textbook-methodology
Use when drafting prose sections for a bookwright (technical non-fiction) project. Encodes the Bernoulli-textbook workflow: atom-outward design, deferral discipline, running threads, page budgets, Path A subagent pattern, header comment block convention.
What this skill does
# Textbook Methodology (bookwright)
The Bernoulli-textbook approach: discipline that makes long-form technical books actually finishable.
## Atom-outward design
When designing a Part, sequence the chapters so the FOUNDATION chapter is drafted LAST. The Bernoulli textbook drafted chapter 1 (the noisy bit, the foundational atom) after chapters 2, 3, 4, because chapter 1 is best written knowing where the reader is being taken. The same pattern applies at the Part level: the part introduction chapter benefits from being drafted after the technical chapters it introduces.
## Deferral discipline
Earlier chapters often need to mention a topic that gets full treatment later. Use the "we'll address this in §X" pattern: name the deferral explicitly, cite the section that will retire it, and make sure the integration check verifies that the target section actually does.
Examples from the Bernoulli textbook:
- Chapter 1 §1.4 said "the full treatment of estimation lives in chapter 7." Chapter 7 §7.1 explicitly says it retires this deferral, and §7.2-7.3 cash in.
- Chapter 1 exercise 10 said "what would a non-noisy-bit look like? See chapter 16." Chapter 16 §16.1 lists this as one of the deferrals it cashes.
## Running threads
The master spec names 3-5 running threads (recurring concepts/examples that appear across chapters). Each chapter carries N of M threads. The integration check verifies each thread appears in the chapters the spec assigned it to.
Bernoulli threads: BSC (binary symmetric channel), biased coin, classifier verdict, Bloom filter, Miller-Rabin, Bernoulli[T] type. Each carries through multiple chapters; the integration check produces an inventory.
## Page budgets
Per-section page targets are stated in the per-chapter plan. Plans 1-3 of Bernoulli came in 30-43% over target; Plans 4+ adjusted by aiming for the LOWER end of the target band to land near nominal. Tolerance: plus-or-minus 30 percent is the integration-check band.
If a section comes in significantly over, reviewers should ask: is the math density justifying it (acceptable), or is the prose padded (cut)?
## Path A subagent discipline
For each section drafting task, the cadence is:
1. Implementer subagent: drafts the section per the plan's content checklist, builds the book, commits.
2. spec-auditor subagent: checks against the content checklist.
3. quality-auditor subagent: cold-reads for clarity and craft.
4. If either auditor surfaces substantive findings: a fix subagent applies the changes, then the relevant auditor is re-run to verify.
This pattern protects main conversation context and catches issues per-section rather than per-chapter.
## Header comment block convention
Every section file starts with a comment block (LaTeX % lines) that documents:
- DEFINED here: labels this section creates.
- RESOLVED: labels from prior chapters that this section cites (cite each, with file path).
- FORWARD: labels this section cites that resolve in later sections/chapters (cite the resolving section).
The cross-ref-auditor reads these blocks to verify integrity.
## Source-paper reformulation
If the book draws on prior research papers, the cite-don't-copy discipline applies: cite the paper for results, produce fresh pedagogical prose. The source-reformulator agent handles this.
## Commit discipline
- One drafting task = one commit.
- Commit message HEREDOC with subject "book: <action>" and Co-Authored-By trailer.
- Do NOT stage book.pdf (binary artifact; rebuild from source).
- Review fixes get their own commits ("book: fix chapter X §X.Y per quality review").
## What this skill does NOT cover
- Cross-reference label naming and the header comment block template: see `bookwright:cross-reference-discipline`.
- Notebook execution and numerical-sanity-target conventions: see `bookwright:notebook-paired-with-prose`.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.