More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    literature-notes: reading notes for academic research

    1

    8 agent skills that turn academic PDFs into a structured, queryable wiki of reading notes anchored to pages, citations and your research scope.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    literature-notes: reading notes for academic research

    Example session with this skill installed

    /literature-notes-annotate ~/papers/vaswani-2023-attention-is-all-you-need.pdf --pages 5 --focus "multi-head attention"

    • Read your context and instructions
    • Compiled the literature-notes

    Summary

    Read page 5 of Vaswani et al. (2023) and wrote 1 reading note, anchored to the page and cited in APA 7, the norm chosen at setup. The source record already existed, so only the note was created.

    Created

    FileKindPageTags
    notes/vaswani-2023--p5--multi-head-attention.mdsummary5attention, transformer

    The note

    ---
    type: Reading Note
    source_id: '[[vaswani-2023]]'
    page: 5
    note_kind: summary
    tags: [attention, transformer]
    citations:
      apa7:
        text: (Vaswani et al., 2023, p. 5)
    ---
    
    > "Multi-head attention allows the model to jointly attend to information
    > from different representation subspaces at different positions."
    
    ## Configuration used
    
    - h = 8 parallel attention heads.
    - dk = dv = dmodel / h = 64 per head, so the total cost is similar to
      single-head attention at full dimensionality.
    

    Next steps

    • Run /literature-notes-query --tag attention to see everything you have on this idea.
    • After a few more sources, run /literature-notes-review to confront your notes with the research scope.
    • Run /literature-notes-validate --check-quotes before you commit .literature-notes/, to confirm each quote appears on the page you cited.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A system of 8 agent skills that turns academic PDFs (articles, dissertations, theses, books) into a structured LLM wiki of reading notes, anchored to page numbers, cited in the norm your research follows, and read against your research scope.

    Why I built it

    I built these skills to help me study and write my master's dissertation. Two goals shaped them:

    1. A second brain for academic research. Every reading becomes small, linked, searchable notes, each tied to a page and to the question I am asking. I can find what I read, and see how one author connects to another.
    2. Input for writing. The notes keep the quote, the page and the citation in one consistent structure, so an agent, or I, can draft from them and every claim traces back to its source. The pack does not write the paper for you. It gives you material you can trust and trace.

    The aim was a system that is easy to control and to interact with: plain Markdown files that you own, a handful of commands, and a workflow you can see.

    What you get

    • Setup, research scope, annotate, query, review and validate, as one workflow.
    • Your citation norm. Setup asks which norm you follow (APA, ABNT, MLA, Chicago or another formal norm), looks up the rules, shows you a draft and freezes it only after you approve. Every note carries its citation in that norm.
    • Page handling that matches your source: cite PDF pages or printed pages, with an offset when they differ.
    • Three note kinds: authorial (your own idea), interpretive (your reading of the author) and summary (a neutral account).
    • A research scope (RESEARCH.md) and a controlled glossary (Glossary.md) that every note is read against, and a review step that interviews you and updates them as your reading changes your mind.
    • Query by tag, source, note kind, page, influence links, verification status or free text.
    • Validation of broken references (unknown tags, dangling links, undefined glossary terms), with an optional check that each quote really appears on the page you cited.
    • A read-only HTML "second brain" with full-text search, backlinks and a link graph.
    • Diagrams of the workflow and two complete example bundles (APA 7 on two machine learning papers, and ABNT on judicial activism) that validate cleanly.

    Why it's different

    The notes stay accountable to your research question. A query only loads what matches, so the bundle can grow to hundreds of notes without bloating the context. Generated prose is written in your own language, and quotes stay in the source's language.

    Requirements

    Python 3. The skills install pyyaml and pypdf with pip on first use. literature-notes-review also uses the free third-party grilling skill. The HTML viewer loads fonts and libraries from public CDNs.

    Single-user license. Your notes are yours.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.

    Requires Python 3 and pip. The HTML viewer needs internet access for its CDN libraries. Notes and citations are generated by a model, so verify them against the original source (the optional quote check helps). The rules for your citation norm are drafted from the sources the agent finds and only take effect after you approve them. Single-user license.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 15 days ago

    Software
    Node.jsPython

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Listed15 days ago

    What's inside

    Frequently Asked Questions

    Any formal academic norm: APA, ABNT, MLA, Chicago or another. Setup asks which one you follow, looks up its rules, shows you a draft and freezes it only after you approve. Every note and source then carries its citation and reference in that norm. Official manuals are often paid, so the draft states which sources it used. Compare it with your own copy of the norm.

    Python 3. The skills install pyyaml and pypdf with pip the first time they run. Review also uses the free third-party grilling skill. The notes are plain Markdown, so they work in Obsidian, GitHub or any editor. The optional HTML viewer loads fonts and libraries from public CDNs when you open it.

    Yes. /literature-notes-review interviews you, one question at a time, about notes not yet reconciled with your scope, and updates RESEARCH.md and Glossary.md where your answers push them. It records the change as a decision, so you can see why your scope moved.

    Treat them as drafts that you verify. Each note is marked as generated, and you can list the ones nobody has confirmed. /literature-notes-validate --check-quotes also checks that every quote appears on the PDF page you cited, which catches wrong pages and altered quotes. It does not replace reading the original source.

    The 8 skills (setup, research scope, annotate, review, query, validate, visualize and a skill picker), two complete example bundles (APA 7 on two machine learning papers and ABNT on judicial activism), workflow diagrams, a changelog and the license. Documentation is also online, linked on this page.

    The skills follow the open SKILL.md standard, so they work with compatible agents such as Claude Code, Codex CLI and Cursor. Behavior depends on the model your agent runs, so try one PDF in your own setup before you rely on it.

    The pack itself does not upload anything. The text of the pages you ask it to read goes to whatever model your agent uses, as with any request you make to that agent. Your notes stay as files in your own project.

    Yes. Setup asks whether you cite PDF pages or printed pages, and each source can carry a page offset, so a quote taken from PDF page 12 can be cited as the printed page of the book.

    It is a single-user license: you can use the pack for your own research on your own devices. You cannot copy, resell or redistribute it, and a team needs one license per user. You own the notes, research files and glossaries you create with it. The license covers the pack, not your content.

    New in Research & Analysis