Menu
Load context from previous sessions so you can pick up where you left off
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
Guide users through progressive lessons to learn AI assistant basics
Save what you worked on so your AI can pick it up next time
Example skill demonstrating the skill structure. Use as a template for creating your own skills.
Extract actionable content and filter hype/marketing from videos and articles. Invoke when user provides content with potential hype/marketing, wants signal without noise, or needs bullshit filtering.
Improve LLM prompts using prompt engineering best practices. Invoke when user wants to optimize prompts, improve slash commands, or apply prompt engineering.
Summarize meeting transcripts or notes into actionable format. Invoke when user provides meeting transcripts, notes, or wants actionable meeting summaries.
| name | start |
| description | Load context from previous sessions so you can pick up where you left off |
Run this at the beginning of each working session, or when starting a new conversation with your AI assistant.
Invocation: /start or "Let's start a session"
When this skill is invoked, follow these steps:
Look for session logs in ~/ai-data/logs/sessions/.
Read the last 3-7 days of logs (files named YYYY-MM-DD.md). Focus on:
If no session logs exist yet, that's fine - this is a new system.
Check for ~/ai-data/learning/user_model.yaml.
If it exists, read it to understand:
If it doesn't exist yet, skip this step.
Look in the most recent session log for:
Respond with a short acknowledgment. Examples:
Keep it brief. Don't summarize everything unless the user asks.
Over time, as you use /start regularly:
As you get comfortable, you might add:
These are enhancements - the core skill works without them.
