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
release-gates.mdrules/
- name:
- release-gates
- description:
- Go/no-go checks for shipping skill updates safely
- metadata:
- {"tags":"release, quality-gates, governance, process"}
Release gates for skill changes
Required pass conditions
- No universal 0% criteria with skill enabled
- No negative delta on critical scenarios
- Benchmark run recorded with date, matrix, and deltas
- Follow-up issues opened for unresolved failures/regressions
Soft pass conditions
- At least one measurable gain on a target weak model
- No significant context-size increase without measured benefit
PR checklist
- Updated
SKILL.mdlinks for any new/renamed rule file - Added/updated benchmark run log entry
- Included validation command outputs (
test,typecheck,lint) - Linked tracking issues and remediation notes
Post-merge loop
- schedule rerun after next model update
- compare against prior run history
- prune stale guidance that no longer moves metrics