nm-abstract-skills-evalEvaluate and improve Claude skill quality through auditing
Install via ClawdBot CLI:
clawdbot install athola/nm-abstract-skills-evalGrade Limited — 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 May 6, 2026
This skill produces a DESCRIPTIVE Git-history reflection report. It is intended ONLY for: (a) a developer running it on their own repository for self-reflect...
Connect to external services through Maton-managed API routes. Use this skill only after the user names the target app, account, and task. Start with read/li...
Ad intelligence & app analytics assistant. Search ad creatives, analyze apps, view rankings, track downloads/revenue, and get market insights. Get your API k...
Write and run tests across languages and frameworks. Use when setting up test suites, writing unit/integration/E2E tests, measuring coverage, mocking dependencies, or debugging test failures. Covers Node.js (Jest/Vitest), Python (pytest), Go, Rust, and Bash.
Tally API integration with managed OAuth. Manage forms, submissions, workspaces, webhooks, organization users, and organization invites. All write operations...
Build, debug, and deploy websites using HTML, CSS, JavaScript, and modern frameworks following production best practices.