Nima Skill Creator

PassAudited by ClawScan on May 1, 2026.

Overview

This looks like a coherent skill-building helper, but it can run local Python scripts that create, validate, and package persistent skill files, so users should confirm paths before use.

This skill appears safe for its stated purpose. Before using it, confirm where it will create files, avoid packaging folders that contain secrets or unrelated files, and review generated skills because they can affect future agent behavior.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Running the helper can add a new skill under the local Codex skills directory.

Why it was flagged

The skill explicitly tells the user or agent to run a bundled Python scaffolding script. This is central to the stated purpose, but it executes local code and creates persistent files.

Skill content
python3 scripts/init_skill.py my-skill --path "${CODEX_HOME:-$HOME/.codex}/skills" --resources scripts,references
Recommendation

Run the scripts only after confirming the target directory and review generated files before relying on the new skill.

What this means

If a user keeps unrelated or sensitive files inside the skill folder, they could be included in the local package archive.

Why it was flagged

The packaging helper archives files from the selected skill directory. This is expected for packaging, but it will include whatever non-ignored files are present there.

Skill content
for path in iter_files(skill_dir):
            zf.write(path, path.relative_to(skill_dir))
Recommendation

Before sharing or installing a packaged archive, inspect the skill directory and resulting zip contents for unintended files.