Source Intake

Community

scholay

source-intake

Organize, classify, and register raw research materials into a stable, trackable source layer. Use when processing newly collected PDFs, archives, image folders, or mixed downloads; assigning stable IDs; maintaining intake manifests; or deciding what type of object each material is before any processing begins.

Overview

Publisher	scholay
Repository	`skills`
Skill name	`source-intake`
Stars	139
Forks	0
Bundled files	2
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.
2 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 Source Intake 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/source-intake
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/source-intake .claude/skills/source-intake

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

Use it in TypingMind

Enable Source Intake 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 Source Intake 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 Source Intake 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.

Source Intake

The core problem

Research materials accumulate in chaotic ways: some arrive as standalone PDFs, some inside zip archives, some as image folders, some as web pages saved to disk. Processing them without first understanding what you have creates a false baseline — you think you've ingested everything when the most important items are still locked inside a zip file.

Rule zero: expand all archives before claiming anything is ingested.

Object types

Before assigning an ID to anything, classify it:

Type	Description
`source_pdf`	A PDF that can be processed directly
`derived_pdf`	A PDF you generate from images, scans, or web pages
`image_group`	A folder of images that form a logical unit (scanned pages, figures)
`dataset`	Structured data files (CSV, XLSX, JSON, GIS)
`reference_file`	Rights, permissions, licenses, or metadata files
`archive`	ZIP, RAR, or other compressed container — expand first, then classify contents
`ambiguous`	Needs a decision before it can be registered

Workflow

1. Inventory before touching

Before doing anything else, list what you have and where it came from. Keep a raw inventory file. Do not rename or move anything in the raw layer.

2. Expand all archives

Expand every archive into a staging area. Note the parent archive ID for each extracted file so you can trace it back later.

Update these manifests after expansion:

expanded_inventory — what came out of which archive
pending_pdf_candidates — PDFs waiting for registration
pending_image_groups — image folders waiting for a handling decision

3. Check for duplicates

Before assigning a new ID, check whether this item is already registered. Match on: DOI or URL first → title + year → manual review.

4. Assign stable IDs

Once an item is confirmed unique and classified, assign a stable ID. Recommended format:

Raw objects: RAW-#### (source as received, untouched)
Processed source objects: SRC-#### (stable, normalized copy)

Keep both IDs in your manifest so the chain from raw to processed is always traceable.

5. Normalize

Create one clean, stable copy of each source object:

PDF: copy with a stable filename into your normalized folder
Image group: document the group strategy before doing anything else (will this become a derived PDF, or stay as individual images?)
Dataset: register and note the format; do not force into PDF
Web page: preserve the URL and access date; create a PDF capture if needed

6. Record derivatives separately

If you generate page images, OCR text, or other derivatives from a source object, record them in a separate manifest — not in the raw inventory. Keep the chain: raw → normalized → derivative.

Rules

Never rename or overwrite files in the raw layer. All transformations happen in a separate staging or working layer.
Do not register a source object before checking for duplicates.
Do not force image groups into PDF form by default — decide the handling strategy first.
Do not force datasets, license files, or ambiguous objects into PDF form.
Manifests must make parent–child relationships explicit (which archive did this PDF come from?).
Record the source before generating any derivatives.
If a source is ambiguous, mark it status: pending_decision rather than guessing.

Manifest minimum fields

For each registered source object, record at minimum:

stable ID (SRC-####)
object type (from the type table above)
original raw path
normalized/working path
parent raw ID (if from an archive)
language
status
notes

References

Read references/naming-conventions.md for ID formats, filename patterns, and status vocabulary.
Read references/archive-first.md for why archive expansion must come before registration, and common mistakes when skipping it.

Bundled files

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

Frequently asked questions

What does the Source Intake AI skill do?

Why use Source Intake on TypingMind?

Because you install it once and use it with any model. Source Intake 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 Source Intake in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/scholay/skills/tree/main/source-intake. 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 Source Intake?

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 Source Intake?

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

Is the Source Intake 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

Unified Memory

affaan-m

CommunityPopular

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer…

Draw Your Font

Turn a handwriting photo into an installable TTF font.

Adversarial Ux Test

Roleplay a hostile user to find and triage UX pain points.

3 Statement Model

Build integrated IS/BS/CF financial workbooks in Excel.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Source Intake

The core problem

Object types

Workflow

1. Inventory before touching

2. Expand all archives

3. Check for duplicates

4. Assign stable IDs

5. Normalize

6. Record derivatives separately

Rules

Manifest minimum fields

References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now