textbook-distillation

textbook-distillation is a skill for Claude Code, Codex from Lingtai-AI/lingtai. It costs 116 tokens per session (2,767 once invoked), scanned A, original, Apache-2.0.

A process for turning a textbook or other long technical source into a self-paced learning course. It creates a chapter map, lesson plan, and HTML notes with examples, exercises, and questions.

In plain words
What is it for?
Use it to build learning material from a textbook, technical document, lecture transcript, or set of papers.
Why use it?
It breaks a large source into lessons that can be studied independently. The explanations are rewritten in new words instead of copying the source.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build learning material from a textbook, technical document, lecture transcript, or set of papers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lingtai-ai/lingtai/textbook-distillation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Lingtai-AI/lingtai --skill textbook-distillation
Clone the repo
git clone --depth 1 https://github.com/Lingtai-AI/lingtai

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for textbook-distillation

README.md
[![agentmods](https://agentmods.dev/badge/skills/lingtai-ai/lingtai/textbook-distillation/github.svg)](https://agentmods.dev/skills/lingtai-ai/lingtai/textbook-distillation)
Your own site
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/textbook-distillation"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/textbook-distillation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for textbook-distillation

Your own site · 80×15
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/textbook-distillation"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/textbook-distillation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,767 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.02767
Opus 5 $0.00058 $0.01384
Sonnet 5 $0.00023 $0.00553
Haiku 4.5 $0.00012 $0.00277

Measured 6d ago against content hash 1000f8dd5646, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

textbook-distillation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

tui/internal/preset/skills/textbook-distillation/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Textbook Distillation — Self-Paced Learning Tracks

You are helping a human teach themselves from a textbook (or a long technical document, lecture transcript, or paper set) without a live instructor. Your job is to distill the source into a structured learning track and ship self-contained HTML lecture notes in the style the human asks for: extract the concepts, structure, and worked logic, then re-explain them in your own words with your own examples. Distillation is never reproduction of the author's text. Read Source limits & safety before you intake anything — those boundaries shape every later step.

When to use

The frontmatter description carries the triggers and anti-triggers. Two boundaries deserve restating here: an ask framed as "summarize the whole book so I can skip buying it" or "paste me the chapter" crosses the copyright line — decline it and offer a legitimate distillation instead; and material the human cannot point to a legitimate source for is out of scope entirely. Both are spelled out under "Source limits, copyright & safety" below.

Workflow at a glance

intake → chapter map → lesson plan → (per lesson) HTML lecture notes → review loop

Work the phases in order. Do not jump to generating HTML before the human has seen and approved the chapter map and lesson plan — that approval is what keeps the track aligned to their goal, not your guess at it. This is a multi-round, human-in-the-loop flow: talk to the human through the active user-facing channel (mail/email or the relevant chat bridge), not internal scratch/text output, because each phase needs their input.

Phase 1 — Intake the source

Goal: know exactly what you are distilling and confirm you are allowed to.

  1. Identify the source precisely. Title, author, edition, and the format you have access to (a PDF in the project, a URL, the human's own notes, a file the human pasted). Record the path or link — you will cite it in every artifact.
  2. Confirm authorization and scope. Ask the human: do they own/have legal access to this material? Which parts do they want covered — whole book, a range of chapters, one topic? Do not proceed on material they cannot point to a legitimate source for.
  3. Capture the learning goal. Why are they studying it — exam, project, curiosity, teaching it onward? Their level (beginner / refresher / advanced)? Time budget (one weekend vs. a semester)? These set lesson granularity.
  4. Capture style constraints early (see Style constraints). Collect them now so the lesson plan and the HTML are designed for them, not retrofitted.

Read the full file on GitHub · 224 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago Changed · -4 lines · -46 tokens per session 1000f8dd5646
  2. 9d ago First seen · 228 lines · 162 tokens per session scan A b8e26581bb69

Subscribe to this mod's changes

textbook-distillation is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It adds 116 tokens to every session and 2,767 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.