awesome-codex-skills icon indicating copy to clipboard operation
awesome-codex-skills copied to clipboard

A curated list of practical Codex skills for automating workflows across the Codex CLI and API.

Results 27 awesome-codex-skills issues
Sort by recently updated
recently updated
newest added

Summary: Adds a reusable SwarmClaw skill folder and a Development & Code Tools entry. The skill covers setup, launch, operations, MCP/provider guidance, and troubleshooting for the self-hosted SwarmClaw runtime. Validation:...

## Summary Updates the DEFAULT_REF variable in the skill installer script to match the repository's actual primary branch. ## Context The current ```install-skill-from-github.py``` script is hardcoded to use ```main``` as...

## Summary - Add a Simplified Chinese README translation - Add language switch links between English and Chinese READMEs ## Testing - git diff --check - Checked README links, commands,...

Adds `bringyour-migration-auditor`, a public Codex skill for auditing Claude Code -> Codex harness migrations. The skill checks the parts that do not behave like a normal file copy: AGENTS.md /...

## Summary - Update the PaperJSX README entry to avoid advertising unsupported standalone DOCX/XLSX/PDF/MCP-server installs. - Limit the standalone install path in `paperjsx/SKILL.md` to the currently installable PPTX package. -...

## Summary Adds `harness`, a meta-skill for designing specialized subagent teams in the Codex CLI environment. It generates `.codex/agents/*.toml` agent definitions, `.agents/skills/` skill bundles, and `AGENTS.md` configuration from a user's...

Pre-install security scanner for AI agent skills. ## What it does 6-phase security audit before installing third-party skills: - Surface scan: Detect 30+ malicious patterns (curl|bash, base64, instruction override) -...

Notice: this issue was generated by ChatGPT 5.5 on behalf of Thomas Bray during a local Codex Desktop evaluation. If you want a human attestation beyond reproducing it in your...

## Summary - **Add `logic-lens`** — logic-first code review via semi-formal execution tracing. Surfaces behavioral bugs, semantic errors, and runtime failures that linters miss, with L1–L6 risk codes. Six skills:...