uinaf/skill-audit
Audit existing skills through a formal Tessl review or recent-task experiential feedback. Report recommendations for audit-only requests; make the smallest skill changes only when improvement or revision is explicitly requested.
95
98%
Does it follow best practices?
Impact
86%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
85%
10%Skill Audit: Onboarding Assistant Skill
Tessl run first
70%
80%
Correct single-skill command
0%
100%
Score reported
25%
12%
Tessl command reported
71%
100%
Strongest parts identified
100%
100%
Findings with file references
100%
100%
Blockers separated from polish
100%
88%
Smallest change set
100%
100%
Rerun status reported
87%
87%
Repo conventions loaded
100%
71%
Optimizer not invoked
100%
100%
Adjacent issues flagged separately
66%
77%
88%
-1%Skill Health Check: Release Coordinator
Rubric moved to references
100%
100%
Examples moved to references
100%
100%
Duplicate checklist removed
100%
100%
Frontmatter cleaned
22%
100%
References linked from SKILL.md
100%
100%
Tessl run before edits
100%
77%
Tessl rerun after edits
77%
44%
Before/after scores compared
75%
37%
Change reasons documented
100%
100%
SKILL.md remains workflow-focused
100%
100%
Optimizer not used
100%
100%
Scope respected
100%
100%
86%
-7%Skill Portfolio Review: Activation and Routing Problems
Tessl run per skill
100%
25%
Score per skill reported
100%
100%
Vague names flagged
37%
87%
Missing boundaries flagged
100%
100%
Third-person descriptions proposed
100%
100%
What and when in descriptions
100%
77%
Overlap boundary in descriptions
100%
100%
Misplaced code review content flagged
100%
100%
No skill invented
88%
55%
Evidence over taste
87%
87%
Optimizer not invoked
100%
100%
Scope respected
100%
100%
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6