Material Learning Studio

Turn books, papers, and office documents into traceable, testable, offline learning pages.

Stars
★ 1.5k
Last updated
1mo ago
License
MIT
Primary language
Python

At a glance

How it runs
Agent plugin / skillCLI
Works with
Universal · cross-platformCodex · Claude Code
Cost
Free, no paid service needed
Setup effort
Low · running in minutes
You'll need
Python 3.10 or laterAn agent that can read files, run local commands, and recognize SKILL.mdShell / CLILocal filesystem
Typical use
Graduate researchers studying long papers or technical PDFs who need every major claim, method, and source location to remain traceable.
Not a fit if
  • Users limited to pure chat without filesystem access or Python execution
  • Users processing MOBI/AZW without Calibre installed
  • Teams expecting automatic installation of parsing or OCR dependencies
Maintenance
Commits in the last 6 monthslast commit 2026-10-19latest release v1.1.0 (2026-10-19)+9.3 ★/day over 7 days
Source review
82/100 · Good

What does this agent do, and when should you use it?

learn-from-materials is a cross-agent skill built on the Agent Skills specification for books, PDFs, slides, Word files, web pages, and multi-material collections. It combines a SKILL.md workflow with Python extraction and validation scripts, content protocols, HTML templates, and example knowledge bases, and it relies on a host agent that can read files and run local commands. Users choose between Quick Overview, which scans the full structure and reviews displayed citations, and Systematic Study, which adds full coverage, summary mapping, action-rule review, and an independent content pass. Deliverables include a traceable .learnkb/ knowledge base, a self-contained interactive HTML page, Markdown derived from the same data, bound page data, a delivery manifest, and a ZIP archive. The page includes framework maps, guided content, a glossary, action rules, dynamic self-checks, and local notes, while Apply This Methodology only creates a copyable prompt and does not run AI inside the page. Its scripts operate offline by default, install no dependencies automatically, and keep notes, learner profiles, and wrong-answer records in browser local storage.

The workflow starts with scripts/extract.py, which extracts text and source mappings from formats including PDF, EPUB, DOCX, PPTX/PPTM, HTML, Markdown, TXT, and RTF; MOBI/AZW/AZW3 requires Calibre's ebook-convert. After extraction, the agent reads the source and authors page.json, methods.json, and methodology.json; the scripts do not automatically create this learning content from the source text. scripts/methods.py bind and scripts/methodology.py bind then connect method cards, the integrated whole-material methodology, and page content through a shared data model. A Quick Overview uses scripts/prepare_quick.py to audit citations displayed in the final page, while Systematic Study additionally requires summary-ledger.json, action-rule-ledger.json, content-review.json, and a reviewed original-heading index for PDFs. Finally, scripts/finalize.py validates the selected depth's source and coverage records and produces HTML, Markdown, bound page JSON, the knowledge base, a delivery manifest, and a ZIP. Generated pages can show fine-grained PDF page, slide, or EPUB chapter locations and distinguish source-backed facts, uncovered areas, model-added content, and externally verified items.

  1. Graduate researchers studying long papers or technical PDFs who need every major claim, method, and source location to remain traceable.
  2. Educators turning slides, handouts, and supplemental documents into an offline page with a glossary, self-checks, and local notes.
  3. Analysts producing a quick but source-aware map of an industry report's arguments, limits, and action rules.
  4. Book learners converting EPUBs or extracted books into browsable knowledge bases and accumulating reusable method cards.
  5. Teams using Codex, Claude Code, WorkBuddy, or GitHub Copilot CLI that want a structured material-learning workflow inside an existing agent.

Key setup facts

Pulled from the install and usage notes below. The project README has the current values.

Config files
~/.agents/skills/learn-from-materials ~/.claude/skills/learn-from-materials ~/.copilot/skills/learn-from-materials page.json .learnkb/methods.json
Runtime
Python 3.10

How do you install or deploy this agent?

You need Python 3.10 or later and an agent that can read the material and skill directory, run local commands, and recognize SKILL.md. For the documented 1.0 release, extract learn-from-materials-1.0-release.zip and place its complete learn-from-materials/ directory in the client's skill search path. SKILL.md, scripts/, references/, and templates/ must sit directly inside that directory. Back up an existing directory of the same name before replacing it, then reload or restart the client.

You may instead install the repository's default branch, although it can differ from the 1.0 ZIP release. For a user-level Codex installation:

git clone https://github.com/dmoshehun-prog/learn-from-materials.git ~/.agents/skills/learn-from-materials

For Claude Code:

git clone https://github.com/dmoshehun-prog/learn-from-materials.git ~/.claude/skills/learn-from-materials

For GitHub Copilot CLI, one documented location is:

git clone https://github.com/dmoshehun-prog/learn-from-materials.git ~/.copilot/skills/learn-from-materials

No API credential is documented as required. The project does not automatically install optional parsers, OCR tools, or browser dependencies.

How do you use this agent?

After installation and client reload, attach or identify the material and state the desired learning depth. A first Systematic Study request is:

Please use learn-from-materials to systematically study this PDF and generate a traceable knowledge base and a learning page.

For a Quick Overview of slides:

Give me a quick overview of this PPT, keep per-slide sources, and generate an offline learning HTML.

If you omit the depth, the skill asks once. From the skill root, you can first inspect available parsing capabilities:

python3 scripts/extract.py --check

To run extraction manually, replace the placeholders with real paths:

python3 scripts/extract.py <material-path> --mode text --ocr auto --output-dir <topic>.learnkb

After the agent has authored page.json, methods.json, and methodology.json, bind the method data:

python3 scripts/methods.py bind --library <topic>.learnkb/methods.json --page page.json --knowledge-base <topic>.learnkb --output page-with-methods.json
python3 scripts/methodology.py bind --model <topic>.learnkb/methodology.json --page page-with-methods.json --knowledge-base <topic>.learnkb --output page-ready.json

For a Quick Overview, review displayed citations and then run:

python3 scripts/prepare_quick.py page-ready.json --knowledge-base <topic>.learnkb
python3 scripts/finalize.py page-ready.json --knowledge-base <topic>.learnkb --output-dir ./delivery --name learning-quick

For Systematic Study, prepare the required full knowledge base and review records before running:

python3 scripts/finalize.py page-ready.json --knowledge-base <topic>.learnkb --output-dir ./delivery --name learning-systematic

What are this agent's strengths and limitations?

Pros
  • A single content model drives the knowledge base, interactive HTML, and Markdown, reducing drift among delivery formats.
  • Fine-grained mappings cover PDF pages, PPT slides, and EPUB chapters while explicitly separating source facts, model additions, and external verification.
  • Systematic Study uses coverage, summary, action-rule, and independent content-review records; Quick Overview still scans the complete structure and reviews displayed citations.
  • Method cards retain stable IDs and versions, while synthesized methods receive new IDs and explicit parent references instead of overwriting source methods.
  • Scripts are offline-first and do not transmit materials; page notes, learner profiles, and wrong-answer records remain in local browser storage.
Limitations
  • The host agent must still read the source and author the page and method JSON files; the scripts do not automatically write the substantive learning content.
  • Python 3.10, filesystem access, and local command execution are required, so pure chat environments cannot perform extraction, coverage validation, or HTML rendering.
  • Scanned PDFs and image-heavy slides need separate OCR or vision capability; otherwise affected ranges remain explicitly unverified.
  • MOBI/AZW/AZW3 has no built-in fallback and depends on Calibre's ebook-convert.
  • Initial deliveries are static-only with visualReview: not-run; static and in-memory DOM checks do not constitute browser visual acceptance.

How does this agent compare with similar options?

The repository explicitly derives from two MIT-licensed projects: virgiliojr94/book-to-skill supplies material extraction, knowledge decomposition, and the base knowledge-base structure, while crayon-ai/book-to-webpage supplies the interactive page, themes, source display, and follow-up interaction design. learn-from-materials extends that foundation with a cross-agent Agent Skills workflow, two study depths, a versioned method library, an integrated whole-material methodology, coverage and content-review records, and an offline delivery pipeline. The upstream projects may be a narrower fit when only their foundational extraction or webpage conversion scope is needed; this repository is the broader option when one workflow must produce source-audited learning artifacts and reusable method records.

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
Material Learning Studio This agent 82 · Good Agent plugin / skillFree ★ 1.5k 1mo ago Python Codex · Claude Code
Pinvou Agent Desktop Workspace 56 · Major gaps Desktop appFree + model costs ★ 3k today Rust Codex · Claude Code · OpenAI API · Claude API
LLM Wiki 53 · Major gaps CLIFree + model costs ★ 1.8k 11d ago Python Codex · Claude Code · Claude.ai
LazyMind 61 · Some gaps Desktop appFree + model costs ★ 790 1d ago Go Codex

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Good
82/ 100 5-point scale 4.1 / 5
Trust 24/29
Reliability 9/14
Adaptability 15/18
Convention 15/18
Effectiveness 12/13
Verifiability 7/8
Why each dimension lost points
Trust24 / 29 · 4.1/5

SECURITY.md and SKILL.md limit processing to user-designated materials and output directories, say dependencies are not installed automatically, exclude unrelated credentials, prohibit active network transmission, and treat input as untrusted data. This supports high scores for least privilege, data-flow transparency, and external-effect controls. The privacy guidance identifies path and sensitive-content risks but relies mainly on users to inspect outputs before sharing, so sensitive-data handling is deducted. README says the skill asks once when learning depth is unspecified, recommends backing up before installation, avoiding overwrite, using a new delivery name, and preserving existing deliveries. These support confirmation and recovery, but there is no explicit confirmation gate for every action or general rollback mechanism. Source attribution is central to the workflow through locators, quotations, and source records.

Reliability9 / 14 · 3.2/5

README and SKILL.md consistently require coverage checks, source rereading, and phased review, while warning that mechanical validation does not establish semantic completeness. Parsing has fallbacks for many formats, but MOBI/AZW has no built-in fallback and scanned material depends on OCR or vision, limiting dependency availability. SECURITY.md says oversized inputs stop with an error, and the supplied tests cover some failure conditions, but the packet does not establish that user-facing failure messages are adequate across the workflow.

Adaptability15 / 18 · 4.2/5

The materials cover quick and systematic study, method libraries, follow-up questions, self-checks, updates, and many input formats, with explicit Chinese and English support. The skill clearly states that environments without filesystem access or Python can only use part of the workflow and identifies limits for scanned materials, long inputs, and browser verification. Its trigger description spans several tasks, including learning, summaries, application, and method retrieval, so trigger precision is not fully established. Python, client, and optional Node/Playwright requirements are listed, but compatibility still depends on each agent's skill discovery and local capabilities.

Convention15 / 18 · 4.2/5

Repository layout, reference routing, installation locations, commands, examples, and known limitations are described in detail. Stable IDs and version fields are specified, but the packet does not establish a comprehensive naming-change policy. The MIT license file is present. Version numbers, release notes, and migration information are provided, though the materials offer limited evidence of a maintained release-history process or long-term update commitment. A security reporting path is documented; however, publisher identity is unverified and the packet names no accountable maintainer or ongoing maintenance arrangement, so maintenance responsibility scores low.

Effectiveness12 / 13 · 4.6/5

Deliverables include offline HTML, Markdown derived from the same data, a knowledge base, source mappings, quizzes, and local notes. Shared canonical data and source hints support practical usability. The reusable method library, relationship maps, and coverage audits add value beyond ordinary summaries. Full rereading, ledgers, and phased review require substantial human and model effort, and long materials benefit from high-context models. Checkpoints and recovery help manage that effort, but the cost-benefit case is not fully established.

Verifiability7 / 8 · 4.4/5

The contracts call for source IDs, quotations, locators, fingerprints, coverage records, and review ledgers, and distinguish material-backed facts, uncovered areas, model additions, and externally verified items. README, SKILL.md, SECURITY.md, examples, and tests corroborate several boundaries, but the supplied files are only a sample and the README explicitly says screenshots are not independent acceptance evidence. Cross-source corroboration therefore falls short of full marks.

Risks and how to mitigate them
  • This review uses only the static file sample in the prompt; code was not run and generated results were not independently checked. Confidence is low.
  • Publisher identity is unverified. The materials say storage and processing of submitted content depend on the model platform's terms and account settings.
  • Scanned or image-heavy materials may need extra OCR or vision capability; MOBI/AZW formats have no built-in parsing fallback.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision f8849746d85c
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/learn-from-materials.svg)](https://followagents.com/en/agents/learn-from-materials)
<a href="https://followagents.com/en/agents/learn-from-materials"><img src="https://followagents.com/badge/learn-from-materials.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v1.1.0 1.1.0 release
    Release notes excerpt
    learn-from-materials 1.1.0 相对于 GitHub 正式版 1.0,本次完善来源优先的顺序学习流程、内容与关系复核、任务恢复及交付一致性。 - 来源优先的单元记录与确定性组装,同源派生页面、章节 Markdown 和出处映射。 - 框架/关系候选账本,逐单元原文回读,以及分开的正确性和原文遗漏/应用检查。 - 检查点恢复、依赖指纹、验收输入冻结和阶段耗时记录。 - 框架曲线连线、图外未连线清单、方向提示、出处浮片及窄屏/全屏改进。 - 交付包顶层的独立方法论 Markdown,以及统一的 1.1.0 元数据、中英文文档和当前顺序示例。 - 保留 GitHub main 中的安装/使用求助 issue 模板。 安装:解压 learn-from-materials-1.1.0.zip,保留完整 learn-from-materials 文件夹;文件夹顶层直接包含 SKILL.md、scripts、references、templates。更新已有安装时先备份旧目录,避免与旧并行文件混合。按客户端既有 skill 导入/搜索目录机制加载。 …
    View on GitHub ↗
  2. v1.0 1.0 release
    Release notes excerpt
    从 v0.2.0 升级到 1.0 release,完善材料复核、交付流程和学习页交互。 - 系统学习增加来源优先的第二遍内容复核,检查总结、规则、封闭清单及记录是否过期。 - 改进框架图分组、搜索、长标签布局、悬浮说明滚动和全屏交互;更新三主题与中英文界面。 - 统一快速了解的规范方法绑定、出处复核和完整交付流程,保留快速模式的轻量范围。 - 修复 Windows 命令行编码问题;保留证据文件字节,避免 Git 换行转换使哈希失效。 - 移除真实论文全文及其生成知识库,替换为自编、MIT 许可的三页教学 PDF 与配套示例。 - 同步版本、两份 README、示例索引和相对于 v0.2.0 的累积更新日志。 English …
    View on GitHub ↗

FAQ

Does it require an API key or network connection?
The repository scripts require no documented API key and operate offline by default without sending materials over the network. How the host agent stores or processes submitted content still depends on that platform, its account settings, and its terms.
Does Quick Overview only read the beginning of a document?
No. It scans the complete structure and reviews citations displayed in the final page, but it does not claim the exhaustive coverage required by Systematic Study.
What happens when a scanned PDF has no extractable text?
The workflow needs existing OCR or model-vision capability with access to the actual page images. Without it, affected ranges are flagged for OCR or visual review rather than treated as verified.
Does the generated webpage call an AI model?
No. Apply This Methodology constructs a prompt from the user's question, goal, constraints, and selected method; the user copies that prompt into the material conversation.
Do the validation checks prove that the result is correct and complete?
No. The content checker can bind evidence to an exact input version and detect missing mappings, stale records, and shortened enumerated lists, but it does not prove semantic truth or zero omissions. Browser visual acceptance is also a separate step.
Is Material Learning Studio free?
Yes. Material Learning Studio is free to use and does not need a paid service.
Is Material Learning Studio open source?
Yes. The source code is on GitHub (dmoshehun-prog/learn-from-materials) under the MIT licence.
Is Material Learning Studio safe to use?
FollowAgents' FARS review (Nov 08, 2026) scored Material Learning Studio 24/29 on trust and safety. None of the eight safety controls the review checks for was missing outright.
Is Material Learning Studio still maintained?
Development has slowed: the latest commit on GitHub is from 2026-10-19, within the last six months but not the last 30 days. The latest release is v1.1.0 (2026-10-19).
Who makes Material Learning Studio?
Material Learning Studio is published on GitHub by the account dmoshehun-prog. FollowAgents has not verified which person or company is behind that account.
Was this page helpful?
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related concepts