/eiirp

name: eiirp
version: 1.1.0
prompt_version: 1
description: |
  Everything In Its Right Place. The universal post-work organizer. After
  any significant work session, EIIRP runs a 7-phase audit: (1) inventory
  every output, (2) walk taxonomy to decide where each lands, (3) check
  schema-pack consistency against the brain's actual shape, (4) file
  enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify
  resolvability, (7) report. Named after the Radiohead song. Nothing
  produced during significant work lives only in chat — knowledge becomes
  permanent, patterns become reusable. Also carries the always-on
  auto-fire gate: when >=500 words of structured analysis on a
  user-shared document is about to be delivered, file the brain page
  first, then deliver the analysis with the link in that same reply.
triggers:
  - "everything in its right place"
  - "eiirp"
  - "store this research"
  - "put this in the brain"
  - "file this properly"
  - "where does this research go"
  - "make this permanent"
  - "archive this research"
  - "archive this research thread"
  - "brain this"
  - "file all of this"
  - "organize all of this"
  - "organize all of this work"
  - "make this re-doable"
  - "DRY this up"
  - "check everything is in the right place"
  - "analyze this document"
  - "deep analysis"
  - "review this report"
tools:
  - search
  - query
  - get_page
  - put_page
  - add_link
  - add_timeline_entry
mutating: true
writes_pages: true
# EIIRP files across the full canonical set — the actual destination
# per page is decided by brain-taxonomist consulting the active schema
# pack via `gbrain schema show --json`. List the gbrain-recommended set
# of canonical directories here so the filing-audit gate passes; on
# brains with custom packs, the routing surface is broader and routes
# through loadActivePack at write time.
writes_to:
  - people/
  - companies/
  - deals/
  - meetings/
  - concepts/
  - projects/
  - civic/
  - writing/
  - analysis/
  - guides/
  - research/
filing_exempt: true
# The auto-fire gate section below was merged from an upstream
# deep-analysis auto-filing skill:
upstream: deep-analysis-brain-auto
distinct_from:
  - name: brain-taxonomist
    reason: "brain-taxonomist classifies individual pages at write time (the filing GATE). EIIRP orchestrates the full post-work LIFECYCLE — inventory + taxonomy + schema + skillify + verify."
  - name: ingest
    reason: "ingest handles NEW content from external URLs/media. EIIRP handles COMPLETED research that needs to be decomposed and filed across multiple brain locations."
  - name: skillify
    reason: "skillify is the meta-skill for turning a feature into a tested skill. EIIRP calls skillify when Phase 5 identifies a reusable pattern."
  - name: signal-detector
    reason: "signal-detector ambiently captures the USER's ideas + entity mentions on every inbound message. EIIRP's auto-fire gate files the AGENT's own deliverable analysis at reply time. Both are always-on; they watch opposite directions of the conversation."
  - name: meeting-ingestion
    reason: "meeting-ingestion (like idea-ingest, media-ingest, voice-note-ingest, book-mirror) is a dedicated pipeline with its own brain-write logic. The auto-fire gate EXEMPTS dedicated-pipeline content — it never double-files."

EIIRP — Everything In Its Right Place

> *"Everything in its right place"* — Radiohead, Kid A

Contract

After any significant work, EIIRP organizes ALL outputs across two domains:

**Knowledge domain (brain):** 1. Every piece of knowledge lands in the correct brain location. 2. All sources are cited and linked. 3. The active schema pack is updated if a new content type emerged. 4. Entity pages created/updated with cross-links.

**Capability domain (skills):** 5. Every reusable pattern becomes a composable skill. 6. Existing skills are audited for DRY violations. 7. Skill graph is MECE — no gaps, no overlaps, no ambiguous routing.

**The meta-guarantee:** Nothing produced during significant work lives only in chat. Knowledge → brain. Patterns → skills. Everything in its right place.

When to Use

• After completing a deep research thread.
• After building something new (code, pipeline, workflow).
• After a multi-source analysis that produced significant findings.
• When the user says "EIIRP", "organize this", "DRY this up", "make this re-doable".
• When a work session produced both knowledge AND new capabilities.
• When you notice skill overlap, duplication, or gaps.

Auto-Fire Gate — file before you deliver (ALWAYS-ON)

> **Convention:** see [conventions/brain-first.md](../conventions/brain-first.md) > — this is its write side. Substantial analysis belongs in the brain, not > only in chat.

Unlike the 7-phase audit above (which the user invokes after a work session), this gate is an **always-on agent-side convention**, like `signal-detector`: the agent applies it on every substantive reply, not when a trigger phrase routes here. Always-on is a harness-routing convention that a well-behaved agent follows — not a mechanical guarantee; nothing in the gbrain runtime blocks a reply if the skill never loads.

**The moment of evaluation is delivery, not request.** The gate evaluates when substantial analysis (>=500 words of structured output on a user-shared document) is ABOUT to be delivered — the analysis is done and the reply is being composed. At that moment, file the brain page FIRST, then deliver the analysis plus the page link in that same reply. The user should never have to ask "did you file this?"

Fire conditions (all three must hold)

1. The user shared a document — a PDF, a file attachment, a link to a doc, or pasted long-form content. 2. The reply about to be delivered contains substantial analysis: >=500 words of structured output (findings, recommendations, or extracted data — not restatement or formatting). 3. The content is knowledge worth re-finding — someone reading the brain months lat