ai-personal-os-s3

Diagnose how far along your AI Chief of Staff ("Robin") actually is — a 25-check, 5-layer maturity review across Identity, Sources, Skills, Autonomy, and Output that returns a rank (Intern → Junior Assistant → Trained CoS → Senior CoS → Hand of the King), your weakest layer, and the ONE highest-leverage next move. Evidence-based: it inspects your actual system (identity files, memory, MCP/connectors, skills, scheduled loops) instead of asking you to self-report, then asks only for the behavioral checks it can't detect. Auto-detects Claude Code vs Codex. Use for "/cos-review", "what's my CoS rank", "how good is my Robin", "grade my Chief of Staff", "where is my AI weakest". Modes: `setup` (first full scan + guided fix), bare (bi-weekly re-score vs last time), `status` (30-sec health check of MCPs + skills).

Package the user's whole AI Personal OS ("Robin") into a portable, shareable plugin — a `.claude-plugin/plugin.json` manifest plus their identity files, best skills, and one scheduled loop, bundled into a folder and a `.zip` that installs on any machine with `claude --plugin-dir` (or the Codex equivalent). Turns "a pile of dotfiles" into "infrastructure you can hand to a teammate." Inventories what Robin is made of, lets the user pick what ships, runs a hard secrets scan so no token/.env/key ever gets bundled, writes a clean manifest, zips it, and test-loads it. Auto-detects Claude Code vs Codex. Use for "/ship-robin", "ship my OS", "package Robin", "export my Chief of Staff", "make my setup a plugin", "share my Robin", "bundle my skills as a plugin". Always shows the file list and asks before zipping. Never bundles secrets.

Set up a two-way chat channel for the user's AI assistant ("Robin") on Telegram OR Slack, end to end: create the bot/app, let Robin push messages to the user, let the user message Robin and get a reply that acts with their context and skills, and deploy it to the cloud so it runs 24/7 with the laptop closed. Auto-detects whether it's running in Claude Code or Codex and works on both. Use when the user says "give Robin a voice", "set up Telegram", "set up Slack", "I want to text/DM my assistant", "two-way bot", "Robin in Slack", "/give-robin-a-voice", or wants their agent to message them. Walks them through it conversationally — they never edit code by hand.

Turn content into atomic Zettelkasten notes in ~/vault/atomic/ and keep ~/vault/index.md current. THREE modes by who drafts the note — FILE-IT (you wrote the insight, I only file it), DRAFT-IT (I draft one note from your scattered raw material, you edit a line and approve), IMPORT (I bulk-atomize a source you already authored — transcript, export, daily-logs — you elaborate at least one note before it commits). Connections are PROPOSE-then-DECIDE — I suggest [[wikilinks]] with reasons and flag contradictions, you choose which to keep; I never auto-write a link. Use on /atomize, "atomize this", "break this into notes", or to import an export/transcript/article.

Initialize Robin's identity (CLAUDE.md, SOUL.md, user-profile.md) from evidence — your AI conversation history (Claude Code sessions, Codex sessions, or exported ChatGPT / Claude.ai). Extracts behavioral evidence (not self-description), surfaces recurring people / acronyms / project codenames as a seed glossary, interviews you for any gaps, drafts the three files, and asks you to review before writing anything to disk. Use at the start of the AI Personal OS course (Workshop 1) or to refresh Robin's identity from new evidence. Always reviews drafts with you before committing.

Complete Robin's birth certificate. Runs three short interviews to produce course-goals.md, goals-2026.md, and achievements.md — the three files /init-robin cannot infer from conversation history because they require explicit declaration, not behavioral evidence. Use after /init-robin (Workshop 1 homework, ~15-20 min total), or invoke a single section to refresh just one file. Re-run goals-2026 annually; re-run achievements quarterly.