跳到主要内容
知仓学习社ZHICANG

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-deb…

不碰外部(只输出文字)无严重或高危命中hashgraph-online/awesome-codex-plugins

它会碰到什么

扫了多少1 个文本文件,3 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

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.

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。