nm-abstract-skills-evalEvaluate Claude skill quality through auditing
Install via ClawdBot CLI:
clawdbot install athola/nm-abstract-skills-evalGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
post → https://blog.fsck.com/2025/12/17/claude-code-skills-not-triggering/Calls external URL not in known-safe list
https://github.com/athola/claude-night-market/tree/master/plugins/abstractUses known external API (expected, informational)
arxiv.orgAudited Apr 17, 2026 · audit v1.0
Generated May 6, 2026
A company deploying multiple AI assistants across customer service, sales, and support. They use the skills evaluator to regularly audit each assistant's skill definitions, ensuring they follow best practices for token efficiency and trigger reliability, reducing operational costs and improving response quality.
A SaaS provider offering AI-powered features. They integrate the skill auditor into their CI/CD pipeline to automatically review new skill contributions from developers, catching structural issues and deprecated patterns before deployment, maintaining high performance across all customer-facing AI features.
A large enterprise uses an internal AI knowledge base. The skills evaluator helps audit and improve the skill definitions that govern how the AI retrieves and summarizes information, leading to more accurate responses and lower token usage across thousands of daily queries.
A healthcare application integrates multiple AI tools for appointment scheduling, symptom checking, and patient follow-up. The evaluation framework ensures each tool's skill definition is optimized for reliability and compliance with healthcare regulations, minimizing errors and improving patient trust.
Offer ongoing skill auditing and optimization as a subscription service for companies using AI agents. Provide regular reports, automated compliance checks, and prioritized improvement plans.
Release the skill auditor as a free open-source tool with basic features, and charge for premium features like advanced analytics, priority support, and integration with popular CI/CD platforms.
Offer consulting services to help organizations develop and optimize their AI skills. Provide training workshops and certification programs on skill authoring best practices.
💬 Integration Tip
Integrate the skill auditor into your CI/CD pipeline to automatically audit new skill contributions on pull requests, ensuring quality before deployment.
Scored Jul 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.