Menu
Generate a new image or edit existing images and return the result to the chat.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Publish architecture review HTML reports for this repository.
Publish architecture review HTML reports for this repository.
Find deepening opportunities in a codebase, informed by the project architecture map, glossary, constraints, and decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Use before choosing, creating, modifying, or verifying tests for a feature, bug fix, regression, refactor, integration, async workflow, or behavior change. Focuses agents on vertical proof first, real evidence before fixes, red/green proof, and clarification when the desired outcome is ambiguous.
Manage diagnostic logging with minimal context: find relevant logs, inspect status, enable or disable narrow logging, add runtime toggles when missing, and clean up after debugging.
Use when you need to send local files, media, or directories to the chat.
| name | generate-image |
| description | Generate a new image or edit existing images and return the result to the chat. |
Use this skill when the user needs an image artifact returned to the chat.
Run this command to enqueue image generation:
node "$(git rev-parse --show-toplevel)/scripts/enqueue-action-request.js" generate-image --prompt "<prompt>" [--image-path "<canonical-media-path>"]
Rules:
--image-path once per source image when editing existing media.