Agent skill
skill-development
Use when the user wants to create or refine Codex skills, improve skill descriptions, organize skill resources, or follow Codex skill best practices.
Install this agent skill to your Project
npx add-skill https://github.com/troykelly/codex-skills/tree/main/external/skills/skill-development
SKILL.md
Skill Development (Codex)
This skill provides guidance for creating effective Codex skills and aligning with current Codex CLI conventions.
What Skills Are
Skills are modular packages that give Codex reusable workflows, domain knowledge, and tooling. Codex uses a skill in two ways:
- Implicit invocation: Codex selects a skill when the user's request matches its description.
- Explicit invocation: The user mentions
$skill-name(or uses the/skillspicker in supported clients).
Where to Save Skills (Codex Scopes)
Codex loads skills from these locations, in precedence order (highest to lowest):
$CWD/.codex/skills$CWD/../.codex/skills(if inside a git repo)$REPO_ROOT/.codex/skills(git repo root)$CODEX_HOME/skills(default~/.codex/skills)/etc/codex/skills
Notes:
- Higher-precedence skills override lower-precedence ones with the same name.
- Codex ignores symlinked skill directories.
Skill Structure
skill-name/
├── SKILL.md (required)
├── scripts/ (optional)
├── references/ (optional)
└── assets/ (optional)
SKILL.md Requirements
SKILL.md must include YAML frontmatter with:
name: non-empty, <= 100 characters, single linedescription: non-empty, <= 500 characters, single line
Extra keys are ignored by Codex.
Example:
---
name: draft-commit-message
description: Draft a conventional commit message when the user asks for help writing a commit message.
---
Creation Workflow
-
Clarify triggers Define concrete user phrases that should activate the skill. Keep the description specific.
-
Plan reusable resources Decide which scripts, references, or assets will save time. Prefer scripts for deterministic steps.
-
Create the skill folder Put it in a valid Codex skill path (see scopes above).
-
Write SKILL.md Keep it lean. Use imperative instructions and link out to references for detailed material.
-
Add references or scripts Store long docs in
references/and reusable code inscripts/. -
Restart Codex Codex loads skills at startup. Restart to pick up changes.
Best Practices
- Be explicit in descriptions so Codex can trigger correctly.
- Use progressive disclosure: keep SKILL.md short and move details into references.
- Avoid overlapping descriptions to prevent ambiguous triggers.
- Validate frontmatter length and single-line fields to avoid startup validation errors.
Related Resources
references/skill-creator-original.mdfor deeper guidance on structure and progressive disclosure
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
hook-development
Use when the user wants to create Codex workflow hooks (pre/post run gates, tool-use validators, stop checks) or needs guidance on hook scripts and hooks.json configuration.
sentry-setup-ai-monitoring
Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.
agent-development
Use when the user wants to design Codex agent equivalents (specialized workers/profiles/prompt files), define triggering conditions, or build reusable agent prompts and validation tools.
sentry-setup-logging
Setup Sentry Logging in any project. Use this when asked to add Sentry logs, enable structured logging, setup console log capture, or integrate logging with Sentry. Supports JavaScript, TypeScript, Python, Ruby, React, Next.js, and other frameworks.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
sentry-code-review
Analyze and resolve Sentry comments on GitHub Pull Requests. Use this when asked to review or fix issues identified by Sentry in PR comments. Can review specific PRs by number or automatically find recent PRs with Sentry feedback.
Didn't find tool you were looking for?