SCHEMA
Single source of truth for the shape of every agent in this pack. One schema, one pool — `agents/index.json` is generated from these files, and the…
A focused single-agent workflow for turning rough source material into a strategic first-person chapter draft with explicit revision loops.
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
A focused single-agent workflow for turning rough source material into a strategic first-person chapter draft with explicit revision loops.
> A focused single-agent workflow for turning rough source material into a strategic first-person chapter draft with explicit revision loops.
Use this workflow when an author has voice notes, fragments, or strategic notes, but not yet a clean chapter draft. The goal is not generic ghostwriting. The goal is to produce a chapter that strengthens category positioning, preserves the author's voice, and exposes open editorial decisions clearly.
| Agent | Role | |-------|------| | Book Co-Author | Converts source material into a versioned chapter draft with editorial notes and next-step questions |
Activate Book Co-Author. Book goal: Build authority around practical AI adoption for Mittelstand companies. Target audience: Owners and operational leaders of 20-200 person businesses. Chapter topic: Why most AI projects fail before implementation starts. Desired draft maturity: First substantial draft. Raw material: - Voice memo: "The real failure happens in expectation setting, not tooling." - Notes: Leaders buy software before defining the operational bottleneck. - Story fragment: We nearly rolled out the wrong automation in a cabinetmaking workflow because the actual problem was quoting delays, not production throughput. - Positioning angle: Practical realism over hype. Produce: 1. Chapter objective and strategic role in the book 2. Any clarification questions you need 3. Chapter 2 - Version 1 - ready for review 4. Editorial notes on assumptions and proof gaps 5. Specific next-step revision requests
The Book Co-Author should respond in five parts:
1. `Target Outcome` 2. `Chapter Draft` 3. `Editorial Notes` 4. `Feedback Loop` 5. `Next Step`
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
Single source of truth for the shape of every agent in this pack. One schema, one pool — `agents/index.json` is generated from these files, and the…
How to write an agent body that is useful, compact, and consistent with the rest of the pack. Follow this when adding a new agent or materially rewriting an…
Curated list of every tag an agent is allowed to declare. Source of truth: [`tags.json`](tags.json). Linter rejects any tag not in this list.
Expert in cultural systems, rituals, kinship, belief systems, and ethnographic method — builds culturally coherent societies that feel lived-in rather than…
Expert in physical and human geography, climate systems, cartography, and spatial analysis — builds geographically coherent worlds where terrain, climate,…
Expert in historical analysis, periodization, material culture, and historiography — validates historical coherence and enriches settings with authentic period…