mcollina/skill-optimizer
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 and release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.
87
Quality
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Securityby
Passed
No known issues
context-budget.mdrules/
- name:
- context-budget
- description:
- Keep skills compact while preserving high-value behavior
- metadata:
- {"tags":"context, tokens, compression, relevance"}
Context budget optimization
Compression priorities
Keep:
- trigger lists
- decision tables
- short checklists
- one integrated example per high-value scenario
Trim:
- repeated background explanations
- duplicate examples with the same lesson
- low-signal prose that does not change behavior
Layering strategy
SKILL.md: high-signal overview, activation cues, linksrules/*.md: deeper procedures and examples
Only promote details to SKILL.md when repeated eval failures show they are being missed.
Budget checks
Before shipping a skill update, ask:
- Which added lines are behavior-critical?
- Could this section be expressed as a checklist/table?
- Does each example teach a unique failure mode?
Safe simplifications
- Convert paragraphs to bullet checklists
- Merge similar examples and annotate variants
- Move deep rationale into one explanation section and cross-link to it