Personal Codex agent skills maintained by noobnooc.
This repository keeps each skill as a portable folder under skills/. A skill folder contains a SKILL.md entrypoint and, when useful, agent-specific metadata under agents/.
| Skill | Purpose |
|---|---|
wtf |
Pre-launch and pre-commit audits for fast-moving projects, focused on repository hygiene, secrets, environment variables, database readiness, deployment risks, dead code, and common AI-built app mistakes. |
better-codex |
A reliability overlay for Codex coding work: safer scope control, stale-edit prevention, dependency judgment, root-cause debugging, quality-first implementation, focused tests, and concise user updates. |
See skills/README.md for the catalog.
Clone the repository and copy the skills you want into the skills directory used by your agent.
git clone https://github.com/noobnooc/agent.git
cd agent
mkdir -p ~/.codex/skills
cp -R skills/wtf skills/better-codex ~/.codex/skills/For local development, symlink the skill folders instead of copying them:
mkdir -p ~/.codex/skills
ln -s "$(pwd)/skills/wtf" ~/.codex/skills/wtf
ln -s "$(pwd)/skills/better-codex" ~/.codex/skills/better-codexIf your agent reads skills from another directory, copy or symlink the same folders there.
Invoke a skill by name in a Codex prompt:
Use $wtf to audit this project before I commit or deploy it.
Use $better-codex to complete this coding task safely and concisely.
skills/
better-codex/
SKILL.md
agents/openai.yaml
wtf/
SKILL.md
agents/openai.yaml
When adding or changing a skill:
- Keep the trigger description in
SKILL.mdspecific enough that agents load it only when useful. - Keep
agents/openai.yamlshort and focused on display metadata and the default prompt. - Update
skills/README.mdwhen the catalog changes.