skill-compassDiagnose, fix, and prevent agent skill trigger failures. Use when a skill doesn't activate, when skills trigger incorrectly, when troubleshooting "skill not working" issues, when auditing skill descriptions for quality, when optimizing trigger accuracy, or when asked "why didn't my skill fire?". Also use proactively after installing new skills or when agent behavior seems to ignore available skills. Covers description optimization, YAML frontmatter validation, token budget analysis, conflict detection, and auto-remediation.
Install via ClawdBot CLI:
clawdbot install krishna-505/skill-compassGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
${ANTHROPICSends data to undocumented external endpoint (potential exfiltration)
Report → https://github.com/Evol-ai/SkillCompass/security/advisories/newPotentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://github.com/Evol-ai/SkillCompassGenerated Apr 7, 2026
A marketplace platform for Claude skills uses SkillCompass to automatically evaluate all submitted skill packages before publication. The system runs /eval-audit on entire directories to batch assess quality, ensuring only skills with PASS scores (≥70) and no D3 security issues get listed. This prevents low-quality or insecure skills from reaching users while maintaining consistent quality standards.
A financial services company implements SkillCompass as part of their AI governance framework to audit custom Claude skills used by employees. The security team runs /eval-security scans regularly to detect vulnerabilities, while /eval-compare tracks version changes to ensure compliance with internal policies. This provides audit trails for regulatory requirements around AI tool usage.
A development team building Claude skills for internal use employs SkillCompass throughout their CI/CD pipeline. They use /eval-skill for quality gates on pull requests, /eval-improve for automated fixes during development, and /eval-evolve for continuous improvement cycles. This ensures skills maintain high quality while evolving to meet changing business needs.
An organization with dozens of Claude skills uses SkillCompass to identify redundant or obsolete skills. The /eval-compare command helps compare similar skills, while D6 uniqueness scoring identifies overlap. This enables rationalization of the skill portfolio, reducing maintenance costs while improving user experience through better skill differentiation.
A company evaluating third-party Claude skill vendors uses SkillCompass to objectively assess skill quality before procurement. They run /eval-skill with --scope full to get comprehensive evaluations across all six dimensions, comparing vendor offerings based on standardized metrics rather than marketing claims. This reduces procurement risk and ensures value for money.
Offer SkillCompass as a cloud-based service where organizations pay monthly/annual subscriptions based on usage volume. The platform provides web interface, API access, and integration with existing CI/CD tools. Revenue comes from tiered pricing based on number of skills evaluated, frequency of scans, and advanced features like /eval-evolve automation.
Sell perpetual licenses or annual enterprise agreements to large organizations needing on-premises deployment or extensive customization. This includes dedicated support, custom integration with internal systems, and training services. The model appeals to regulated industries or companies with strict data sovereignty requirements.
Integrate SkillCompass into existing AI skill marketplaces as a quality assurance layer. Revenue comes from taking a percentage of transactions for skills that pass evaluation or charging listing fees for verified skills. This creates a win-win where marketplaces improve quality while SkillCompass gains distribution.
💬 Integration Tip
Start with /eval-skill on existing skills to establish baselines, then implement /eval-audit in CI/CD pipelines for automated quality gates. Use the .skill-compass directory for version tracking without modifying original skill files.
Scored May 20, 2026
AI Analysis
The skill appears to be a legitimate evaluation tool for Claude skills with no evidence of active data exfiltration or credential harvesting. The GitHub URL references are consistent with its open-source nature, and while there are some concerning patterns like eval() usage, these appear to be part of its analysis functionality rather than malicious intent.
Audited Apr 16, 2026 · audit v1.0
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...