Reading Books Skill — Development skill for Claude Code
Claude skill for reading notes in two layers: what the book says and what it means, plus a method card in skill grammar.
How to install Reading Books Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open EricD1012/reading-books-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Reading Books Skill does
Claude skill for reading notes in two layers: what the book says and what it means, plus a method card in skill grammar. Never writes the reader's personal takeaways.
Alternatives in Development
- Grammar Check — Identify grammar and flow errors with targeted fix suggestions 7.8k ★
- Fidelity — Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a let 3.6k ★
- Reader Review — reader skill — 苛刻读者版 669 ★
README
Reading Books — literal meaning and interpretation, not a book report
A Claude skill that turns a book into a **note whose spine can be read in ten minutes**: what the book says, what it means, and what method can be taken away from it. It is built for one book a day, for notes that can be searched back into six months later, and for a stack of notes that can later be merged into a skill.
It is built against three habits of language models asked to "analyze a book": blend the author's claims with the model's opinions, write the reader's "what this means for me" on the reader's behalf, and bury the useful method under a long report.
The rules that make it different
**Two layers, kept apart.** *Literal meaning* is what the book says: the question and answer, the skeleton, the core claims in the author's own words, the load-bearing cases, the author and era. *Interpretation* is what it means: the mechanism, the hidden assumptions, what holds and what does not, the concept tools, connections to other books, one contemporary test. Block quotes contain only the author's words. "The author says" and "I think" are never mixed in one sentence.
**No "what this means for me."** The skill never writes the reader's personal relevance, action items, or reflections. Reconciling the reader's own views, scoring the book's predictions against reality, and personal application all belong to the conversation after the reader has read. The note ends when the book ends.
**A napkin before the note.** If the book could leave only one formula, one diagram, one sentence: those three come first. A two-minute layer above the ten-minute layer.
**The method card is written in skill grammar.** Name as a verb phrase, trigger signals as observable phenomena, steps as actions with questions written verbatim, coaching questions, the conditions under which the method misleads, and a back-reference to source anchors. Cards from many books can be merged into a draft skill without re-reading
Related Skills
Ultra Goal Skill
UltraGoal — an Agent Skill that interviews you into a grounded goal (intent, anchor, boundary, droppable means
Translate Book
Claude Code skill that translates entire books (PDF/DOCX/EPUB) into any language using parallel subagents.
Dd Book
Open the Book to Knowledge and Action department (reflect stage) and route the request to one of its 45 atomic
Lt Bartini Method
LT method of Bushuev-Bartini-Kuznetsov as an agent skill: resolve contradictions by assigning physical dimensi
OCR
Run OCR on existing book page captures (Vision + agent re-reading)
Quick Eval
Quick job evaluation. Paste a JD and get a score plus one-paragraph summary. Faster than a full evaluate. Use
Related Agents
Book Distiller
Extract quotes and chapter summaries from books for the Library OS. Given a book title, author, and optional s
Diagram Engineer
Diagram-rendering specialist for books-pipeline networking/tech books. Owns lib/cisco_topology.py and lib/book
Codex Analyst
Token-heavy READ-ONLY analysis, codebase surveys, audits and inventories, executed by the Codex CLI rather tha