Menu
Use when ending a session to persist project knowledge, user corrections, and inferred details from the conversation into the appropriate CLAUDE.md files.
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
| name | save-session-learnings |
| description | Use when ending a session to persist project knowledge, user corrections, and inferred details from the conversation into the appropriate CLAUDE.md files. |
Look for:
| Keep | Discard |
|---|---|
| Project-specific patterns and constraints | One-off fixes unlikely to recur |
| Corrected misconceptions about the codebase | Anything obvious from reading the code |
| Non-obvious gotchas and landmines | Standard practices already documented elsewhere |
| Architectural decisions with context | Temporary state from this session |
| Content type | File |
|---|---|
| Shared project knowledge (team-wide) | CLAUDE.md in the nearest relevant directory |
| Personal setup, local paths, dev preferences | CLAUDE.local.md in the project root |
| User-wide preferences across all projects | ~/.claude/CLAUDE.md |
When in doubt, use the CLAUDE.md closest to the code the learning refers to. A learning about a specific subdirectory belongs in that subdirectory's CLAUDE.md, not the root.
Each entry must be:
Do not add boilerplate or verbose explanations. If a reader would understand it by reading the code, skip it.
After updating, print:
Updated: <file> — <entry>
Updated: <file> — <entry>
Discarded: <topic> (<reason>)
Use when working with Kubernetes clusters, manifests, and related tasks.
Read HANDOFF.md and continue from where we left off
Use when ending a session, completing a milestone, or stopping mid-task and context must be preserved for the next agent
Use when organizing raw content into slide-ready format, or when the user says "prepare slides", "structure this for a presentation", "brief for pptx".
Use when the user shares a URL or article and asks to extract key learnings, summarize topics, or generate a digest formatted for Google Chat, Slack, Discord, Telegram, or similar messaging tools. Accepts an optional format parameter.
Use when writing a CV, bio, LinkedIn post, or talk abstract for Silvio; when calibrating technical recommendations to Silvio's experience ("do I have experience with X?"); or when an introduction or speaker section is needed. Loads timeline, stack, credentials, and preferences on demand via the pointer table.