Audit AI agent skills for structural compliance and token efficiency.
npx skills add https://github.com/j-show/ai-everything --skill skill-review-j-show
Please help me install this Agent Skill. Skill: skill-review Source: https://github.com/j-show/ai-everything/tree/main/skills/skill-review Command: npx skills add https://github.com/j-show/ai-everything --skill skill-review-j-show
This skill solves the lack of systematic quality control for AI agent skills, preventing issues like vague instructions, bloated context, and ineffective workflows.
Run the skill review command on your target skill directory to receive a prioritized report of improvements.
High-intent search queries and answers about installing and using this skill.
To audit AI agent skills, you can run a five-dimensional review that evaluates structural compliance, description quality, workflow design, token efficiency, and anti-patterns to ensure high-quality model outputs.
Preventing vague instructions and bloated context requires systematic quality control that validates skill metadata, instruction clarity, and adherence to established anti-pattern guardrails before publishing.
You can check your plugin-based agent toolkit by running an automated audit that validates skill metadata and verifies adherence to established anti-pattern guardrails for structural compliance.
Yes, the skill review process provides actionable reporting with prioritized, specific fixes rather than generic feedback when it identifies workflow design or structural issues.
You need to run a token efficiency audit before publishing a new skill to ensure it follows best practices and provides a reliable, high-quality experience without bloated context.
An AI agent skill quality audit evaluates five dimensions: structure, description quality, workflow design, token efficiency, and adherence to anti-patterns to ensure actionable outputs.
bordenetValidate skill.md YAML frontmatter, line limits, and coordination metadata in skills/ repositories.
haryelramalhoValidate agent skill metadata and SKILL.md structure against compliance checklists.
Manvendra08Reduce token consumption and context overflow in LLM interactions.
Nairon-AIEvaluate review feedback against the codebase and tests before implementing changes.
