Learn Taste
Turn a session's design corrections into rules, with their why, in DESIGN.md, a project skill, or a lint check
Skillhawk's judgement
| Measure | Result |
|---|---|
| Grade | C (73/100) |
| Review findings | 2 (1 high, 0 medium, 1 low) |
| Security | No security findings |
| Size | about 2281 tokens, paid on every load |
| Licence | MIT |
| Source | https://github.com/emilkowalski/skills |
Top review findings
- high
SKILL.md:3[description-no-when] description does not say when to use the skill; agents decide to load a skill from its description alone - low
SKILL.md:76[vague-instruction] vague or hedging wording ("try to"): the model already does this, so it costs context and changes nothing
Install
npx skillhawk install @community/learn-taste --agent claude
Add -g to install for every project. Original source: emilkowalski/skills (MIT).