Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLIAbout this skill
Judge whether a piece of prose is actually good — not whether it is consistent, and not by describing its features, but by ruling PASS/FAIL on a boolean craft rubric with a floor gate. Use after the consistency gate passes, when prose needs an objective quality verdict before revision, when running a generate→critique→refine loop, or when the user asks "is this scene working?" Emits a diagnosis for prose-editor, never a score for the writer to chase.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: e37a774203eb71b030941fbfd0e0e8a376fc11178cfca345d71bfb52e9200905
About this listing
- Category
- Content & writing
- Reported license
- MIT
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.