book-study
Skill2 starsChanged 7 months agoMITView on GitHub
Reading coach: guides users through books systematically with knowledge compilation, mastery testing, spaced repetition, and knowledge querying. Triggers on "read this book", "book study", "start studying", "/book-study".
3 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- mtibebu/technical-learning-labtheir own version, first seen Nov 8, 2026
- sanyuan0704/code-review-expertedited, first seen Oct 8, 2026
- sanyuan0704/sanyuan-skillsedited, first seen Apr 14, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- sanyuan0704/code-review-expert★ 3.9k35% same
- sanyuan0704/sanyuan-skills★ 3.9k35% same
Wrote their own version · 1
- mtibebu/technical-learning-lab★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- skills/coding/redis-agent-skills/AGENTS.mdAGENTS.md
- skills/coding/redis-agent-skills/CLAUDE.mdCLAUDE.md
- agent-browserSkill
- autopilotSkill
- brainstormingSkill
- browser-useSkill
- cavemanSkill
- androidSkill
- brand-guidelinesSkill
- canvas-designSkill
- frontend-designSkill
- supabase-postgres-best-practicesSkill
- theme-factorySkill
- vercel-react-best-practicesSkill
- web-design-guidelinesSkill
- context7-aware-codingSkill
- document-intakeSkill
- explore-codebaseSkill
- find-skillsSkill
- finishing-a-branchSkill
- ohc-coding-disciplineSkill
- pdfSkill
- ralphSkill
- requesting-code-reviewSkill
- retrospectiveSkill
- seo-auditSkill
- skill-creatorSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
7 rules. 2 are common, 0 are distinctive, and 5 are very specific to this project.
2
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 65
File naming: All lowercase, hyphen-separated.
- Very specific: line 77
Check if book-wiki/<book-slug>/ exists
- Very specific: line 163
Read study-plan.md, confirm current chapter
- Common: line 167
Probe intuition: Ask what they _expect_ the author to argue, so they read with a hypothesis to test
- Very specific: line 170
Update study-plan.md status to "Guided"
- Common: line 176
When user comes back after reading a chapter:
- Very specific: line 180
Update study-plan.md status to "Ingested"
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Book Study — Reading Coach
Guide users through books systematically using active recall, mastery learning, and spaced repetition.
Mastery Scale (4-Criterion Rubric)
| Level | Criteria | Description |
| Accurate | Truth | Does it match what the book actually says? |
| Explained | Reasoning | Can the user articulate why, not just what? |
| Applied | Utility | Can the user apply it to a novel, real-world scenario? |
| Discriminated | Contrast | Can they distinguish it from similar or related concepts? |
Mastery Threshold: >= 3/4 per question AND >= 80% overall for the chapter.
Usage
/book-study <book-name> # Start a new book or resume progress
/book-study <book-name> --chapter 3 # Jump to chapter 3
/book-study ingest # Compile current chapter to wiki
/book-study query <keyword> # Query the knowledge base
/book-study review # Spaced repetition review
/book-study compare <book-A> <book-B> # Cross-book comparison
/book-study questions # View open questions
/book-study status # View all reading progressData Structure
Wiki defaults to book-wiki/ under the current project root.
book-wiki/
├── index.md # Global index: all books + cross-book concepts
├── log.md # Append-only operation log
├── <book-slug>/ # One directory per book
│ ├── meta.md # Book metadata (title, author, reading status)
│ ├── study-plan.md # Reading plan + progress tracking
│ ├── mastery-map.md # Mastery status map
│ ├── chapters/ # Chapter summaries
│ ├── concepts/ # Core concepts from the book
│ ├── cases/ # Cases, stories, experiments
│ ├── models/ # Frameworks, models, methodologies
│ ├── quotes/ # Notable quotes
│ └── questions/ # Questions raised during reading
└── cross-book/ # Cross-book knowledge
├── concepts/ # Shared concepts across books
└── comparisons/ # Cross-book comparisonsFile naming: All lowercase, hyphen-separated. Book slug: book title in pinyin or English abbreviation (e.g. thinking-fast-and-slow).
Cross-references: [[concepts/xxx]] within a book, [[/cross-book/concepts/xxx]] across books. Obsidian-compatible.
Learning Flow
Phase 0: Open a Book
On first /book-study <book-name>:
- Check if
book-wiki/<book-slug>/exists- Yes → read
study-plan.md, restore progress (see "State Restoration") - No → initialize new book
- Yes → read
- New book initialization (interactive — ask one at a time):
- What format do you have? (physical / ebook / PDF)
- Why are you reading this book? What problem are you trying to solve?
- How familiar are you with this domain? (beginner / some background / experienced)
- Rough timeline to finish?
- Generate
meta.md:
# <Book Title>
- **Author**: XXX
- **Category**: Psychology / Economics / Tech / ...
- **Status**: In Progress
- **Started**: YYYY-MM-DD
- **Core Question**: What question does this book try to answer?
- **One-line Review**: (fill after finishing)- Generate
study-plan.md:
# <Book Title> Study Plan
## Info
- **Title**: XXX
- **Author**: XXX
- **Total Chapters**: XX
- **Goal**: user's problem to solve
- **Timeline**: X weeks
- **Started**: YYYY-MM-DD
## Chapter Plan
| # | Chapter | Core Question | Status | Mastery | Date |
| --- | ------------ | ------------------------- | ----------- | ------- | ---- |
| 1 | Chapter Name | What this chapter answers | Not Started | - | - |
### Status Legend
- Not Started
- Guided (pre-reading done, ready to read)
- Reading
- Ingested (compiled, pending test)
- Mastered (test passed)
- Needs Review (test failed)
## Current Position
- **Current Chapter**: Chapter X
- **Next Action**: guide / read / ingest / test / review- Generate
mastery-map.md:
# <Book Title> Mastery Map
## Concepts
| Concept | Chapter | Status | Last Tested | Next Review |
| -------------------------- | ------- | ------ | ----------- | ----------- |
| (auto-populated on ingest) | | | | |
## Models
| Model | Chapter | Status | Last Tested | Next Review |
| ----- | ------- | ------ | ----------- | ----------- |
## Stats
- Total knowledge points: X
- Mastered: X (X%)
- Due for review: X
- Untested: XPhase 1: Pre-Reading Guide (before each chapter)
Purpose: activate prior knowledge, set reading questions.
- Read
study-plan.md, confirm current chapter - Design 2-3 pre-reading questions following these principles:
- Connect to user's goal: Tie back to the problem they stated in Phase 0
- Activate prior chapters: Reference concepts already mastered ("You learned [X] last chapter — how do you think that relates to this chapter's topic?")
- Probe intuition: Ask what they expect the author to argue, so they read with a hypothesis to test
- Keep it concrete: Not "What do you think about XX?" but "If you had to solve [specific scenario], what would you do right now?"
- Present questions and send user off to read
- Update
study-plan.mdstatus to "Guided"
If user is a complete beginner (diagnosed in Phase 0), do a brief Socratic warm-up on foundational concepts before sending them to read.
Phase 2: Read + Compile (Ingest)
When user comes back after reading a chapter:
- Accept user input (notes, verbal summary, highlights, raw text)
- Execute ingest (see "Knowledge Compilation" section below)
- Update
study-plan.mdstatus to "Ingested"
Extended content
This repository enforces a short root SKILL.md. Continue with references/skill-body-continuation.md for the rest of the original skill body.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

