Skill Judge
This is a meta-skill that evaluates other skills against the official spec. It scores across dimensions like knowledge delta (does it teach Claude what it doesn't already know, or just waste tokens on basics?), mindset and procedures, and anti-pattern quality. The underlying philosophy is sharp: skills aren't tutorials, they're knowledge externalization mechanisms where good design means expert-only insights minus what Claude already has baked in. If you're building or reviewing skills and want to know whether you're actually adding value or just burning context window on "what is a for-loop" explanations, this gives you a rubric. The 120-point scoring system is thorough but opinionated, which is exactly what you want from a judge.
- skills.sh installs
- 134
- GitHub stars
- 25
- last updated
- Aug 21, 2026
Install
$ npx -y skills add gohypergiant/agent-skills --skill skill-judge --agent claude-codeInstalls into .claude/skills of the current project.
Files
This is a meta-skill that evaluates other skills against the official spec. It scores across dimensions like knowledge delta (does it teach Claude what it doesn't already know, or just waste tokens on basics?), mindset and procedures, and anti-pattern quality. The underlying philosophy is sharp: skills aren't tutorials, they're knowledge externalization mechanisms where good design means expert-only insights minus what Claude already has baked in. If you're building or reviewing skills and want to know whether you're actually adding value or just burning context window on "what is a for-loop" explanations, this gives you a rubric. The 120-point scoring system is thorough but opinionated, which is exactly what you want from a judge.
Browse the repository on GitHubSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/gohypergiant/agent-skills
- Categories
- Code Review & Quality, AI & Agent Building, Design & UI/UX
- First seen
- Jun 3, 2026
More from gohypergiant/agent-skills
All 14- Ask Questions If Underspecified132
- Accelint Nextjs Best Practices386
- Accelint Readme Writer386
- Accelint Ts Testing350
- Accelint Ts Performance347
- Accelint React Best Practices335
- Accelint Ts Best Practices334
- Accelint Security Best Practices323
- Accelint React Testing282
- Accelint Tanstack Query Best Practices279
- Accelint Ts Documentation263
- Accelint Skill Manager230
- Humanizer140
Recommended
More Code Review & Quality
self-reflectionninehills/skillsDaily self-reflection and personal growth. Triggered by heartbeat at end of day. Review the day's experiences, extract lessons, update personality, and write a 124skills.sh installs
rustpproenca/dot-skillsRust performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring Rust code to ensure optimal performance patterns. Tr124skills.sh installs
nanobanana-skillfeiskyer/codex-settingsGenerate, remix, or edit images with Nanobanana / Nano Banana 2 through the bundled Gemini CLI wrapper. Use this whenever the user wants AI image generation or 120skills.sh installs
design-system-managementanthropics/knowledge-work-pluginsManage design tokens, component libraries, and pattern documentation. Trigger with "design system", "component library", "design tokens", "style guide", or when118skills.sh installs
ln-647-env-config-auditorlevnikolaevich/claude-code-skillsChecks env var config sync, missing defaults, naming conventions, startup validation. Use when auditing environment configuration.116skills.sh installskiro-skillfeiskyer/codex-settingsInteractive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and implementation task lists. Use w115skills.sh installs