Literature Discovery

Community

scholay

literature-discovery

Systematically discover and shortlist academic literature for a research project. Use when building a reading corpus from scratch, expanding an existing one, filling topic or language gaps, or turning search results into a prioritized intake queue.

Overview

Publisher	scholay
Repository	`skills`
Skill name	`literature-discovery`
Stars	139
Forks	0
Bundled files	1
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by scholay on GitHub. Read the source before you install it.

Installation

Install the Literature Discovery AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/scholay/skills/tree/main/literature-discovery
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/scholay/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/literature-discovery .claude/skills/literature-discovery

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Literature Discovery in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Literature Discovery on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Literature Discovery is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Literature Discovery

The core problem

Most researchers start by downloading everything that looks relevant. This creates an unmanageable pile with no structure and no sense of what's missing. The alternative: build the corpus in deliberate waves, starting from a small seed set and expanding outward in three directions.

Workflow

1. Define scope before searching

Write one sentence: what is this research about, and what is it not about? This sentence is your filter for every candidate you encounter.

Then build a search matrix:

Axis	Examples
Topic terms	main concept + synonyms + older names
Region/context	geographic or institutional scope
Object type	what specific thing you're studying
Time period	historical range
Language	all relevant languages, not just English
Method	field methods you're comparing against

2. Start from a seed set, not a broad search

Pick 3–5 items you already know are strong:

One overview or survey paper
One foundational monograph or book
One case-study cluster
One methods paper

Do not start by downloading 200 results from a keyword search.

3. Expand in three directions from each seed

Backward — who does this paper cite? Follow references to earlier foundational work.

Forward — who cites this paper? Use Google Scholar, Semantic Scholar, or OpenAlex to find later work building on it.

Lateral — what related terms or adjacent topics does this paper not cover? Search those gaps explicitly.

4. Record every candidate before annotating

Keep a running candidate list. Add a row for every item you encounter, even if you don't have the PDF yet. Minimum fields per row:

title, authors, year
source (where you found it)
language
status: candidate / keep / exclude / needs_pdf / needs_translation
reason (one line)

Do not annotate or read deeply at this stage.

5. Check for coverage bias

Before promoting items to intake, ask:

Am I over-representing one language, one region, one time period?
Are there practitioner sources, grey literature, or non-English materials I haven't touched?
What would a critic say is missing from this list?

6. Promote only strong items

Only keep-status items move to the next stage (source intake). Everything else stays in the candidate list with a reason recorded.

Output expectations

A reusable search matrix
A candidate list with statuses and one-line reasons
A gap list: what's under-covered and why
A keep queue ready for source intake

Rules

Search in waves. One wave = one seed's full expansion before starting the next seed.
Never download everything from a keyword search in one pass.
De-duplicate before promoting: DOI first, then title + year, then manual check.
Keep translated titles and original titles together.
Record the search URL and date for every batch — you will need to verify later.
A candidate list with 200 items and no statuses is not useful. Triage as you go.

References

Read references/search-matrix.md for a reusable matrix template and project-specific axis examples.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/search-matrix.md2 KB

Frequently asked questions

What does the Literature Discovery AI skill do?

Why use Literature Discovery on TypingMind?

Because you install it once and use it with any model. Literature Discovery is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Literature Discovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/scholay/skills/tree/main/literature-discovery. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Literature Discovery?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Literature Discovery?

As many as you like. As long as a model supports skills, you can use Literature Discovery with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Literature Discovery AI skill free?

Yes. It is published on GitHub by scholay under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Html Ppt Zhangzara Cobalt Grid

nexu-io

OrganizationPopular

OpenDesign renewal + seat-expansion business case for a growing customer: realized value, usage proof, and the expansion ROI. Built as a decision-grade B2B sales deck for champion, finance approver.

Html Ppt Zhangzara Monochrome

nexu-io

OrganizationPopular

A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review…

Html Ppt Zhangzara Scatterbrain

nexu-io

OrganizationPopular

A design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty.

Create Agent Adapter

Create or modify Paperclip agent adapters across server, UI, and CLI surfaces. Use when adding support for a new CLI agent, API agent, custom process, or adapter package.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Literature Discovery

The core problem

Workflow

1. Define scope before searching

2. Start from a seed set, not a broad search

3. Expand in three directions from each seed

4. Record every candidate before annotating

5. Check for coverage bias

6. Promote only strong items

Output expectations

Rules

References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now