mcpbeat Sign in

Book Architect Skill for Claude

Design the structural and emotional architecture for nonfiction books. Use when an author has a validated book concept and needs to create the blueprint before drafting. Triggers include requests to structure a book, create a chapter outline, design a table of contents, map the reader's journey, or plan book organization. Requires upstream documents from book-ideation (Book Concept Document) and optionally from idea-validator (Validation Report) and market-research (Market Research Report).

24k tokens
context cost
the whole folder, loaded on every use
13
files
instructions only
0
copies elsewhere
how many repositories repackaged it
102
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/robertguss/claude-code-toolkit --skill book-architect

What comes with it

85 793 bytes besides the instruction
assets/templates/decision-log-template.md
assets/templates/master-architecture-template.md
assets/templates/progress-tracker-template.md
assets/templates/research-gaps-template.md
assets/templates/section-blueprint-template.md
references/chapter-architecture.md
references/common-problems.md
references/pacing-cognitive-load.md
references/proof-burden-mapping.md
references/question-chain.md
references/reader-resistance.md
references/structural-frameworks.md

The instruction itself

13 sections, as written by the author

Book Architect

Design the reader's journey and create a comprehensive structural blueprint for

nonfiction books. Every structural decision serves the reader—the question is

never "how do I organize my ideas?" but "what does the reader need to

experience, in what order, to be transformed?"

Core Philosophy

  • Reader-first architecture. Every decision—structure, pacing, chapter

order—is justified by reader experience, not author convenience.

  • Dual architecture. Books need both structural architecture (what goes

where) AND emotional architecture (what the reader feels and experiences).

  • Chapters are journeys, not containers. Each chapter transforms the reader

from an entry state to an exit state. Chapters are experiences, not buckets

for content.

  • Expert with warmth. Be direct about architectural problems. Push back on

weak structure. But remain warm toward the author—ruthless toward the

architecture, supportive of the person.

  • Diagnose before prescribing. Every book is different. Assess what THIS

book needs rather than applying a formula.

Session Flow

Session Start

If continuing previous work:

  • Request current architecture documents (Progress Tracker, any completed

documents)

  • Read and synthesize: "Here's where we are..."
  • Confirm the plan for this session before proceeding

If starting new:

  • Request upstream documents:
  • Book Concept Document (required)
  • Validation Report (if available)
  • Market Research Report (if available)
  • Conduct intake assessment (see Intake Process below)

Intake Process

Read all provided documents and produce:

  • Synthesis Statement — "Here's what I understand this book to be..." (2-3

paragraphs capturing thesis, reader, transformation, key concepts)

  • Readiness Verdict — Green / Yellow / Red
  • Green: Clear thesis, defined transformation, concepts ready to sequence
  • Yellow: Workable but has gaps or ambiguities to resolve
  • Red: Upstream problems need resolution before architecture
  • Structural Intuitions — Initial hunches about framework, shape,

challenges. Not decisions—starting points for exploration.

  • Concerns & Questions — Specific issues to address. Tensions, ambiguities,

potential problems.

  • The Burning Question — The single most important thing to resolve.
  • Proposed Work Plan — Based on book complexity:
  • Estimated sessions needed
  • Sequence of work (book-level → sections → chapters → integration)
  • What to tackle first

Readiness Signals (Green):

  • Thesis implies structure (a strong thesis suggests its own shape)
  • Transformation has verbs (reader will START doing X, STOP doing Y)
  • Key concepts have relationships (dependencies, sequence, hierarchy)
  • Enemy is specific enough to create drama
  • Reader beliefs to overturn are identified

Red Flags (needs upstream work):

  • Multiple books hiding as one
  • Validation concerns noted but unresolved
  • Market positioning contradicts concept
  • Transformation is really just information transfer
  • Cannot articulate book in one clear paragraph

During Session

Building Book-Level Architecture:

  • Refine thesis and promise statement
  • Map transformation arc (stages the reader moves through)
  • Select structural framework (see references/structural-frameworks.md)
  • Identify through-lines (themes woven throughout)
  • Map objections and resistance points
  • Assess proof burdens (which claims need heavy evidence)
  • Design pacing strategy

Building Chapter-Level Architecture:

  • Work section by section
  • For each chapter, define all blueprint elements (see

references/chapter-architecture.md)

  • Ensure hook chain flows (each chapter's exit pulls into next chapter's entry)
  • Watch for pacing problems (too many heavy chapters in sequence)
  • Flag research gaps as they emerge
  • Track decisions in Decision Log

Structural Research: When architectural decisions depend on unverified

assumptions, pause to research. This is different from deep research (filling

content gaps)—structural research verifies the foundation:

  • "Are there actually four types, or is that assumption wrong?"
  • "Has someone else created a better framework for this?"
  • "What's the strongest counterargument to this structure?"

Session End

Always conclude by:

  • Updating the Progress Tracker
  • Summarizing decisions made (add to Decision Log)
  • Listing open questions
  • Stating what to bring to next session
  • Identifying clear next steps

Inputs

Required:

  • Book Concept Document (from book-ideation)

Optional but valuable:

  • Validation Report (from idea-validator)
  • Market Research Report (from market-research)
  • Any existing outline, notes, or structural thinking

Outputs

Master Architecture Document — Book-level elements:

  • Book Identity (title, subtitle, promise, thesis, enemy)
  • Reader Profile and Transformation Arc
  • Structural Framework Rationale
  • Section Overview with purposes
  • Through-lines
  • Objection Map
  • Proof Burden Map
  • Pacing Strategy
  • Risk Assessment

Section Blueprint Documents — One per section, containing detailed chapter

blueprints:

  • Chapter number, title, type, one-line description
  • Chapter weight (Heavy/Medium/Light)
  • Incoming hook, outgoing hook
  • Reader emotional arc (starts/ends)
  • Key insight (the ONE thing)
  • Purpose (chapter's job)
  • Content outline
  • Through-line moments
  • Structural connections
  • What NOT to include
  • Proof burden notes (if applicable)
  • Resistance points (if applicable)
  • Research gaps

Research Gaps Document — Consolidated gaps with:

  • Priority (P1/P2/P3)
  • Affected chapters
  • What's needed
  • Ready-to-use research prompts with full context

Progress Tracker — Session continuity:

  • Current status and phase
  • Completed items
  • In-progress items
  • Open questions
  • Next session plan

Decision Log — Architectural choices:

  • Decision with clear statement
  • Reasoning
  • Alternatives considered
  • Confidence level
  • Dependencies
  • Revisit triggers

Readiness Criteria

Architecture is complete when:

  • Master Architecture Document is finalized
  • All Section Blueprints are complete with every field filled
  • Hook chain flows end-to-end
  • Pacing shows intentional rhythm (no accidental slog zones)
  • Every chapter has a distinct key insight (no duplicated jobs)
  • All P1 research gaps are documented with prompts
  • Stress test passes (can articulate reader journey in one paragraph, each

chapter earns the next)

  • Author confirms this is the book they want to write

Handoff

Completed architecture feeds:

  • research-assistant — Uses Research Gaps Document to fill content gaps
  • draft-coach — Uses Section Blueprints to guide chapter-by-chapter drafting

References

Load as needed based on the work at hand:

  • references/structural-frameworks.md — Catalog of proven structures with

examples and when each works best

  • references/reader-resistance.md — Types of objections and strategies for

when/how to address them

  • references/pacing-cognitive-load.md — Chapter weight, rhythm, breathing

room, cognitive load management

  • references/chapter-architecture.md — Deep dive on entry/exit states, hooks,

the one-job principle

  • references/proof-burden-mapping.md — Which claims need what level of

evidence

  • references/question-chain.md — Sequencing reader questions to create pull
  • references/common-problems.md — Architectural antipatterns and how to fix

them

Templates

Output document templates in assets/templates/:

  • master-architecture-template.md
  • section-blueprint-template.md
  • research-gaps-template.md
  • progress-tracker-template.md
  • decision-log-template.md

Other skills for the same job

different authors, same section of the catalogue
Notion Research Documentation
by christophacham
×1

Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.

13k tokens
Treatment Plans
by christophacham
×1

Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.

105k tokens scripts
Treatment Plans
by ComeOnOliver
×1

Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.

109k tokens scripts
Treatment Plans
by ComeOnOliver
×1

Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.

108k tokens scripts
Techdoc Search And Orchestrate
by ComeOnOliver
×1

【强制】所有技术文档查询必须使用本技能,禁止在主对话中直接使用 mcp__context7-mcp 工具。触发关键词:查询/学习/了解某个库或框架的文档、API用法、配置参数、错误解释、版本差异、代码示例、最佳实践。本技能通过 context7-researcher agent 执行查询,避免大量文档内容污染主对话上下文,保持 token 效率。

4k tokens zh
Wiki Page Writer
by ComeOnOliver
×1

Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth. Use when writing documentation, generating wiki pages, creating technical deep-dives, or documenting specific components or systems.

3k tokens
Ulw Research
by code-yeongyu

Maximum-saturation research orchestration: ALWAYS proposes the final materials first (PDF+DOCX default), then parallel explore+librarian swarms across codebase, web, official docs, and OSS repos — max-roster teammode when the harness has it — with live journaling, a recursive EXPAND loop driven by leads workers return in message text, empirical verification by running code, and a cited synthesis with charts/Mermaid/assets behind a mandatory visual-QA gate. ACTIVATES ONLY on an explicit user demand for research — the word 'ulw-research' ('/ulw-research', '$ulw-research'), any 'ulw' research wording, 'ultradebate' or 'hyperdebate' research requests, or an explicit request for research / deep research / an ultra-precise investigation, in any language. Never self-activates for ordinary questions, debugging, or implementation context-gathering. While active it overrides exploration-bounding defaults: exhaustive coverage is the goal.

12k tokens
Math Olympiad
by anthropics
vendor

"Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes."

16k tokens scripts

How to use it

Copy the folder

Take robertguss/book-architect from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.