Home / tronghieu / agent-skills · skills/deep-reader/SKILL.md · GitHub

deep-reader skillA

deep-reader is agent-read markdown (skill) from tronghieu/agent-skills: Read, study, and answer questions about long books and papers without loading the whole text into one context window, keeping page-anchored notes as a reusable workspace. Use whenever the user asks to read, study, summarize, analyze, review, or answer questions about a long book, textbook, PDF, EPUB, thesis, dissertation, survey paper, or any document of roughly 50+ pages, in any language (Vietnamese "đọc sách", "tóm tắt sách", "phân tích luận án"). Also use when a `<slug>-notes/` workspace from.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Deep Reader

Read long books and papers the way a careful human researcher does: skim for
structure first, read deeply chapter by chapter with notes as you go, then
synthesize from the notes — never the raw text — at the end. The method comes
from Adler's *How to Read a Book*, SQ3R's Recite step, and Keshav's three-pass
method for papers.

## Why multi-pass, why notes

An LLM's attention dilutes over long contexts, and it loses track of material
buried in the middle of a big prompt ("lost in the middle"). Loading a
500-page book into one context and asking questions about it produces answers
that quietly forget chapter 3 by the time you're discussing chapter 12.

The fix is the same one human researchers use: never hold the whole book in
working memory at once. Read it in passes — first for structure, then chapter
by chapter for content — and externalize what you learn into note files as you
go. The notes become the durable memory; the book itself only needs to be
back in view when you're actively reading a specific chapter or verifying a
specific claim. Page numbers are the coordinate system that makes every claim
traceable back to the source, in this session or a later one.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add tronghieu/agent-skills/deep-reader@git:20260905.623c278
Exact content
mdr add tronghieu/agent-skills/deep-reader@sha256:ab2b51098aaa4a69

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7xgta7omajp54fhx.svg)](https://markdownregistry.com/a/art_7xgta7omajp54fhx)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.623c278 latest2026-09-05 623c278 14,367 BA view · diff
git:20260705.adf40c72026-07-05 adf40c7 14,772 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14367 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

tronghieu/agent-skills · 72 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7xgta7omajp54fhx
GET https://markdownregistry.com/api/v1/resolve?ref=tronghieu/agent-skills/deep-reader
GET https://markdownregistry.com/api/v1/blob/ab2b51098aaa4a6941cc79d7b1ce53f6891ee6e5c3253a3926864c3022623595

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from tronghieu/agent-skills

AGENTS.md agents
tronghieu/agent-skills · AGENTS.md
git:20260922.0785dc1 · audit A · 72 stars
CLAUDE.md claude
tronghieu/agent-skills · CLAUDE.md
git:20260905.20a4e97 · audit B · 72 stars
bmad-run-inspector skill
tronghieu/agent-skills · skills/bmad-run-inspector/SKILL.md · Inspect and explain bmad-loop run artifacts under `.bmad-loop/runs/`. Use for live health checks ("is it stuck?", "is…
git:20260905.623c278 · audit A · 72 stars
brainstorm-coach skill
tronghieu/agent-skills · skills/brainstorm-coach/SKILL.md · Coach structured brainstorming sessions on any topic: diverge on ideas together, then converge on priorities and next…
git:20260905.623c278 · audit A · 72 stars
critical-thinking skill
tronghieu/agent-skills · skills/critical-thinking/SKILL.md · Audit the reasoning of a document or argument (memo, proposal, investment analysis, board paper, article, the user's…
git:20260905.623c278 · audit A · 72 stars
cv-scorer skill
tronghieu/agent-skills · skills/cv-scorer/SKILL.md · Score candidate CVs on a 100-point scale against a Job Description. Use this skill when the user wants to evaluate…
git:20260403.cede59c · audit A · 72 stars
data-scientist skill
tronghieu/agent-skills · skills/data-scientist/SKILL.md · Act as an end-to-end data scientist: turn business questions into defensible analysis, validated models, and…
git:20260905.623c278 · audit A · 72 stars
design-thinking skill
tronghieu/agent-skills · skills/design-thinking/SKILL.md · Facilitate a full design-thinking engagement (Empathize, Define, Ideate, Prototype, Test) grounded in real user…
git:20260905.623c278 · audit A · 72 stars
diataxis-writer skill
tronghieu/agent-skills · skills/diataxis-writer/SKILL.md · Write, restructure, classify, and review documentation with the Diataxis framework. Use when the user asks to create…
git:20260905.981b761 · audit A · 72 stars
fiction-studio skill
tronghieu/agent-skills · skills/fiction-studio/SKILL.md · A complete fiction-writing studio, run as a team of named specialist agents, that guides an author from a bare idea to…
git:20260615.d190775 · audit A · 72 stars
manual-testing skill
tronghieu/agent-skills · skills/manual-testing/SKILL.md · Run a session-based manual test of the project's running app in one of five modes: exploratory, verification, smoke…
git:20260922.b4bfb22 · audit A · 72 stars
market-researcher skill
tronghieu/agent-skills · skills/market-researcher/SKILL.md · Conduct rigorous, citation-backed desk market research: quick go/no-go market scans, market sizing (TAM/SAM/SOM)…
git:20260710.b4648bb · audit A · 72 stars

Every file in tronghieu/agent-skills

Browse by kind, by grade A, or by owner.