Battle Test

If you're maintaining a skills directory and need to know where it's falling short of the Skill Creator standard, this runs a systematic audit across your entire collection. It scans frontmatter for structural issues, checks trigger patterns and file globs, then deep-dives a sample of skills against a formal rubric covering trigger accuracy, format quality, verification steps, and token efficiency. You get a scored report with point deductions per finding and a phased remediation plan. The orchestration is thorough but deliberate, walking through discovery, breadth scans, deep evaluation, and interactive follow-up options like generating task files or fixing the worst offenders immediately. Honestly feels like the kind of tooling you build when you've hit critical mass on skills and need to enforce consistency at scale.

GitHub stars: 504
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill battle-test --agent claude-code

Installs into .claude/skills of the current project.

Files

Battle Test Skill

[!IMPORTANT] Deep audit of a skills directory against the Skill Creator standard. Produces a scored report and phased remediation plan.

Instructions

When the user asks to perform this workflow, execute the following steps:

⚔️ Battle Test Orchestrator

Goal: Evaluate every SKILL.md in the target directory against common-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.

SKILL.md on GitHub

Details

Repository: github.com/hoangnguyen0403/agent-skills-standard
Categories: Testing & QA, AI & Agent Building, Productivity & Planning
License: Apache-2.0
First seen: Jun 11, 2026