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

chat

Skill6 starsChanged 2 months agoMITView on GitHub

Find a Telegram chat, group or channel by name and return its numeric id and t.me link from a local index, with no live crawl. Also answers which groups you share with a person or company. This is the chat lane, not people search. Triggers: "/chat <query>", "find the <X> chat", "chat id for <X>".

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When you need to act on "some chat by name", FIRST query the local index — never crawl the live dialog list blind.

    line 19
  2. Very specific:

    If a brand-new chat is missing, run that refresh or fall back to live search_dialogs.

    line 52
  3. Very specific:

    All under $IMPORTS_ROOT/dialogs/.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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 — instant Telegram chat lookup

Anton's pain: "find chat X" used to mean 20–60 min crawling the live dialog list. The chat's telegram_id + link already live in chats.db (built from the CRM tg_entities dump — the same extraction the CRM's mtproto-api does). Look it up, get the id, then operate the chat directly via the Telegram MCP.

Rule (always)

When you need to act on "some chat by name", FIRST query the local index — never crawl the live dialog list blind. Memory: [[telegram-chat-index]].

Lookup — find_chat.py

cd $IMPORTS_ROOT/dialogs
PYTHONUTF8=1 python find_chat.py <query words>      # chats first, then people
PYTHONUTF8=1 python find_chat.py <query> --all      # include user DMs
PYTHONUTF8=1 python find_chat.py <query> --limit 80

Prints [TYPE] telegram_id name t.me-link (+members). Matching reuses ..\namesearch\name_norm.py so wrong-layout (dbrnjh) / translit / typos still hit. ⚠️ ALWAYS PYTHONUTF8=1 (else cp1252 crash). The ??? in console = ASCII echo only; the DB stores proper UTF-8 — read it programmatically when you need the real title.

"Common groups with a person / company" — common_groups.py

PYTHONUTF8=1 python common_groups.py @handle [--account corp_acct]
PYTHONUTF8=1 python common_groups.py "Firstname Lastname"
PYTHONUTF8=1 python common_groups.py <telegram_id>

Lists groups where one of OUR accounts sits alongside that person (ours/theirs + which account + link). COVERAGE: rosters are full for small/curated groups, partial for big public ones → for an authoritative per-person answer use the live MCP get_common_chats(user, account).

Visual (Anton works by eye)

_Dashboards\Telegram-Groups.html — all chats, filter by account / ours-vs-theirs / topic / value, search, per-group sub-classification.

Freshness

chats.db backbone = CRM dump (refreshed by the telegram-chat-index-refresh routine that appends live list_chats from Anton's accounts via refresh_chats.py). If a brand-new chat is missing, run that refresh or fall back to live search_dialogs.

Build / rebuild (rarely)

build_chats_db.py → index · build_group_graph.py → accounts/members/ours-theirs · build_group_digest.py + Sonnet classifier → group_class · build_groups_dashboard.py. All under $IMPORTS_ROOT/dialogs/. See memory [[telegram-chat-index]].

<!--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