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".
インストールする前に、エージェントに与えられる指示の中身を確認できます。
🧒 When reporting to Anton end with a child-simple "In plain words" recap. (memory
eli5-always)
A fast, read-only "what does my day look like" — the manual counterpart of the scheduled Tg calendar agenda task (same intent, fired by hand). It assembles, it does NOT act (sending/booking lives in /pipeline + /intro).
mcp__a63ab772-..._list_events for today across Anton's calendars (list_calendars first if unsure). If that tool id is stale (connector reconnected), load it via ToolSearch query "calendar list events" like the tg-calendar-agenda twin does. His reminders live in owner.calendar@example.com, times in Europe/Lisbon (he lives there mostly — [[remind-anton-via-calendar]]). List meetings/reminders with times.$IMPORTS_ROOT/tg_followups.json + Platinum CRM, or call /pipeline's triage logic), a real human awaiting his reply, a money/legal deadline. He doesn't read email → surface only the email items that need HIM ([[anton-doesnt-read-email]]); no digest walls.04-Coach/, echo it.Top of the list = time-bound + needs-Anton (a meeting in 2h, a lead going cold). Then fixed calendar blocks. Then nice-to-have. Keep it tight — this is a glance, not a report. Offer the obvious next action ("work the leads → /pipeline", "a meeting with no agenda → /intro").
Read-only. Never send a message, book, or commit from here — hand off to /pipeline, /intro, or ask.
A short ranked agenda (≤~8 lines): ⏰ time-bound first, then context. Then 🧒 recap. Visual option: the Life-OS / Coach dashboards already render the day by eye ([[prefer-visual-dashboards]]).
<!--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.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
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.
日本語の概要は準備中です。原文の説明を表示しています。
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".
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
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".
日本語の概要は準備中です。原文の説明を表示しています。
- 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“
日本語の概要は準備中です。原文の説明を表示しています。
LLM-judge stage of an alpha-mining pipeline: take a miner's deterministic candidate list, keep only real signal, drop noise, and propose additions to that miner's curated note. Use after any zero-token detector run. Reads only the candidate digest and the home note, never the corpus. Triggers: "/alpha-judge <miner>", "judge the candidates".
日本語の概要は準備中です。原文の説明を表示しています。