Skill Effectiveness Auditor
SkillDev toolsReviews whether a skill will trigger reliably, guide useful behavior, avoid overlap, and produce testable outcomes.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Skill Effectiveness Auditor skill
What this skill tells your AI
The instructions your AI receives, as published by archieindian/openclaw-superpowers in skills/core/skill-effectiveness-auditor/SKILL.md and read by ahel’s review.
Structural validation proves a skill can load. Effectiveness review asks whether the agent will use it well. Use this skill when reviewing a new skill, improving an existing skill, or deciding whether a proposed skill belongs in the library.
When to Use
- A skill passes format checks but may still be vague or redundant
- A contributor proposes a new skill
- A skill is not triggering when expected
- A skill seems too broad, too long, or hard to verify
Audit Process
-
State the intended behavior.
- Write one sentence describing what the skill should make the agent do.
- List 3 user prompts that should trigger it.
- List 2 prompts that should not trigger it.
-
Check trigger clarity.
- The frontmatter description should name the task and the trigger.
- Avoid generic descriptions such as "helps with quality" or "improves workflow".
- Prefer concrete verbs: reviews, validates, scans, plans, records, summarizes.
-
Simulate agent use.
- Walk through the skill as if responding to a real prompt.
- Note any step where the agent must guess policy, inputs, output format, or stopping conditions.
- Flag steps that say "think about" without telling the agent what to produce.
-
Check overlap.
- Compare with nearby skills before approving a new one.
- If overlap is mostly structural, merge or reference the existing skill.
- If the new skill owns a distinct trigger, state that difference clearly.
-
Check testability.
- The output should show whether the skill was followed.
- Add verification criteria for high-risk workflows.
- For stateful skills, require
STATE_SCHEMA.yamlrather than prose-only memory.
Verdicts
Use one verdict:
keep- clear trigger, useful behavior, low overlaprevise- useful idea with fixable trigger or process gapssplit- too broad for one skillremove- duplicated, vague, or not a skill-level behavior
Output
Return:
- Verdict
- Trigger assessment
- Actionability issues
- Overlap risks
- Suggested frontmatter rewrite
- Required edits before merge
Signals
- GitHub stars
- 72
- Forks
- 14
- Last commit
- May 2026
Advanced
- Item type
- skill
- Key
skill-effectiveness-auditor- Source
- github.com/archieindian/openclaw-superpowers
github.com/archieindian/openclaw-superpowers