A curated list of practical Codex skills for automating workflows across the Codex CLI and API.
Awesome Codex Skills
A curated list of practical Codex skills for automating workflows across the Codex CLI and API.
Want skills that do more than generate text? Codex can send emails, create issues, post to Slack, and take actions across 1000+ apps. See how →
Quickstart: Add Skills to Codex
Install with the Skill Installer (recommended)
git clone https://github.com/ComposioHQ/awesome-codex-skills.git
cd awesome-codex-skills/awesome-codex-skills
# Install one or more skills into $CODEX_HOME/skills (defaults to ~/.codex/skills)
python skill-installer/scripts/install-skill-from-github.py --repo ComposioHQ/awesome-codex-skills --path meeting-notes-and-actions
The installer fetches the skill and places it in $CODEX_HOME/skills/<skill-name>. Restart Codex to pick up new skills.
Manual install
Copy the desired skill folder (e.g., ./spreadsheet-formula-helper) into $CODEX_HOME/skills/ (defaults to ~/.codex/skills/).
Restart Codex so it loads the new metadata.
In your next session, describe the task or mention the skill name; Codex will trigger matching skills based on their description frontmatter.
Contents
Bernstein - Multi-agent orchestrator with Codex CLI adapter. Runs parallel Codex agents in isolated git worktrees with quality gates.
Codex skills are modular instruction bundles that tell Codex how to execute a task the way you want it done. Each skill lives in its own folder with a SKILL.md that includes metadata (name + description) and step-by-step guidance. Codex reads the metadata to decide when to trigger a skill and loads the body only after it fires, keeping context lean.
Skills
Development & Code Tools
brooks-lint - AI code reviews grounded in six classic engineering books — decay risk diagnostics with book citations, severity labels, and four analysis modes (PR review, architecture audit, tech debt, test quality). Install: python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py --repo hyhmrright/brooks-lint --path skills/brooks-lint --name brooks-lint
codebase-migrate/ - Run large codebase migrations and multi-file refactors in reviewable batches with CI verification.
create-plan/ - Quickly draft concise execution plans for coding tasks.
deploy-pipeline/ - End-to-end Stripe → Supabase → Vercel release pipelines with verify and rollback.
support-ticket-triage/ - Triage customer support tickets with categories, priority, next actions, and draft replies.
file-organizer/ - Organize, rename, and tidy files to keep workspaces clean.
paperjsx/ - Generate PPTX presentations, DOCX documents, XLSX spreadsheets, and PDF invoices/reports/charts from structured JSON. Runs locally via @paperjsx/mcp-server — no API key, no network calls.
skill-share/ - Share skills and reusable instructions across teammates.
Communication & Writing
email-draft-polish/ - Draft, rewrite, or condense emails for the right tone and audience.
skill-installer/ - Helper scripts to install skills from curated lists or GitHub paths.
skill-creator/ - Guidance for building effective Codex skills with progressive disclosure.
Using Skills in Codex
Skills live in $CODEX_HOME/skills (default ~/.codex/skills). Each subfolder needs a SKILL.md with name and description frontmatter.
After installing or updating a skill, restart Codex so it reloads metadata.
In a session, describe the task naturally; Codex auto-triggers skills whose descriptions match the request. You can also mention a skill by name if you want it considered.
To verify installation, list installed skills (ls ~/.codex/skills) and inspect metadata (head ~/.codex/skills/<skill>/SKILL.md).
Creating Skills
Skill layout:
skill-name/
├── SKILL.md # Required: instructions + YAML frontmatter
├── scripts/ # Optional: helper scripts for deterministic steps
├── references/ # Optional: long-form docs loaded only when needed
└── assets/ # Optional: templates or files used in outputs
Basic SKILL.md template:
---name: my-skill-namedescription: What the skill does and when Codex should use it.---# My Skill Name
Clear instructions and steps for Codex to execute the task.
Best practices:
Keep the description exhaustive about when to trigger; keep the body focused on execution steps.
Use progressive disclosure: put detailed references in references/ and call them out from SKILL.md only when needed.
Include scripts for repeatable or deterministic operations; mention when Codex should run them.
Avoid extra docs (README, changelog) inside the skill folder to keep context lean.
Contributing
PRs welcome. Add real, reusable skills, keep descriptions precise, and include any needed scripts or references. If you add new skills, ensure the description clearly states when Codex should trigger and test that metadata fits within context limits.
Join the Community
Join our Discord - Chat with other developers building Codex skills.