跳到正文
cccskills
免费在 GitHub 公开

bible

Load the operations codex that governs everyone acting as or for the owner (the owner, human assistants and AI agents) before outreach, replies in their chats, scheduling, purchases, hiring or household ops. Covers where the rules live in the vault, how to pull the right slice, and the rule that the newest entry wins per topic. Triggers: "/bible", "what do the rules say".

中文简介正在准备中。当前显示原文说明。

集成工具TelegramTrello
查看安装方法

包含的文件(1)

  • SKILL.md5.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Bible — Anton's behavioral codex (mega-skill)

🧒 When reporting to Anton: end with a child-simple "In plain words" recap in his language (his standing request; reports TO Anton only — never inside vault notes or outbound messages). See memory eli5-always.

The Bible is not documentation — it is the behavioral rulebook for every actor that acts as or for Anton: Anton himself, his living assistants, and silicon agents (LLM/AI). One artifact, many readers. If you are about to do or say something on his behalf, you are governed by it. Canonical logic lives in the vault note protocol-bible-as-prompt.

Who is governed

Anything done "as Anton" or "on Anton's behalf" — you (the agent), his assistants, him.

Where the rules live (single source of truth = the vault)

Vault root: $OBSIDIAN_VAULT. Never duplicate rules into this skill — copies drift. Load from:

  • The umbrella note: concept-bible-platinum.
  • Domains / indexes:
    • 📤 Outreach & external leads (priority #1): _Bible-Outreach-MOC
    • 🏢 Operations: _Operations-Bible-MOC · Trello cards: _Bible-Trello-Index
    • 🛒 Purchases: _Pokupki-Rules
    • 🙋 Anton's personal layer: concept-bible-personal
  • Altitudes (note prefixes): insight-* (principle) → protocol-* (playbook) → reglament-* (atomic rule) → decision-* (precedent).
  • Self-maintenance: protocol-bible-self-maintenance. Secrets boundary: decision-bible-secrets-quarantine.

How to load the right slice

Pull the narrow relevant slice for the task — not all 10 years.

  • By domain: open the matching MOC above.
  • By meaning: python $IMPORTS_ROOT/brain_ask.py "<question>" (semantic search over the curated layer).
  • By keyword: grep reglament-* / protocol-* under 03-Insights\Operations\ and 05-Resources\Protocols\.
  • Filter by audience: load agent + both; skip human-only (needs live judgment).

Precedence — resolving conflicting rules

  1. Newer beats older on the same topic (Anton's law) — by date_established; the loser becomes superseded.
  2. Anton's explicit rules are protected — to override an origin: anton / authored_by: human rule, the new one must also be Anton's or carry supersedes:. Team/agent don't override Anton by date alone.
  3. Specific beats general (carve-outs).
  4. Priority flag must > should > may.
  5. Letter-vs-spirit clash (reglament vs insight) → escalate to Anton to rewrite the reglament.

consult → act → write-back

  1. Consult the slice before acting.
  2. Act by the rules. Consequential/irreversible (money, outbound to external people, commitments, access) → Tier-2: ask Anton (operating-agreement). Outbound lead messages = draft→approve, never autonomous.
  3. Gap → escalate to Anton; his answer becomes a new reglament-* (verbatim, with audience). "Error/gap → write the rule immediately."

Secrets quarantine

Because the Bible is now a prompt, never load or emit secrets (passwords, accesses, financial figures, "grey" techniques). They live outside the loadable Bible. See decision-bible-secrets-quarantine.

Relation to other skills

telegram-assistant and telegram-lead-outreach are channel playbooks under this contract — same precedence, same write-back, same secrets boundary. When they act on Anton's behalf, this skill's rules apply.

How to write a rule (dual-reader)

Verbatim from Anton · imperative WHEN → DO · self-contained + example · frontmatter (type, altitude, audience, theme, origin, authored_by, date_established, status, confidence, plus supersedes / superseded_by on replacement). Full standard: vault note protocol-bible-as-prompt. Step-by-step playbook with examples (even for a weak LLM): vault note protocol-bible-rule-authoring.

<!--kit-footer-->

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.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

03

免费

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.

中文简介正在准备中。当前显示原文说明。

tonydzi/second-brain-starter-kit92026年10月20日 更新

1

免费

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".

中文简介正在准备中。当前显示原文说明。

tonydzi/second-brain-starter-kit92026年10月20日 更新

agenda

免费

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".

中文简介正在准备中。当前显示原文说明。

tonydzi/second-brain-starter-kit92026年10月20日 更新

ai-slop

免费

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.

中文简介正在准备中。当前显示原文说明。

tonydzi/second-brain-starter-kit92026年10月20日 更新

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".

中文简介正在准备中。当前显示原文说明。

tonydzi/second-brain-starter-kit92026年10月20日 更新

- 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“

中文简介正在准备中。当前显示原文说明。

tonydzi/second-brain-starter-kit92026年10月20日 更新

查看 tonydzi 的全部技能

报告此技能的问题