Overview
Close reading, not shortening. It reconstructs the author's argument: the central claim, how the reasoning is built, where the support actually sits, what is only an example quietly promoted into a rule, which premises go unstated, and how a skeptic would push back. Modes on demand: quick gist, deep argument breakdown, a mind-map-ready knowledge map, the Feynman check (you explain, gaps get located, then the corrected version, an analogy and a review plan), or whole-book chapter mapping and synthesis.
Very long material is split on content boundaries, digested part by part and synthesized once more; major claims record their relation to the ones above them, evidence entries are pinned to page or section, and incomplete extraction is stated rather than leaned on.
It works only on material you hand over — finding sources belongs to deep research, templated exec briefs to the summarizer. Notes, claim maps and recall cards write back to your workspace or Notes, durable and revisitable.
Where it helps
- Read a whole book into a chapter map plus a Feynman recall plan
- Decompose a long paper into an argument tree and evidence ledger
- Generate a mind-map-ready knowledge map for course material
- Use feynman mode to find where your closed-book explanation breaks and fix it with an analogy
#reading#documents#extraction#qa
Examples
Examples describe the request and the shape of the expected deliverable; they are not completed run results.
01Example prompt
Deep-read chapter 6 of Thinking, Fast and Slow in whole-book mode: chapter thesis, recurring evidence and cross-chapter tensions — not a summary log.
Expected output
Chapter-to-thesis mapping, a page-pinned evidence list and the tension set, saved in your workspace.
02Example prompt
I can't explain this Bayesian-inference chapter closed-book. Run the Feynman mode: I'll explain, you locate the gaps, then give the corrected version and one strong analogy.
Expected output
A gap diagnosis, a tightened corrected explanation and recall-plan cards.
Requirements and limits
- Install platforms
- iOS: iOS · Android: Android
- Script runtime
- No script runtime (guidance and workflow)
- Minimum app version
- iOS: 1.7.59
Reviewed permission scope
iOS · Android
- Capabilities
- Read workspace filesWrite workspace files
- Review decision
- Approved
- Review stage
- Static content review
- Reviewed on
- 2026-10-28
Implementation and runtime details
- Adaptation stage
- frozen
iOS
- Capabilities
- Read workspace filesWrite workspace files
Android
- Capabilities
- Read workspace filesWrite workspace files
License and source
Source and trace details
License
MIT
MIT (root LICENSE)
The pinned skill subtree and shipped references were audited; full applicable license and per-file adaptation/asset notes are preserved under references/licenses/ and references/PROVENANCE.md.
- Source
- https://github.com/alirezarezvani/claude-skills
- Upstream path
- research/deepread
- Source checked
- 2026-10-26
- Publisher
- JiangNanGenius
- Publication commit (retrieval)
- 25e07dbeeb6cc93c2fe83ddc72a34302cc40832a
- Audited source commit
- 84c524b6fb483e4cad94db076e7d9c9962966c19
- Signed catalog digest
- iOS 46196ba57ed7ea7f22085e74b113207f31193e820ab8983cf7a60eee953f2340 · Android 16de89d019e2057804a40f215485ccb09d5495a25864b34d681168eeaf8f9697
- Publication snapshot (UTC)
- 2026-10-31
Publication commit 25e07dbeeb, audited source 84c524b6fb; catalog digest iOS 46196ba57ed7… · Android 16de89d019e2….
Versions and status
Version records ship with the signed catalog; the target and released versions are shown below.
- Adaptation
- Ready
- Publication state
- Curated skills are available
- Released version
- 1.0.1