Menu
Export the current conversation history to a formatted transcript. Usage: /export [format]
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
Check Claude Brain status — shows whether hooks, MCP server, and memory are working
Analyzes code for bugs, security vulnerabilities, performance problems, and style issues. Use when reviewing a PR, reading a diff, auditing a file, or asked to check, critique, inspect, or audit code. Outputs a structured markdown report with severity ratings.
Breaks a complex multi-step request into subtasks and routes each to the appropriate skill. Use when given a high-level goal that requires multiple steps, a multi-phase workflow, or when asked to plan and execute a project, pipeline, or sequence of tasks. Outputs a step plan with skill assignments and handoff contracts.
Condenses any text into a structured summary with key points and a one-sentence takeaway. Use when asked to summarize, TLDR, condense, distill, or recap text, articles, transcripts, meeting notes, or documents. Outputs an overview paragraph, bullet-point key points, and a single takeaway line.
Switch or show the AI model for the current session. Usage: /model [model-name|default|list]
Show token usage and estimated cost for this session
| name | export |
| description | Export the current conversation history to a formatted transcript. Usage: /export [format] |
The user wants to export or save the current conversation history.
/export → export as markdown (default)/export markdown → export as formatted markdown/export json → export as JSON/export text → export as plain text**User:** / **Assistant:** with a horizontal rule between turns.{"role": "user"|"assistant", "content": "..."} objects.User: / Assistant: labels and blank lines between turns.