💻 Developer Tools

eval-skills

Name: eval-skills
Author: dzhng

by dzhng16 days ago622

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expected outcome, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus example input→expected-output pairs. Pairs with [write-skills](../write-skills/SKILL.md) (the authoring principles every fix obeys).

Install

npx skills add https://github.com/dzhng/skills --skill eval-skills

Show step-by-step

1
Open your terminal
- Mac: Press ⌘ Space, type "Terminal", press Enter
- Windows: Press Win R, type "cmd", press Enter
2
Paste the command above and press Enter
Use the Copy command button, then paste in your terminal (Mac: ⌘V, Windows: Ctrl V).
3
Restart Claude Code
Close and reopen Claude Code, or start a new session, so it picks up the new skill.

Where it lives

~/.claude/skills/dzhng--skills--skills--authoring--eval-skills/
├── SKILL.md
└── ... (skill resource files)

View on GitHub

Comments

X@dzhng

"Fable then eval-hardened the skill via my eval-skills skill It blind ran on Opus against fixture codebases with planted landmines, graded by a separate judge..."

Related skills

✍️ Writing

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

by obra · 13 days ago258.6k

📦 Product

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

by obra · 13 days ago258.6k

🎨 Design

p5js

p5.js sketches: gen art, shaders, interactive, 3D.

by NousResearch · 2 months ago218.2k

💻 Developer Tools

grill-me

A relentless interview to sharpen a plan or design.

by mattpocock · 3 months ago179.9k