Allowed Dirs Skill

SkillAI & models

A skill with development directories that require --allow-dirs.

Available today. Use it from your connected AI after setup.

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 Allowed Dirs Skill skill

What this skill tells your AI

The instructions your AI receives, as published by agent-ecosystem/skill-validator in testdata/allowed-dirs-skill/SKILL.md and read by ahel’s review.

This skill demonstrates using non-standard directories alongside the standard skill structure. The evals/ and testing/ directories are development artifacts that require --allow-dirs to suppress warnings.

Usage

Follow the instructions in the reference guide to get started.

Run scripts/validate.sh to check your work.

Notes

The evals/ directory contains evaluation test cases and the testing/ directory contains integration test fixtures. Neither is part of the standard skill structure, but both are useful during development.

Signals

GitHub stars
251
Forks
30
Last commit
Sep 2026

ahel review

  • K6low
    bundled executables the agent is told to run

Automated review, not a security audit. Ruleset v1+k2.

Advanced
Item type
skill
Key
allowed-dirs-skill
Source
github.com/agent-ecosystem/skill-validator