← ClaudeAtlas

codex-consultlisted

Consult OpenAI Codex (via the local `codex` CLI, non-interactive `codex exec`) for the two things it is comparatively strong at: (1) CONCISE, well-STRUCTURED writing — tightening verbose prose, restructuring a doc into a clean outline / tables / sections, executive summaries, README skeletons, changelog entries — and (2) IMAGE GENERATION — hero/placeholder art, logos, simple illustrative art, produced as real PNG files on disk (labeled flowcharts / architecture / sequence diagrams are NOT this — render those natively as Mermaid). Use whenever a document needs to get SHORTER and better ORGANIZED (not prettier-sounding), or whenever the user wants a generated image. Triggers: "codex한테 물어봐 / codex로 정리해 / 간결하게 정리해줘 / 구조화해줘 / 문서 구조 잡아줘 / 이미지 만들어줘 / 그림 생성해줘", or in English "ask codex", "tighten this up", "make this concise", "restructure this doc", "generate an image". Korean NUANCE/copy polish belongs to the sibling skill gemini-consult — this skill owns structure, concision, and images. Returns candidates/files f
uzysjung/uzys-agent-harness · ★ 3 · AI & Automation · score 69
Install: claude install-skill uzysjung/uzys-agent-harness
# codex-consult Delegate to OpenAI Codex (via `codex exec`) for **concise, structured writing** and **image generation** — two areas where a second model with different training is a cheap upgrade over Claude working alone. Codex is an *advisor and generator*: it produces drafts, structures, and image files; the repo stays the source of truth and the user makes the final call. ## Why this exists - **Concision & structure.** Codex is good at compressing verbose text and imposing clean structure — outlines, tables, section hierarchies, tight summaries. When a doc says in 300 words what needs 80, delegate the tightening. - **Image generation.** Codex ships a stable `image_generation` tool that writes real PNG files. Claude Code has no image generation — this is a capability gap, not just a quality gap. - **Division of labor with gemini-consult.** Korean *nuance/카피* (natural phrasing, marketing tone) and multi-persona critique → `gemini-consult`. *Structure, concision* → this skill. *Images* → both skills can generate; this one is the default (writes files straight to your OUT_DIR under an OS-level sandbox) — use gemini's image mode when the user asks for Gemini / "Nano Banana" style output. If a Korean text needs both structure and nuance: structure first here, then polish the phrasing there. ## Prerequisite: the `codex` CLI (auth is the user's action — do NOT fix it yourself) This skill shells out to the OpenAI Codex CLI. It is an external dependency, n