Skip to main content
affpapa.org
RU EN
skill

skill-judge — Claude Code skill: review SKILL.md

This skill reviews SKILL.md files and skill packages against specifications and design practices. Use it to audit a skill and get suggestions for improvement.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --skill productivity/skill-judge
Open on GitHub

What skill-judge does

skill-judge assesses how much useful knowledge a skill adds beyond what the model already knows, and flags material that repeats familiar concepts. It also considers whether the instructions shape the model’s reasoning and include relevant domain procedures. The output includes scores across multiple dimensions and actionable suggestions.

Its evaluation draws on official specifications and patterns derived from skill examples. The described criteria include knowledge delta and the balance between thinking frameworks and procedures. This reviews skill design; it is not a test of whether your project code runs. Install it in Claude Code with npx claude-code-templates@latest --skill productivity/skill-judge.

What it helps with

  • audit a SKILL.md before publishing it
  • spot repeated explanations of basic concepts
  • check whether a skill adds expert knowledge
  • get concrete suggestions for improving a skill package

Example prompts for the agent

  • Audit SKILL.md for knowledge the model already has and suggest ways to improve it.
  • Review this skill package against design practices and flag redundant explanations.
  • Assess whether these instructions guide domain-specific reasoning and procedures.

How to install skill-judge

1claude-code-templates

npx claude-code-templates@latest --skill productivity/skill-judge

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill skill-judge -a claude-code

3Manually: put the files in place

~/.claude/skills/skill-judge/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-judge/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-judge

How do I install skill-judge in Claude Code?

Run npx claude-code-templates@latest --skill productivity/skill-judge to install the skill with claude-code-templates.

What does skill-judge do?

It evaluates the design of SKILL.md files and skill packages, provides scores across multiple dimensions, and suggests improvements.

What does skill-judge look for in a skill?

It considers whether the skill contributes knowledge beyond what the model already knows, and whether it guides reasoning and provides relevant domain procedures.

Similar skills

All skills for Agent setup: memory, context, orchestration →
setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set495

The whole set →
performance-profiling A Claude skill that keeps the agent on a fixed loop: measure, find the bottleneck, change one thing, confirm the result. Useful when a page drags. 132installs llm-app-patterns This skill outlines RAG designs and tool-using agent patterns. Consult it when planning document retrieval or choosing an agent architecture. 129installs linear-task-to-issue A slash command that turns a Linear task into a GitHub issue, carrying over fields, links, attachments and comments. Useful when planning lives in Linear and code lives in GitHub. 129installs bulk-import-issues A slash command that migrates GitHub issues into Linear in batches, with filtering by label or milestone and retries when a batch fails. 129installs telegram-mini-app Plan Telegram Mini Apps with guidance on the Web App API, TON Connect, payments, and Telegram user data. Useful when building a web app that runs inside Telegram. 128installs react-useeffect A skill that walks through React's useEffect rules from the official docs and points out what to use instead when an Effect is unnecessary. 127installs svelte-scaffold Builds out a new SvelteKit project, feature module or component library with a ready folder layout and config files. Handy when you want a starting point without wiring it by hand. 127installs pymoo Use this skill to work through Python optimization problems, from a single objective to competing goals. It helps when you need to compare trade-offs or account for constraints. 125installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor