skill-evaluatorEvaluate Clawdbot skills for quality, reliability, and publish-readiness using a multi-framework rubric (ISO 25010, OpenSSF, Shneiderman, agent-specific heuristics). Use when asked to review, audit, evaluate, score, or assess a skill before publishing, or when checking skill quality. Runs automated structural checks and guides manual assessment across 25 criteria.
Install via ClawdBot CLI:
clawdbot install Terwox/skill-evaluatorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://www.npmjs.com/package/skilllensAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
A platform hosting third-party AI skills uses this evaluator to automatically screen submissions for quality and security before listing, ensuring only reliable, well-documented skills are published. It helps maintain trust by flagging issues like missing dependencies or poor error handling.
A company building internal AI agents for tasks like customer support or data analysis employs the evaluator to audit custom skills for compliance, reliability, and maintainability. It ensures skills meet organizational standards and reduces risks from faulty code.
An educational institution teaching AI development uses the evaluator as a grading tool for student projects, providing structured feedback across criteria like usability and security. It helps learners understand best practices in skill creation.
A community-driven repository for AI skills leverages the evaluator to review contributions, prioritize fixes based on P0/P1/P2 findings, and maintain a high-quality codebase. It automates checks for consistency and security vulnerabilities.
A regulated industry like finance or healthcare uses the evaluator to assess AI skills for adherence to standards such as data safety and error reporting, ensuring they meet legal and operational requirements before deployment.
Offer basic automated evaluations for free to attract users, then charge for detailed manual assessments, premium reports, or certification badges that skills can display on marketplaces. Revenue comes from subscription tiers for advanced features.
Sell licenses to large organizations for internal use, integrating the evaluator into their development pipelines. Provide customization, support, and compliance reporting as value-added services to generate steady revenue.
Partner with AI skill marketplaces to embed the evaluator as a mandatory pre-publishing tool, taking a percentage of transaction fees or charging per evaluation. This model leverages network effects and high usage volume.
💬 Integration Tip
Integrate the evaluator into CI/CD pipelines to automate checks on every skill update, and use the JSON output option for easy parsing in reporting tools.
Scored Apr 19, 2026
Dynamic goal-aware browsing assistant that generates checklists, evaluates page relevance, produces session wrap-ups, and persists all session data to the wo...
Creates a comfort-focused room airflow map, timing routine, and weekly review checklist for stuffy rooms without HVAC diagnosis, repair advice, allergy guida...
Create a 20-minute phone notification audit card for attention hygiene, without account, credential, surveillance, or monitoring setup.
Create a clinician-friendly migraine or recurring headache pattern log with episode timelines, possible context factors, symptom notes, medication response t...
Automate Karpak Life registration and SBT minting on the Karpak Living Map. Activate when user asks to register/mint an SBT.
Install, configure, authorize and run wakehook so the user's agent (OpenClaw or Hermes) runs their morning routine when they wake up. wakehook turns Google H...