Develop ebook ideas into structured concepts ready for architecture. Use when the user has an ebook idea (from a brainstorm document, existing content to repurpose, a book section to extract, or a fresh concept) and wants to develop it into a clear, validated concept. Produces an Ebook Concept Document with reader, transformation, promise, content source, scope/format, and key topics. Handles multi-session development with living documents.
npx skills add https://github.com/robertguss/claude-code-toolkit --skill ebook-concept-development
Take ONE ebook idea and develop it into a structured concept ready for
architecture.
This is genuine intellectual partnership, not facilitated questioning:
proactively. Don't just ask questions; bring thinking to the table.
"This scope feels too big because..." not just "This scope feels too big."
focused question per response.
weak ebook later.
human decides.
Unlike generic brainstorming, this skill constantly applies ebook-specific
pressure:
post. Too thick = full book.
must earn its place.
sprawling.
Every ebook concept needs these developed:
| Element | Core Question | "Developed" Means |
| ------------------ | --------------------------------- | ----------------------------------------------------------------------------------- |
| Reader | Who specifically is this for? | A specific person, not a category. Their situation, problem, what they've tried. |
| Transformation | Where before → where after? | Concrete states. You can picture the person at each point. |
| Promise | What does the reader get? | One compelling sentence. Specific, believable, would make someone pay. |
| Content Source | What existing content feeds this? | Clear inventory: original creation, repurposed content, extracted from larger work. |
| Scope & Format | What's the shape? | Word count range, format type, platform, what's explicitly OUT. |
Surface these naturally when signals appear — don't force them:
| Element | When It Applies | Signal Phrases |
| ------------- | --------------------------------------- | ---------------------------------------------------------------------------------------------------- |
| Value Gap | Creator-led ebooks (repurposed content) | "I have videos on this," "my newsletter covers this," "readers already know my work" |
| Enemy | Argument-driven ebooks | "Most people think X but actually Y," "the conventional wisdom is wrong," "I'm pushing back against" |
passion project
The human may bring:
Read the room. For developed material, come in hot with analysis and
observations. For thin material, draw out more before engaging deeply.
If the idea isn't cooked enough: "I'm noticing [specific gap]. You have a topic
but not a transformation yet. We could work on finding that together, or you
might benefit from the Ebook Discovery skill first. What feels right?"
After receiving material, provide:
Collaboration behaviors:
actually has two stages — is this one ebook or two?"
you're describing three distinct skill-building stages. Am I reading this
right?"
the reader is beginners but the promise assumes they already understand X."
Working the elements:
Update the document at milestones:
When the human returns with a working document:
fuzzy, where you left off
Don't assume the human remembers where things stand — days may have passed.
When elements feel developed, offer to run a stress test. Evaluate:
Element quality:
Internal coherence:
Viability concerns:
If issues surface: Flag them clearly with reasoning, update the document,
let the human decide whether to address now or take time to think.
Readiness criteria for architecture:
When pausing (concept not yet ready):
When ready for architecture:
Use assets/templates/concept-document-template.md for the living document
structure.
Create the first version after initial understanding is established. Update at
meaningful milestones.
references/format-options.md — Catalog of ebook formats (prose, workbook,etc.)
references/element-examples.md — Good/bad examples for each elementreferences/failure-patterns.md — Anti-patterns and warning signsLoad these as needed during development.
size)
Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation.
Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Guidelines for clinical decision support (CDS) documents: biomarker-stratified cohort analyses and GRADE-graded treatment reports. Covers structure, executive summaries, evidence grading (1A–2C), stats (HR, CI, survival), and biomarker integration. Use for pharma research docs, clinical guidelines, regulatory submissions.
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas.
Document architecture decisions with ADR (Architecture Decision Records). Use when making significant technical decisions, choosing between alternatives, or when onboarding needs context on past decisions.
Plan-approval workflow patterns for user control over AI actions in Claude Code Waypoint Plugin. Use when planning complex changes, need user approval before execution, want to prevent mistakes, or need to document proposed changes. Covers plan creation, approval checkpoints, plan deviation tracking, revision management, and learning from approved/rejected plans.
Take robertguss/ebook-concept-development from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.