Skill 详情
codex-cli-specialist
Covers Codex CLI setup plus converting and syncing skills between Claude Code and Codex.
使用前先检查
自动化审核只检查相关性,不代表安全审查或推荐。使用前请阅读来源中的说明。
SKILL.md
这段内容是审核时保存的快照。外部来源才是完整且最新的版本。
--- name: codex-cli-specialist description: > OpenAI Codex CLI and cross-platform skill authoring. Use when setting up Codex CLI, converting or syncing skills between Claude Code and Codex, configuring agents/openai.yaml, or validating cross-platform skill compatibility. license: MIT + Commons Clause metadata: version: 1.1.0 author: borghei category: engineering domain: development-tools updated: 2026-06-17 tags: [openai-codex, cross-platform, skill-conversion, cli] --- # Codex CLI Specialist The agent converts Claude Code skills to Codex-compatible format, validates cross-platform compatibility, and builds skill registry manifests. It generates `agents/openai.yaml` configurations from SKILL.md frontmatter, runs 17 compatibility checks across both platforms, and produces `skills-index.json` for discovery systems. ## Core Capabilities - **Skill conversion** — turn a Claude Code SKILL.md into a Codex-compatible skill by generating `agents/openai.yaml` and copying scripts/references/assets. - **Cross-platform validation** — run 17 checks across Claude Code, Codex CLI, and shared categories (frontmatter, openai.yaml, encoding, naming, size). - **Index building** — scan skill directories and emit a `skills-index.json` manifest for registries, discovery, and version pinning. - **Codex CLI setup & operation** — install, configure API access, and run with the right approval mode (suggest / auto-edit / full-auto). - **Dual-target authoring** — write skills that work on both platforms from one shared `scripts/`, `references/`, `assets/` tree. - **Distribution & sync** — keep Claude Code and Codex in sync via shared repo, CI/CD conversion, or git hooks; publish via GitHub releases. ## When to Use - Setting up or operating OpenAI Codex CLI. - Converting or syncing skills between Claude Code and Codex. - Configuring or reviewing `agents/openai.yaml`. - Validating a skill for dual-platform compatibility. - Building a `skills-index.json` for a skill library. ## Clarify First Before converting or building, confirm these inputs. If any is unknown or vague, ASK — do not assume: - [ ] **Task** — convert a skill, validate cross-platform compatibility, or build a skills index (selects `codex_skill_converter.py` vs `cross_platform_validator.py` vs `skills_index_builder.py`) - [ ] **Source path** — the SKILL.md or skill directory to operate on (the input the scripts read) - [ ] **Strictness** — strict validation mode and whether to fail on warnings (sets `--strict` and the pass/fail gate) Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact. ## Tools | Tool | Purpose | Command | |------|---------|---------| | `codex_skill_converter.py` | Convert a Claude Code SKILL.md into Codex format (`agents/openai.yaml`) | `python scripts/codex_skill_converter.py <skill_md> [--output-dir DIR] [--json]` | | `cross_platform_validator.py` | Run 17 Claude Code + Codex + cross-platform compatibility checks on a skill dir | `python scripts/cross_platform_validator.py <skill_dir> [--strict] [--json]` | | `skills_index_builder.py` | Build a `skills-index.json` manifest from a directory of skills | `python scripts/skills_index_builder.py <skills_dir> [--output FILE] [--format json\|human] [--category CAT]` | ## References Load the reference that matches the task — keep this file lean and pull detail on demand: - **[references/workflows.md](references/workflows.md)** — Quick Start, Tools Overview, the 5 core workflows (install, author, convert, validate, build index), Common Patterns, and deep per-tool parameter/output reference. Read when running a workflow or needing exact tool arguments. - **[references/configuration-and-distribution.md](references/configuration-and-distribution.md)** — `agents/openai.yaml` structure, discovery/locations, invocation patterns, cross-platform patterns, frontmatter compatibility, install/versioning, and sync/C在 GitHub 阅读完整来源 (打开外部页面)