agentleFS
Sign inStart free
tonydzitonydzi/second-brain-starter-kit/skills/chat-search/SKILL.md

chat-search

Skill6 starsChanged 2 months agoMITView on GitHub

Search inside past agent sessions and continue the one that matters with a single command. Uses a separate episodic session index, so raw chat noise never pollutes the curated RAG. Triggers: "/chat-search", "which chat discussed X", "did we already research X", "search old chats".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before starting a new topic — check whether it was already dug into (the twin of RECALL).

    line 17
  2. Very specific:

    Every hit: [rr=score] date · machine · topic + a snippet + the line ▶ continue: python continue_session.py <cli>.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/chat-search — the book of chats (search inside old sessions)

A thin wrapper over $IMPORTS_ROOT/chat_search.py. Do NOT reimplement the logic — call the engine and show the result.

When

  • "which chat did we discuss X in?", "have we already looked into this?", "find the old conversation about X".
  • Before starting a new topic — check whether it was already dug into (the twin of RECALL).

What it is (and what it is NOT)

  • It searches a separate session index _brain_sessions.npy (21k+ chunks from _session-md\<machine>\<cli>.md), built by brain_sessions_index.py.
  • It is NOT the essence index behind /ask: raw chats are deliberately excluded from the sharp "mind" (the essence/evidence decision, 2026-06-26). This is the evidence layer — "where exactly it was discussed" — while /ask answers "what I think".
  • HUMAN chats only: service/robot sessions are filtered out at export time (a classifier + a cheap-model judge).

How to run

python "$IMPORTS_ROOT/chat_search.py" "query in your own words"
python "$IMPORTS_ROOT/chat_search.py" --machine LAPTOP-1 "query"   # one machine only
python "$IMPORTS_ROOT/chat_search.py" -n 8 "query"                    # top-N (default 10)

Every hit: [rr=score] date · machine · topic + a snippet + the line ▶ continue: python continue_session.py <cli>.

Continue a chat you found

Copy the command from the hit (or use /resume-last for the most recent one). continue_session.py <cli> assembles a seed of the old chat into the clipboard — paste it into a new session.

Caveats (AK-47)

  • The index is built at night (run_session_archive.local.cmd → brain_sessions_index.py, incrementally). A fresh chat shows up after the nightly run; to force it: python brain_sessions_index.py.
  • Index missing / empty → the engine itself tells you Run: python brain_sessions_index.py --full.
  • Reranker scores can be negative — what matters is the ORDER (top-1 = most relevant), not the sign.
  • Siblings: /ask (meaning across the vault), /search (exact words in Telegram/FB/ChatGPT), /resume-last (continue the latest).
<!--kit-footer-->

Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free