Full-text keyword search across every conversation at once (Telegram, Facebook, ChatGPT, Claude, notes, transcripts) over a local BM25/FTS5 catalog: instant, zero tokens, with snippets and chat-title hits. The exact-words lane, complementary to semantic search. Triggers: "/search <words>", "where did I write about <X>".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
OBJECTIVE: Find specific words/phrases inside Anton's entire conversation corpus (~99k notes in 01-Conversations/**) instantly and token-free, returning ranked snippets + which chats match by title. The lexical (BM25) lane of the unified search layer; the semantic (sqlite-vec + RRF) lane is added per the decision memo.
CONTEXT:
$IMPORTS_ROOT/search/search_catalog.db (SQLite FTS5 over title+body of every conversation .md). Rebuilt by build_catalog_fts.py (derived, rebuildable artifact; ~3 min over 99k files).python $IMPORTS_ROOT/search/search.py [--k N] [--chats] <query> (UTF-8 output, real Cyrillic).python $IMPORTS_ROOT/search/search_server.py -> http://127.0.0.1:8771 (stdlib, no deps; autostart task keeps it alive)...\dialogs\dialogs.db (chat lookup by name).02-Decisions\decision-unified-search-layer.md; memory unified-search-layer. Token law: exact/SQL before BM25, BM25 before embeddings, retrieval before LLM.STEPS:
search_server.py if down).python $IMPORTS_ROOT/search/search.py --k 15 --chats <query> (add --chats when he's hunting for WHICH chat, not just content).build_catalog_fts.py) — the weekly task handles this, or run it on demand.CONSTRAINTS:
/ask (semantic) instead; if it's a person's name, prefer /find.OUTPUT: A short ranked list of the best matches (title · source · date · snippet · file link) + any chat-title hits, then offer next step. End replies to Anton with a 🧒 In plain words recap.
RELATION (do not duplicate):
unified-search-layer + decision note.Like this skill? It is part of 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.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Run an autonomous consensus round between agent peers on several machines: they negotiate a decision over a shared channel and execute it without a human relaying messages. Use when multiple machines must agree on a change. Triggers: "/03", "work it out among yourselves", "find consensus". Wakes the human only for irreversible actions or a deadlock.
The English summary is being prepared. Showing the original description.
Recover a session after a hard crash (app died, machine rebooted, context lost mid-work): replay the turn-state ledger for the last requests, files and decisions, run a green/red health ping over the system map, file sync and MCP connectors, then rebuild the previous session history for pickup. Triggers: "/1", "resume after crash", "wake".
The English summary is being prepared. Showing the original description.
Show the operator's day: today's calendar plus what needs them personally (leads due, people awaiting a reply, deadlines), pulled from Calendar and Telegram and ranked. Read-only: sends and commits nothing. Triggers: "/agenda", "what's on today", "my agenda".
The English summary is being prepared. Showing the original description.
Rewrite machine-written text so it reads like a busy human wrote it: cut 50-70%, break the even rhythm, drop AI-tell words and filler, keep facts and protected terms. Use before publishing any post, reply or email drafted by a model. Triggers: /ai-slop, /slop, humanize, anti-slop, make it shorter and alive.
The English summary is being prepared. Showing the original description.
Decision protocol for strategic work: recall the knowledge vault, run a gap analysis, emit a deep-research prompt for external tools, then synthesize the returned reports into a decision memo. Use before any new product, feature, market, pricing, GTM or architecture call, where local recall alone is not enough. Triggers: "/alfa-search-recall-deepresearch", "alpha protocol", "R+DR".
The English summary is being prepared. Showing the original description.
- КРЕДИТ АВТОРУ ИДЕИ: совет из комментария (TG @ClawRus / @ClawInga, комменты под постами Антона в FB, треды и issue на… Триггеры: “/alpha-credit“, “/credit“, “кто нам это посоветовал“, “запиши совет“, “поблагодари советчиков“, “кому мы должны спасибо“, “кредит автору“, “чей это был совет“, “credit the author“
The English summary is being prepared. Showing the original description.