CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/skill-optimizer

Optimize your skills and tiles: review SKILL.md quality, generate eval scenarios, run evals, compare across models, diagnose gaps, and re-run until scores improve.

86

1.22x
Quality

91%

Does it follow best practices?

Impact

86%

1.22x

Average score across 29 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-27/

{
  "context": "Activation-focused scenario: tests whether a multi-skill collision-diagnosis request activates a skill in this tile (expected: optimize-skill-performance Phase 0.4 or optimize-skill-instructions). Criteria below are placeholders for future content-eval use; activation eval ignores them.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Uses activation eval to surface collisions",
      "description": "Response identifies activation eval as the tool for surfacing per-scenario routing and uses its output to identify competing skill descriptions.",
      "max_score": 50
    },
    {
      "name": "Proposes description disambiguation",
      "description": "Response proposes concrete edits to separate trigger terms between competing skills (e.g., distinct verbs, distinct domain terms).",
      "max_score": 50
    }
  ]
}

evals

README.md

tile.json