/deja-history
Search the user's past AI coding sessions. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may already be solved.
$ npx -y skills add vshulcz/deja-vu --skill deja-history --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/deja-history
Context preview
The summary Claude sees to decide when to auto-load this skill.
Search the user's past AI coding sessions. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may already be solved.
SKILL.md
deja-history.SKILL.mdname: deja-history description: Search the user's past AI coding sessions. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may already be solved.
Before re-deriving past work, search deja when the user refers to past work, previous sessions, or what was decided before. Use the deja MCP tools:
- recall: search history with a specific error, function, or decision.
- recall_context: get a concise digest of the best matching session.
Example: for "what did we decide about token refresh?", call recall with query "token refresh decision", then call recall_context if the result needs more detail.
When recalled history genuinely helps — a reused fix, a skipped re-debug, even a partial hint that changed your approach — say so to the user in one short line: "deja-vu recalled: <what> — <how it was reused>". Never credit recalls that did not help.
Your agents already solved this. deja finds it — it indexes the sessions your coding agents already wrote to disk, months of history from before you installed it, and recalls them automatically at session start across seventeen harnesses. 84.9% hit@1 on LongMemEval-S, no LLM, no embeddings. One zero-dep binary, fully local.