skill-quality-auditorEvaluate and score AgentSkills on design, content, security, and usability, producing a detailed numeric scorecard with improvement suggestions.
Install via ClawdBot CLI:
clawdbot install ann0501/skill-quality-auditorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
~/.aws/credentialsPotentially destructive shell commands in tool definitions
eval(Audited Apr 18, 2026 · audit v1.0
Generated May 7, 2026
Before publishing a new AgentSkill to a marketplace or team repository, an automated pipeline invokes the Skill Reviewer to score it across four dimensions. If the skill fails (REVISE), the pipeline blocks deployment and notifies the developer with a detailed report.
An enterprise evaluating third-party skills for integration uses the Skill Reviewer to generate scorecards for each candidate. The auditor flags security CRITICALS (e.g., scripts in assets/) and ensures each dimension meets internal thresholds before approval.
A skills team periodically runs the Skill Reviewer on their published skills to track quality trends. The output highlights declining dimensions (e.g., usability slipping below 6) and suggests targeted improvements based on referenced checklists.
Marketplace curators use the Skill Reviewer to assign official quality badges to submitted skills. A PASS with ≥8 total and no CRITICALS earns a verified badge, while REVISE skills are rejected with actionable feedback.
When onboarding new skills into a hackathon or internal challenge, organizers use the reviewer to ensure all submissions meet minimum quality. The scoring rubric is disclosed to participants beforehand to align expectations.
Offer the Skill Reviewer as a cloud plugin integrated with CI/CD tools (e.g., GitHub Actions). Teams pay per job run or monthly subscription for automated quality gates.
Partner with AI skill marketplaces to provide vetting services. Charge a per-skill fee for certification badges, either paid by developers submitting skills or by the marketplace.
Provide customized versions for large enterprises that need to audit internal skill repositories. Revenue from yearly contracts including dedicated support and compliance integration.
💬 Integration Tip
Wrap the Skill Reviewer in a simple CLI command that consumes a skill path and outputs the report JSON; integrate into CI via a GitHub Action or Jenkins plugin.
Scored Jun 20, 2026
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Comprehensive security auditing for Clawdbot deployments. Scans for exposed credentials, open ports, weak configs, and vulnerabilities. Auto-fix mode included.
Analyze and classify agent skills for safety using local evaluation. Optionally produce a signed attestation of the vetting result.
Audit codebases and infrastructure for security issues. Use when scanning dependencies for vulnerabilities, detecting hardcoded secrets, checking OWASP top 10 issues, verifying SSL/TLS, auditing file permissions, or reviewing code for injection and auth flaws.
Security engineering workflow for OpenClaw privilege governance and hardening. Use for least-privilege execution, approval-first privileged actions, idle tim...
Git 安全扫描器 - 检查提交中的敏感信息泄露（API keys、密码、token）