Skill
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Use when they say things like 'didn't we fix this before', 'what did we decide…
Development
Skill
/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.
Install
$ 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.
Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.
If these tools are not available in this session, the same index is reachable through the shell: `deja search --json "<query>"`, `deja ctx <query>`, `deja blame <path> --json`.
Finding something
- recall: search with the most specific token available — an exact error string, function name, file path, or flag. Several words are ANDed. Not for library docs or general knowledge; only this user's own sessions.
- recall_context: a full digest of the single best-matching session, once a recall hit looks right and the reasoning behind it matters.
- blame: before editing, refactoring or deleting a file, the prior sessions that discussed it, so you know why it is shaped the way it is. Session history, not git authorship.
- fix: paste a failing output verbatim to see the commands that followed that same error before, in sessions where it did not come back.
- how: the real command with the real flags this machine runs for a build, test, deploy or script, ordered by how many sessions ran it. A guessed invocation is plausible and fails on this setup.
- remember: store one durable decision after it is settled, as a single self-contained fact. Not transcripts, not anything already obvious from the code.
Reading a result
A result may carry a bracketed marker with a date — that is the user's own later judgement on that session, and it is not advisory. Do not repeat a rejected approach. Prefer a replacement over what it replaced. Treat a stale result as needing confirmation before acting on it. A result with no marker carries no judgement in either direction.
Saying what you used
When recalled history genuinely helps — a reused fix, a skipped re-debug, even a partial hint that changed your approach — tell the user in one short line at the start of your reply, naming the session: "déjà vu: we hit this JWT skew in March — reusing that fix (deja:a1b2c3d4-e5f)". Say nothing about recalls that did not help. This is provenance, not advertising; a note on every call would be noise.
Limits worth respecting
- Result windows are bounded. Do not report corpus-wide counts, or claim a complete audit, from the number of hits you got back.
- If deja is unavailable or the index is empty, say that history search is unavailable. Do not invent what it might have found.
- Vary the wording and try a second query before concluding nothing is there. Exact tokens match best, so an error string beats a paraphrase of it.
Read more
name: 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.
Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.
If these tools are not available in this session, the same index is reachable through the shell: `deja search --json "<query>"`, `deja ctx <query>`, `deja blame <path> --json`.
Finding something
- recall: search with the most specific token available — an exact error string, function name, file path, or flag. Several words are ANDed. Not for library docs or general knowledge; only this user's own sessions.
- recall_context: a full digest of the single best-matching session, once a recall hit looks right and the reasoning behind it matters.
- blame: before editing, refactoring or deleting a file, the prior sessions that discussed it, so you know why it is shaped the way it is. Session history, not git authorship.
- fix: paste a failing output verbatim to see the commands that followed that same error before, in sessions where it did not come back.
- how: the real command with the real flags this machine runs for a build, test, deploy or script, ordered by how many sessions ran it. A guessed invocation is plausible and fails on this setup.
- remember: store one durable decision after it is settled, as a single self-contained fact. Not transcripts, not anything already obvious from the code.
Reading a result
A result may carry a bracketed marker with a date — that is the user's own later judgement on that session, and it is not advisory. Do not repeat a rejected approach. Prefer a replacement over what it replaced. Treat a stale result as needing confirmation before acting on it. A result with no marker carries no judgement in either direction.
Saying what you used
When recalled history genuinely helps — a reused fix, a skipped re-debug, even a partial hint that changed your approach — tell the user in one short line at the start of your reply, naming the session: "déjà vu: we hit this JWT skew in March — reusing that fix (deja:a1b2c3d4-e5f)". Say nothing about recalls that did not help. This is provenance, not advertising; a note on every call would be noise.
Limits worth respecting
- Result windows are bounded. Do not report corpus-wide counts, or claim a complete audit, from the number of hits you got back.
- If deja is unavailable or the index is empty, say that history search is unavailable. Do not invent what it might have found.
- Vary the wording and try a second query before concluding nothing is there. Exact tokens match best, so an error string beats a paraphrase of it.
Ships withdeja-vu
One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 20 more coding agents, built from the session history already on disk. A fix found in one agent comes back in any of them, including months of sessions from before you installed it. No LLM, no embeddings, one local Go binary.
Get the whole plugin
Stats
811
Stars
76
Forks
Active
Maintenance
Go
Language
MIT
License
1d ago
Last commit
2mo ago
Created
Repo: vshulcz/deja-vu