About skill-optimizer
A skill for evaluating and improving how reliably models apply other skills. It uses benchmark comparisons, failure analysis, targeted edits, and release gates to track behavior and regressions.
Key features
- 01Measures skill-on and baseline behavior
- 02Classifies failures and regressions
- 03Refines triggers and examples
- 04Compares evaluation results
- 05Defines release guardrails
Use cases
- 01Diagnosing criteria that models consistently miss
- 02Improving skill retrieval under context limits
- 03Checking whether a skill worsens outputs
- 04Setting evaluation gates for skill updates
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/skill-optimizerin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
tile.jsonrules/activation-design.mdbenchmark-loop.mdcontext-budget.mdregression-triage.mdrelease-gates.mdDetails
From the project READMEWhen 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)
- Measure baseline and skill-on behavior (per model, per scenario, per criterion)
- Find failure pattern:
- universal failure (0% with skill)
- model-specific weakness
- regression (negative delta)
- Edit for salience:
- add explicit triggers
- add concrete integrated examples
- tighten checklists and decision rules
- Re-run evals and compare deltas
- Ship with guardrails (documented gate + run history + follow-up issues)
How to use
Read individual rule files for detailed procedures and templates:
- rules/benchmark-loop.md - End-to-end benchmark loop and scoring
- rules/activation-design.md - Improve retrieval and instruction uptake
- rules/context-budget.md - Reduce token cost without losing behavior
- rules/regression-triage.md - Diagnose and fix skill-on regressions
- rules/release-gates.md - Go/no-go criteria before shipping skill updates
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
Comments
Markdown supported