SkillOptimizer

Approachability Audit

EpicenterHQ/epicenterSource at aa955da (opens GitHub)

32% lighter

Same results: 14 of 15 checks passed, original 14 of 15

16,838 tokens, was 24,913 across 1 task, 3 runs each

Check it yourself

SKILL.md keeps every line and gains one block at the end

What AIR found

  • VerifiedNo high-risk findings

    AIR's security review found nothing that needs a closer look. Reviewed Oct 1, 2026.

What changed

Original on GitHub
Files in the skill and how each changed
SKILL.mdNot in the original · Not in the lighter versionModified

Your original, with one block added at the end. Claude Code runs those commands once when the skill loads, so the agent starts with the files it always went looking for and spends no turns finding them.

Task by task

  • Auth types clarity32% lighter

    Original
    24,913 tokens
    Lighter version
    16,838 tokens
Tokens per task, the middle of 3 runs each, on one scale.

Measured in the prepared-facts study, Sep 26, 3 runs per task, graded blind. How we measured

Embed badge
SkillOptimizer result
Markdown
[![SkillOptimizer result](/badge/approachability-audit.svg)](/skills/approachability-audit)

HTML
<a href="/skills/approachability-audit"><img src="/badge/approachability-audit.svg" alt="SkillOptimizer result" /></a>