enhance-prompt

name

enhance-prompt

description

Rewrite a rough or under-specified request into a polished, copy/paste-ready prompt that any agent or LLM can act on cold. Use when the user gives a quick description of something they want done and asks for it to be turned into a better prompt — e.g., "make this a good prompt", "rewrite this so I can paste it into a new session", "turn this into a copy/paste prompt", or invokes the skill with their rough request as the argument. Output is one fenced markdown block the user copies verbatim, plus a 1-2 sentence note on what changed. The output prompt is platform-neutral (no references to specific tools, agents, or platforms) but project-aware (encodes relevant constraints from CLAUDE.md when applicable to the task).

Codex Adapter

Read ../../../.claude/skills/enhance-prompt/SKILL.md completely and follow it as the canonical workflow for this skill.

• Resolve every relative script, reference, asset, and template path from the canonical skill directory under .claude/skills/enhance-prompt/.
• Read ../../../.agents/CODEX-SKILL-COMPATIBILITY.md and apply the status and exceptions for this skill.
• Translate Claude Code tool names to the available Codex equivalent as described by the repository AGENTS.md.
• Before any Claude Task, Agent, or Workflow step, confirm that the current Codex session exposes the required multi-agent tools. Do not replace independent review with self-review.
• Skill invocation alone does not authorize commit, push, PR, merge, deploy, migration, dependency installation, or another outward action unless that action is the user's explicit request.
• Follow Codex system, developer, sandbox, approval, and tool instructions when they differ from the canonical workflow.
• Keep the canonical Claude skill unchanged unless the user explicitly asks to edit the workflow itself.