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
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
List concrete user/task signals near the top of the skill:
If behavior is frequently missed, move it into a numbered top-level checklist. Use imperative wording:
pipeline(...)"Refs: when requested"Add examples that combine multiple rules likely needed together in real tasks. A good integrated example:
Replace fuzzy phrasing:
With strict phrasing when correctness matters: