Allowed Dirs Skill

SkillAI & models

Lets your agent organize extra dev folders like evals and tests inside a skill without triggering warnings.

Use Allowed Dirs Skill in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Allowed Dirs Skill and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Allowed Dirs Skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Allowed Dirs SkillStart free
About this skill

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

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
252
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