static analysis#security review#skill evaluation#quality scoring#html report#prompt injection detection#Agent Skill
One-click install
npx skills add https://github.com/yaojingang/yao-open-skills --skill yao-interpreter-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: yao-interpreter-skill
Source: https://github.com/yaojingang/yao-open-skills/tree/main/skills/yao-interpreter-skill
Command: npx skills add https://github.com/yaojingang/yao-open-skills --skill yao-interpreter-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Evaluating whether a third-party or existing Agent Skill is safe and worth adopting is slow and error-prone, since manually reading every file, checking for risky commands, and judging structure quality takes significant effort. This Skill turns any local Skill directory, SKILL.md file, or zip archive into an evidence-backed quality interpretation report without ever executing the target's code.

Core Features & Use Cases

  • 100-Point Quality Scoring: Scores a target Skill across 9 dimensions (spec compatibility, trigger signal, context efficiency, structure, usage readiness, safety, tests, maintenance, learning value) with red-line downgrades for critical risks.
  • Static Safety Review: Scans for dangerous commands, network access, secret handling, prompt injection, and hidden characters, treating the target strictly as untrusted input and safely rejecting malicious zip archives.
  • Bilingual HTML Reports: Generates a Simplified Chinese HTML report with an in-page Chinese/English switch, plus analysis.json, findings.json, qa_report.json, and summary.md.
  • Use Case: Before adopting a third-party Agent Skill from a zip archive into your team, run the analyzer to get a score, risk level, evidence-linked findings, and an improvement roadmap for an informed adoption decision.

Quick Start

Ask the AI to statically analyze a local Skill directory or zip archive with this Skill and generate the Chinese HTML quality report with its 100-point score, risk review, and improvement roadmap.

Frequently Asked Questions about yao-interpreter-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate the quality of an Agent Skill before using it?▼

Run the analyzer CLI against the Skill directory to get a 100-point score across 9 dimensions, a risk level, and evidence-linked findings. The generated HTML report shows the score breakdown, safety review, and an improvement roadmap.

How to safely analyze a third-party Skill from a zip file?▼

Pass the zip archive directly to the analyze command. The tool rejects path traversal entries, oversized files, and suspicious symlinks, extracts to a temporary directory, and only reads files statically without executing any scripts.

Does this Skill execute the target Skill's scripts during analysis?▼

No. The target Skill is treated strictly as untrusted input. Its scripts, installers, tests, and prompts are never executed, its dependencies are never installed, and its files are never modified.

What output files does the Skill analysis report include?▼

It generates report.zh-CN.html with an in-page Chinese/English switch, analysis.json, findings.json, qa_report.json, and summary.md. An optional standalone report.en.html can be produced with the --lang zh-CN,en flag.

When should I not use this Skill for Skill evaluation?▼

Do not use it to create or refactor Skills, to run a target Skill and verify real task outcomes, or as a replacement for dedicated dependency vulnerability audits and runtime sandbox security testing.

Related Skills

Explore More Software Engineering Skills→
carydencaryden
1

propose-special-skill

Package a skill directory into a zip archive and create a GitHub issue proposing its inclusion.

Community
Intermediate
racciolyraccioly

docguard-score

Identifies and scores documentation and governance maturity using DocGuard CLI, outputting a categorized breakdown and improvement roadmap.

Community
Advanced
NY1024NY1024
25

auditor-skill

Audit OpenClaw agent skills for security vulnerabilities and malicious behavior.

Community
Advanced
koseki2580koseki2580

writing-skills

Create and edit Skill documentation using a RED-GREEN-REFACTOR workflow.

Community
Advanced