HomeJimu HarnessCommunityModelsResourcesDocumentationSkillAgentMCPTeamAbout us
Sign up / Sign in

Quick links

Jimu AI

Jimu AI — tools for building intelligent applications

Loading...
← Back to skills

skill-optimizer

v1.0.0
Matteo Collina

Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.

WorkflowsSkill优化Skill评测激活率元技能
↓ 3 downloads

name: skill-optimizer description: | Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience. author: Matteo Collina license: category: workflow tags: Skill优化, Skill评测, 激活率, 元技能 source: https://github.com/mcollina/skills/tree/main/skills/skill-optimizer

When to use

Use this skill when you need to:

  • Improve whether a skill is actually applied by models
  • Diagnose why some criteria fail across all models
  • Prevent a skill from making outputs worse
  • Refactor skill text for stronger retrieval under context pressure
  • Build repeatable benchmark loops and release gates

Optimization loop (default workflow)

  1. Measure baseline and skill-on behavior (per model, per scenario, per criterion)
  2. Find failure pattern:
    • universal failure (0% with skill)
    • model-specific weakness
    • regression (negative delta)
  3. Edit for salience:
    • add explicit triggers
    • add concrete integrated examples
    • tighten checklists and decision rules
  4. Re-run evals and compare deltas
  5. Ship with guardrails (documented gate + run history + follow-up issues)

How to use

Read individual rule files for detailed procedures and templates:

Practical heuristics

  • Prefer few high-signal rules over many soft recommendations
  • Put fragile, high-value behaviors in top-level checklists
  • Include at least one integrated example per common scenario
  • Add explicit wording for what must not be omitted
  • Track gains/losses with with-skill vs without-skill comparisons