book-to-skill
Skill1 starsChanged 23 days agoMITView on GitHub
Turn a book, PDF, or long article into a skill draft with reference chapters and a glossary. Use when converting long-form source material into a reviewable draft rather than a finished skill.
- Installs packages
20 other projects use a version of this.
Adopted by
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- shaunmarsden/book-to-skilltheir own version, first seen Nov 3, 2026
- JustinTSmith/ai-operator-skillstheir own version, first seen Oct 11, 2026
- c-ibarra/ObsidianKnowledgeCuratortheir own version, first seen Oct 9, 2026
- SanHsien/book-to-skilltheir own version, first seen Sep 27, 2026
- johnwick020213/skilltheir own version, first seen Sep 21, 2026
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- virgiliojr94/book-to-skill★ 37ksame name
- apple-ouyang/book-to-skill★ 148same name
- markoblogo/abvx-agent-skills★ 16same name
- carpatia77/sop-extractor★ 11same name
- CashewTeam/Con11-AI-Skills★ 8same name
- huntsyea/thinking-skills★ 4same name
- Linearl/reasonix_skill_repo★ 3same name
- 13531276085a-create/claude-skills★ 1same name
- lyh843/AgentSkills★ 1same name
- SanHsien/book-to-skill★ 1same name
10 more not listed
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 repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- .gemini/AGENTS.mdAGENTS.md
- .cursor/rules/agent-foundry-orchestrator.mdcCursor rule
- .cursor/rules/agent-foundry-skills.mdcCursor rule
- web/llms.txtllms.txt
- anti-slopSkill
- api-designSkill
- automation-pickSkill
- bottleneck-gatingSkill
- budget-guardSkill
- cache-identitySkill
- constraint-then-solveSkill
- context-optimizationSkill
- cron-troubleshootSkill
- e2e-test-strategySkill
- engram-routingSkill
- execution-observabilitySkill
- fallback-model-routingSkill
- feedback-loopSkill
- judge-integritySkill
- knowledge-extractSkill
- landscape-firstSkill
- measure-firstSkill
- plan-before-codeSkill
- plan-then-actSkill
- prompt-disciplineSkill
- pushback-when-wrongSkill
- quality-protocolSkill
- read-before-buildSkill
- re-verify-findingsSkill
- session-closeoutSkill
- session-distillSkill
- show-your-workSkill
- structured-output-contractSkill
- verify-firstSkill
- workflow-decomposeSkill
- agent-memory-vaultSkill
- agent-team-standardsSkill
- autonomous-briefingSkill
- chrome-devtools-mcp-bridgeSkill
- design-languageSkill
- funnel-pr-guardSkill
- persistent-memorySkill
- sql-migration-trioSkill
- token-compressionSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 55
Add frontmatter: license, author, status: draft, source: local.
- Distinctive: line 57
Add at least two anti-patterns and at least two verification checks.
“Common” is measured: kept by at least 6 in 10 of the 18 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 to Skill
Extracts a long document into chapter references, a glossary skeleton, and a
minimal SKILL.md. The output is a draft. A human writes the procedure and
passes the quality gates.
Procedure
What ships
skills/optional/book-to-skill/scripts/book_to_skill.py.
PDF input requires pypdf (pip install pypdf). Markdown, text, and URLs use
the standard library. URL input fetches the document once.
Usage
python skills/optional/book-to-skill/scripts/book_to_skill.py \
--input=book.pdf --skill-name=my-book --output-dir=plans/skills/drafts/my-book
python skills/optional/book-to-skill/scripts/book_to_skill.py \
--input=chapter.md --output-dir=plans/skills/drafts/my-chapterThere is no extract subcommand: pass the flags directly. Drafts belong under
the gitignored plans/skills/drafts/ tree. The script does not enforce the
destination, so choose it deliberately; never point it at skills/.
What it actually produces
- Up to 30 sections, split on Markdown H1/H2 headings or PDF page headings
references/ch-NN-<slug>.mdfor each sectionassets/glossary.jsonwith bolded capitalized terms (definitions empty)assets/summary.jsonwith section and term counts- A minimal
SKILL.mdcontaining an outline, key concepts, and reference links
It does not generate 3-7 instructions per chapter, does not validate the draft,
and does not add license, author, status, or source metadata.
Human completion pass
- Add frontmatter:
license,author,status: draft,source: local. - State one trigger sentence, then a procedure with verifiable steps.
- Add at least two anti-patterns and at least two verification checks.
- Run
./.venv/Scripts/python.exe scripts/foundry-eval.py --target <draft>/SKILL.md. - Promote only after the evaluator passes and a human reviews the draft.
Anti-patterns
- Copying chapter text verbatim instead of distilling procedures.
- Shipping the generated shell as a finished skill.
- Converting copyrighted material without checking the license.
- Placing drafts in
skills/, where discovery and packaging will pick them up.
Verification Checklist
- Every reference chapter is present and non-empty.
- The glossary is reviewed and definitions are filled in or removed.
- The draft has a single trigger, procedure, anti-patterns, and checks.
foundry-evalpasses before the draft leavesplans/.
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.

