agent-skill-evaluator
CommunityPre-flight safety checks for agent skills.
Software Engineering#security#github#risk-assessment#web-scraping#ai-safety#skill-evaluation#prompt-injection
Authorkentoku24
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Automatically evaluate the security, safety, and trustworthiness of agent skills from GitHub repositories, websites, or direct .skill URLs, and provide actionable risk scoring before installation.
Core Features & Use Cases
- Provenance analysis: Verify creator legitimacy, source credibility, and potential red flags.
- SKILL.md & code review: Inspect skill definitions, scripts, references, and assets for safety signals.
- External research & risk scoring: Aggregate community feedback and generate a final risk verdict with remediation guidance.
Quick Start
Provide a GitHub URL, website URL, or direct .skill link to initiate a security assessment.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agent-skill-evaluator Download link: https://github.com/kentoku24/project-guild/archive/main.zip#agent-skill-evaluator Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.