aios

Plugin aios from marketplace aios in ludwigawra/AIOS. Commands read from the repo's manifest — 1 month ago.

Skills (17)

• aios-explore

  Show the user every skill AI-OS has installed, grouped by purpose, with one-line descriptions and when to use each. Use this any time the user asks "what can this do", "what commands are there", or "help" — and at the end of /aios-start to orient a fresh install.

• aios-help

  The interactive guide to AI-OS. Three modes — tour (linear walkthrough of how the system works), status (live setup-progress with next-step suggestions), and ask (free-form Q&A about the system). Use this whenever the user asks "what is this", "how does this work", "how do I extend", "how do I add",

• aios-start

  Bootstrap a new AI-OS in the current directory. Conversational onboarding that scaffolds a brain-inspired personal operating system — persistent memory, learned patterns, and skills that improve over time. Use this the first time a user sets up AI-OS in a repo.

• aios-update

  Non-destructive update for an installed AI-OS. Pulls new skills, hooks, and templates from the current plugin version into the user's `.claude/` directory without ever touching the brain folders (memory, learning, MEMORY.md, etc.). Use after the user upgrades the plugin (`npm update @aios/plugin` or

• auto-outreach-queue

  Autonomously draft a queue of personalized follow-up messages for people in knowledge/people/ who are overdue, have open commitments, or are relevant to an active goal. Each draft matches the user's voice (voice rules + behavioral-patterns), cites real prior context, and is queued under memory/short

• behavioral-learning

  Observe how the user actually works — not what they say — and extract behavioral patterns the system can use to adapt its own triggers, defaults, and voice. Runs nightly after nightly-consolidation. Reads archived transcripts, the autonomous-runs ledger, and usage frequency signals. Writes inferred

• decision-check

  Check prior decisions and patterns before committing to a new one — surfaces history on a topic, flags contradictions, and recommends whether to proceed, reconsider, or supersede. Use when the user is about to decide something non-trivial, when a new direction sounds familiar, or when you sense tens

• foresight

  Forward-looking strategic planning — ranked priorities for the week (or window) ahead, grounded in goals, decisions, patterns, and whatever calendar or pipeline signals exist. Use when planning the week, when the user feels scattered about what to do next, when a reflection has surfaced a course cor

• memory-search

  Search the AI-OS brain for entities, context, prior decisions, and relevant files before starting work. Use when you need context about a person, company, project, topic, or decision — or any time a session begins referencing something that may already exist in the brain.

• nightly-consolidation

  End-of-day consolidation for the AI-OS brain — processes short-term memory, extracts decisions and patterns, routes new entities, logs skill feedback and corrections, archives processed files, and writes a summary report. Use at the end of a working day, on a scheduled trigger, or on-demand when sho

• nightly-goal-pursuit

  While the user sleeps, advance one long-term goal by doing preparatory work (research, drafts, list-building, brief notes) that removes friction from tomorrow's first move. Use at night (typically scheduled after nightly-consolidation), when the user wants to wake up to visible progress, or when a g

• project-status

  Quick status check on any active project in projects — progress, blockers, days since activity, next concrete action. Use when the user asks about a specific project, when planning a week and needing to decide which projects deserve attention, when a project gets mentioned and you need current state

• reflect

  On-demand strategic reflection across goals, decisions, and learned patterns. Use when the user wants a goal-by-goal progress check, is feeling scattered, is deciding whether to change direction, or at natural checkpoints (end of week, end of month, end of quarter, after a setback). Produces a struc

• signal-calibration

  Nightly self-improvement for the thalamus signal detector — the pre-prompt hook that suggests which brain regions to activate based on keyword signals. Compares what the thalamus predicted vs what actually got loaded or mattered in each session, measures hits and misses, and proposes concrete update

• forge-skill

  Auto-generate intent-wrapped skills from a connected MCP's tool definitions. The user connects a new MCP (Gmail, Notion, Linear, Supabase, whatever), then runs /forge-skill [mcp-name] and the brain proposes 3-5 skill candidates that wrap those tools with natural-language intents. Every skill is appr

• meeting-prep

  Produce a focused brief for an upcoming meeting — who the attendees are, why this meeting exists, what was agreed last time, what is still open, and the one outcome that makes this meeting worth having. Pulls meeting metadata from Google Calendar, attendee context from knowledge/people/ and /compani

• relationship-check

  Quick read on the state of a relationship — who they are, last contact, open commitments, unresolved threads, and a specific next action. Reads knowledge/people/ and cross-references any mentions in memory/decisions/, learning/corrections.md, and projects/. Use before sending an email or message to

Hooks (4)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"

• SessionEnd

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-end.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-tool-failure.sh"

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/user-prompt-submit.sh"

Similar plugins