Agent skill

Ebook Discovery

by robertguss in robertguss/claude-code-toolkit

Surface ebook ideas you didn't know you had. An agent skill from robertguss/claude-code-toolkit.

MITAuto-check passedDocuments & Office

Install Ebook Discovery

skills CLI
$ npx skills add robertguss/claude-code-toolkit --skill ebook-discovery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install robertguss/claude-code-toolkit ebook-discovery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/robertguss/claude-code-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ebook-factory/ebook-discovery .claude/skills/ebook-discovery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ebook-discovery
GitHub stars
123
Token cost
~2k tokens
SKILL.md length
936 words
Files
10 (incl. references, assets)
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Surface ebook ideas you didn't know you had. An agent skill from robertguss/claude-code-toolkit.

  • Works in 4 steps: Update the tracker with current state → Review candidates surfaced this session → Note where to pick up next → …
  • Ready to discover what ebooks might be hiding in your content
  • SKILL.md covers Core Philosophy, What Makes This Ebook-Specific, Session Flow and Entry Modes (11 Total), plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ebook Discovery is an agent skill from robertguss/claude-code-toolkit. Surface ebook ideas you didn't know you had. Use when ready to discover what ebooks might be hiding in your content, expertise, or thinking. Supports both content-rich creators (blog posts, videos, newsletters) and those with unpublished expertise. Produces a curated list of ebook candidates ready for Concept Development. Handles multi-session discovery with living documents.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files and assets (for example `assets/templates/discovery-tracker-template.md`, `assets/templates/handoff-summary-template.md` and `references/candidate-assessment.md`).

It sits in Documents & Office, covering Blog and article writing and Newsletters. The repository describes itself as: A collection of custom skills that extend Claude's capabilities with specialized workflows, methods, and domain knowledge. The licence is MIT.

When your agent uses it

  • Ready to discover what ebooks might be hiding in your content
  • Tasks that involve Blog and article writing
  • Tasks that involve Newsletters

Example prompts

  • “/ebook-discovery”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Update the tracker with current state
  2. Review candidates surfaced this session
  3. Note where to pick up next
  4. Identify any candidates ready for Concept Development

What it can do on your machine

Read from SKILL.md and the folder at commit f7fd35e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ebook Discovery loads about 2k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 936 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~23k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from robertguss/claude-code-toolkit at commit f7fd35e, republished under its MIT licence (© robertguss). 936 words, ~1,996 tokens.

Download SKILL.mdSave it as .claude/skills/ebook-discovery/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
ebook-discovery
description
Surface ebook ideas you didn't know you had. Use when ready to discover what ebooks might be hiding in your content, expertise, or thinking. Supports both content-rich creators (blog posts, videos, newsletters) and those with unpublished expertise. Produces a curated list of ebook candidates ready for Concept Development. Handles multi-session discovery with living documents.

Ebook Discovery

Surface ebook ideas you didn't know you had. This is divergent/generative discovery ("what's here?") that feeds into Ebook Concept Development.

Core Philosophy

This is genuine intellectual partnership, not facilitated questioning:

  • Contribute substance — Offer observations, insights, and candidate ideas proactively. Don't just ask questions.
  • Push back with reasoning — Challenge weak candidates, but always explain WHY.
  • One question at a time — Never overwhelm with multiple questions.
  • Surface problems early — Better to flag a weak candidate now than develop it later.
  • Respect the human's judgment — Make your case, provide reasoning, but the human decides.
  • Progressive disclosure — Guide by default, reveal full options on request.

What Makes This Ebook-Specific

Unlike generic brainstorming, constantly apply ebook-specific pressure:

  • Format-fit calibration — Is this genuinely ebook-sized? Too thin = blog post. Too thick = full book.
  • Value density thinking — Ebooks are concentrated solutions. Every element must earn its place.
  • Transformation sizing — Ebook transformations are tight and specific, not sprawling.

Session Flow

First Session

1. Orientation Question:

"Let me understand your starting point. Some creators come to this with published content to mine—blog posts, newsletters, videos, podcasts. Others have deep expertise that hasn't made it into published form yet. Honestly, both are rich territory for ebook discovery. Which sounds more like you?"

2. Recommend Starting Mode:

Based on their answer, recommend a starting entry mode with reasoning:

  • Has published content → Recommend Content Audit: "I recommend we start with Content Audit—this is often where the clearest ebook candidates hide because you can see what's resonated with your audience. Does that feel right?"
  • Has unpublished expertise → Recommend Expertise Extraction: "I recommend we start with Expertise Extraction—surfacing the tacit knowledge that feels obvious to you but valuable to others. Does that feel right?"

3. Intent Question:

"One more thing before we dive in: What's driving you to create ebooks? Direct income? Building authority? Serving your audience? A passion project? Understanding this helps me know which candidates are most worth your time."

4. Create Tracker:

Ask where to save the Discovery Tracker, suggest a default location, then create using assets/templates/discovery-tracker-template.md.

5. Begin Exploration:

Dive deep into the selected mode. See references/entry-modes-guide.md for detailed guidance on each mode.

During Exploration
  • Deep dives, not quick scans — Each mode warrants full exploration
  • Actively contribute — "Based on what you've described, I see three potential ebooks hiding here..."
  • Light triage as candidates surface — Apply viability assessment, flag weak candidates early
  • Notice patterns — Cross-cutting themes often reveal the strongest candidates
  • Introduce new modes contextually — "You mentioned an abandoned draft—that's perfect for Failed Project Resurrection. Want to explore that?"
Candidate Management

During exploration:

  • Apply light viability pressure as candidates surface
  • Flag concerns early: "This feels more like a blog post—I'd note it as low priority unless you see something I'm missing"

At session transitions:

  • Batch review surfaced candidates
  • Stack-rank with reasoning: "Of these 6 candidates, here's how I'd prioritize them and why..."

In the tracker:

  • Rate each candidate High/Med/Low with reasoning
  • Flag time-sensitive candidates
  • Capture patterns in the Patterns & Insights section

See references/candidate-assessment.md for viability criteria and examples.

Session End
  1. Update the tracker with current state
  2. Review candidates surfaced this session
  3. Note where to pick up next
  4. Identify any candidates ready for Concept Development
Returning Sessions

When user returns with existing tracker:

  1. Read the tracker to orient
  2. Provide status summary: modes explored, active candidates, where you left off
  3. Ask where they'd like to focus
  4. Skip orientation if context is clear
Show full SKILL.md (368 more words)Show less

Entry Modes (11 Total)

Claude introduces modes progressively with reasoning. User can request the full list anytime.

Content-Based (mine what you've published):

  1. Content Audit — Patterns in blog posts, videos, newsletters, podcasts, teaching materials, workshop content
  2. Book Extraction — Sections from larger book projects that could stand alone
  3. Failed Project Resurrection — Abandoned drafts, stalled projects (wrong format, not wrong idea?)

Audience-Based (learn from your readers/viewers): 4. Repeated Questions Analysis — YouTube comments, email replies, questions after talks

Knowledge-Based (surface what you know): 5. Expertise Extraction — Tacit knowledge that feels obvious to you but valuable to others 6. Contrarian Positions — Views that push against mainstream thinking 7. Translation Bridges — Things you explain between worlds you inhabit 8. Personal Systems — Workflows, processes, disciplines you've developed

Archive-Based (dig through your thinking): 9. Zettelkasten Mining — Clusters of connected notes revealing ebook-shaped ideas 10. Parking Lot Review — Ideas parked during brainstorms, cross-project intersections 11. Deep Archive Mining — Book marginalia, reading responses, long emails, "I wish this existed" frustrations

For detailed guidance on each mode: See references/entry-modes-guide.md

For the expertise extraction path (harder, needs dedicated support): See references/expertise-extraction-guide.md

Handoff to Concept Development

A candidate is ready for Concept Development when:

  • Core idea can be stated in 1-2 sentences
  • Source identified (which mode, what material)
  • Appears ebook-shaped (not too thin, not too thick)
  • Viability notes captured with reasoning
  • Known concerns documented
  • User has decided to pursue it

Use assets/templates/handoff-summary-template.md for clean handoff.

Note: "This candidate is ready for the Ebook Concept Development skill."

Working Document

Use assets/templates/discovery-tracker-template.md for the living document.

Create after orientation is complete. Update at milestones, not constantly.

Reference Files

Load as needed during sessions:

  • references/entry-modes-guide.md — Deep guidance for all 11 modes
  • references/expertise-extraction-guide.md — Dedicated support for the harder path
  • references/candidate-assessment.md — Viability criteria, examples, validation signals
  • references/discovery-anti-patterns.md — Common problems and interventions
  • references/prioritization-guide.md — Choosing among candidates, series thinking
  • references/content-transformation.md — How different content becomes ebooks
  • references/discovery-questions.md — Powerful question toolkit

Key Reminders

  • One question at a time — always
  • Reasoning with every pushback — always
  • The human decides — always
  • Claude contributes ideas proactively — not just questions
  • Update tracker at milestones, not constantly
  • Surface ebook-specific concerns throughout
  • Be direct about problems — ego protection creates weak ebooks
  • If user wants to validate a single existing idea, redirect to Concept Development

© robertguss, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references, assets) in skills/ebook-factory/ebook-discovery of robertguss/claude-code-toolkit.

  • SKILL.md
  • assets/templates/discovery-tracker-template.md
  • assets/templates/handoff-summary-template.md
  • references/candidate-assessment.md
  • references/content-transformation.md
  • references/discovery-anti-patterns.md
  • references/discovery-questions.md
  • references/entry-modes-guide.md
  • references/expertise-extraction-guide.md
  • references/prioritization-guide.md

Open the folder on GitHubat commit f7fd35e

Compare with similar skills

Ebook Discovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ebook Discovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ebook Discovery this skillrobertguss/claude-code-toolkit123—~2kAutomated safety check: PassMIT
Voice Buildercharlie947/social-media-skills3.8k—~3.3kAutomated safety check: PassMIT
Humanizer Zhai-zixun/humanizer-zh177—~1.2kAutomated safety check: PassMIT
Content Writer Agentmastra-ai/mastra29k—~1.3kAutomated safety check: PassCustom licence
Content Strategy And Assemblyjacob-dietle/context-os111—~3.1kAutomated safety check: PassMIT
Linkedin Writerflaqai/backlink_skills754—~6kAutomated safety check: PassMIT

Similar skills

  • Voice Builder

    charlie947/social-media-skills

    Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing.

    3.8k GitHub stars~3.3k tokensUpdated 24 days ago
    Writing & ContentAuto-check passed
  • Humanizer Zh

    ai-zixun/humanizer-zh

    Remove signs of AI-generated, translated, or overly mechanical Chinese prose.

    177 GitHub stars~1.2k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed
  • Content Writer Agent

    mastra-ai/mastra

    Authoring playbook for building agents that draft written content — blog posts, marketing copy, social media posts, newsletters, product descriptions, landing pages, or ad copy.

    29k GitHub stars~1.3k tokensUpdated today
    Writing & ContentAuto-check passed
  • Content Strategy And Assembly

    jacob-dietle/context-os

    This skill should be used when producing content (newsletter posts, blog posts, LinkedIn posts) from existing corpus material.

    111 GitHub stars~3.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Linkedin Writer

    flaqai/backlink_skills

    LinkedIn-native long-form article and newsletter writing workflow for LinkedIn and Google-to-LinkedIn topic discovery, business-depth research, professional thought leadership, evidence-led…

    754 GitHub stars~6k tokensUpdated 15 days ago
    Writing & ContentAuto-check passed
  • Create Article

    Abilityai/cornelius

    Create long-form articles from knowledge base insights. An agent skill from Abilityai/cornelius.

    109 GitHub stars~3k tokensUpdated yesterday
    Writing & ContentAuto-check: notes

More from robertguss/claude-code-toolkit

All 16 skills in this repo
  • Brainstorm

    robertguss/claude-code-toolkit

    Collaborative brainstorming partner for multi-session ideation projects.

    123 GitHub stars~1.7k tokensUpdated 23 days ago
    Auto-check passed
  • Voice Capture

    robertguss/claude-code-toolkit

    This skill should be used when extracting voice profiles from sample text, creating voice documentation, or matching a specific writing style.

    123 GitHub stars~1.7k tokensUpdated 23 days ago
    Auto-check passed
  • Dhh Writing

    robertguss/claude-code-toolkit

    This skill should be used when writing in the distinctive style of David Heinemeier Hansson (DHH).

    123 GitHub stars~1.6k tokensUpdated 23 days ago
    Auto-check passed
  • Pragmatic Writing

    robertguss/claude-code-toolkit

    This skill should be used when writing technical content in the style of Hunt/Thomas (The Pragmatic Programmer) and Joel Spolsky (Joel on Software).

    123 GitHub stars~1.5k tokensUpdated 23 days ago
    Auto-check passed
  • Writing Orchestration

    robertguss/claude-code-toolkit

    This skill should be used when orchestrating complex writing workflows with multiple phases.

    123 GitHub stars~1.9k tokensUpdated 23 days ago
    Auto-check passed
  • App Store Opportunity Research

    robertguss/claude-code-toolkit

    Full-pipeline iOS App Store opportunity research. An agent skill from robertguss/claude-code-toolkit.

    123 GitHub stars~5.6k tokensUpdated 23 days ago
    Auto-check passed

Questions about Ebook Discovery

What does Ebook Discovery do?

Surface ebook ideas you didn't know you had. An agent skill from robertguss/claude-code-toolkit. Ebook Discovery is an agent skill from robertguss/claude-code-toolkit. Surface ebook ideas you didn't know you had.

When should I use Ebook Discovery?

Ebook Discovery fits situations like: ready to discover what ebooks might be hiding in your content; tasks that involve Blog and article writing; tasks that involve Newsletters.

How do I install Ebook Discovery in Claude Code?

Run `npx skills add robertguss/claude-code-toolkit --skill ebook-discovery -a claude-code`. Or copy the skill folder (skills/ebook-factory/ebook-discovery in robertguss/claude-code-toolkit) into .claude/skills/ebook-discovery in your project. Claude Code loads it when a task matches its description.

How do I install Ebook Discovery in Codex?

Run `npx skills add robertguss/claude-code-toolkit --skill ebook-discovery -a codex`. Or copy the skill folder (skills/ebook-factory/ebook-discovery in robertguss/claude-code-toolkit) into .agents/skills/ebook-discovery in your project. Codex loads it when a task matches its description.

Can I use Ebook Discovery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add robertguss/claude-code-toolkit --skill ebook-discovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ebook-discovery, .gemini/skills/ebook-discovery, .github/skills/ebook-discovery and .opencode/skills/ebook-discovery in your project.

What does Ebook Discovery need to run?

SKILL.md names no scripts, command-line tools or credentials: Ebook Discovery is instructions for the agent only.

Does Ebook Discovery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ebook Discovery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ebook Discovery use?

Ebook Discovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ebook Discovery use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 21k tokens, read only when the agent opens those files.

What are the alternatives to Ebook Discovery?

Skills that share tags, products or a category with Ebook Discovery: Voice Builder (charlie947/social-media-skills, 3.8k stars), Humanizer Zh (ai-zixun/humanizer-zh, 177 stars), Content Writer Agent (mastra-ai/mastra, 29k stars) and Content Strategy And Assembly (jacob-dietle/context-os, 111 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ebook Discovery?

robertguss (a GitHub user) maintains it in robertguss/claude-code-toolkit, which has 123 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 16, 2026.

Source: robertguss/claude-code-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.