Battle Test Skill
[!IMPORTANT] Deep audit of a skills directory against the Skill Creator standard. Produces a scored report and phased remediation plan.
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
Instructions
When the user asks to perform this workflow, execute the following steps:
⚔️ Battle Test Orchestrator
Goal: Evaluate every
SKILL.mdin the target directory againstcommon-skill-creator. Deliver a quantified health report and prioritized remediation plan.
Step 1 — Target Discovery & Tech Stack
Identify the tech stack and all skill files.
# Count total skills per category
find . -name "SKILL.md" | sed 's|/[^/]*/SKILL.md||' | sort | uniq -c
Step 2 — Frontmatter Audit (Breadth Scan)
Run scans to detect format and structure violations.
- Check for missing mandatory sections:
grep -rL "triggers:\|priority:\|Anti-Patterns" <SKILLS>/ - Check for broad glob triggers:
grep -r "src/\*\*" <SKILLS>/ - Check for length limits:
find . -name "SKILL.md" -exec awk 'END{if(NR>100) print FILENAME": "NR" lines"}' {} \;
Step 3 — Deep Audit & Evidence Classification
Evaluate skills against <SKILLS>/common/common-skill-creator/references/rubric.md:
- Structural Checks: Line count (≤100), frontmatter schema, surgical triggers.
- Textual Utility: Actionability, procedural clarity; verify NO answer-anchor padding.
- Executable Outcomes: Runnable verification commands, deterministic test/verifier pass.
- Rule Retirement & Ablation: Identify retirement candidates via repeated ablation; preserve safety controls until deterministic runtime replacements exist.
Step 4 — Scored Report
Scoring Algorithm: Start at 100 points for each category. Apply deductions for findings (🔴-15 / 🟠-8 / 🟡-3 / 🔵-1). Deduct for answer-anchor padding or bloated narrative.
📊 Report Format
Output the report using the Battle Test Report and Phased Plan templates in:
<SKILLS>/common/common-skill-creator/references/rubric.md when synced.
Step 5 — Interactive Follow-up
- "Generate a
task.mdfor Phase 1 remediation?" - "Fix the worst offender in [category] now?"
- "Deep-dive audit on a specific category (e.g.,
security)?"