Reference Intake logo

Reference Intake

Community
Bandersnatch0x
reference-intake

Reference intake contract from screenshot, URL, design file, or product analogy. Use when the user supplies a visual or product reference before build. Also use when Keep, Change, and Do not copy boundaries are missing.

Overview

PublisherBandersnatch0x
Repositorydesign-playbook
Skill namereference-intake
Stars
3
Forks
0
Bundled files
2
Links
  • 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 Bandersnatch0x on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Bandersnatch0x/design-playbook/tree/main/packages/design-playbook/skills/reference-intake
  4. 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.
2

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/Bandersnatch0x/design-playbook.git /tmp/design-playbook
mkdir -p .claude/skills
cp -r /tmp/design-playbook/packages/design-playbook/skills/reference-intake .claude/skills/reference-intake
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Reference 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 Reference 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 Reference 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.

reference-intake

Turn raw reference material into a run-local declaration input the pipeline can consume without re-deriving from chat.

Not a style library. Not a code export. Not a Pass or Fail gate.

Authority boundary (ADR-0011):

This skill ownsDoes not own
Observed vs inferred evidence about the referencespec.md L1 through L6
Keep / Change / Do not copydecision report / Fill source
License and brand risk notesevaluator verdict

When to apply / skip

Apply when the ask includes at least one of:

  • local screenshot / mock / design export path
  • URL of a live product or design
  • existing in-repo design artifact the user points at
  • explicit product or brand analogy ("like Linear", "reference Feishu settings page", example (zh): "参考飞书设置页")

Skip when the ask is text-only product requirements with no reference material. Narrate once: -> reference-intake?: no reference materials, skipped.

Steps

1. Inventory sources

List every reference source. For each source record:

  • kind: screenshot | url | design_file | product_analogy | other
  • locator (path or URL or product name)
  • for files: SHA-256 when the file is readable. For URLs: the exact URL string
  • captured_at (ISO-8601) and tool (how it was collected)

Write manifest.json under .scratch/<run>/reference/ using the shape in references/contract-template.md. Copy durable local media into reference/assets/ only when needed for later human review. Never into the host Fill tree.

For a temporary PNG, JPEG, WebP, or GIF that enters a design run, call scripts/reference_sources.py ingest_ephemeral_image(...). Pass kind: screenshot for a captured interface and kind: other for any other raster. Keep the helper's detected media_type. Cite the returned source id and run-relative locator. Keep provider as a provider label, never a path. Record host temporary paths nowhere in the manifest or contract. Author URLs, design files, and product analogies directly. Field names and locator rules live in references/contract-template.md.

Treat Figma's official MCP, a Lanhu export, an HTML export, a URL, and a local design file as upstream collection methods. Normalize their outputs into this provider-neutral source contract. Do not add a vendor conversion layer or let provider output write spec.md, the decision report, Fill source, or a verdict.

Done when: every cited source appears in manifest.json with kind + locator. File sources that exist on disk carry sha256.

2. Separate observed from inferred

Read each source's accompanying text: user-provided notes, URL page text, and file facts. Never read the image bytes. Image sources were registered in step 1, not read. Fill every required heading from references/contract-template.md (SSOT for section names and bullet prompts). Do not invent alternate headings.

The host model may have no vision (text-only input). Image sources are registered by preserved locator and metadata only (locator, sha256, captured_at in manifest.json), reading the image is never a required intake action. Materialize an ephemeral image with the helper first and never record its host temporary path. The observed and inferred split then rides the text the session can actually cite (user-provided notes, URL page text, file facts). Visual points nobody can verify stay inferred or move to Unresolved questions. A no-vision host runs this skill end to end without degrading the protocol.

Mandatory no-vision fallback: when the host has no vision and the user supplied only screenshots without accompanying text, stating the limitation is not enough. First ask the user for a short written description of each screenshot and which points to keep or change. Continue intake with that description as citable observed text. Ask once. It is a required step, not an optional courtesy. When the user already supplied text alongside the screenshots, do not ask. A vision-capable host may inspect the image directly and never triggers this ask.

Mark every claim as observed or inferred. Unlabeled claims are invalid. Rewrite them before emit.

Done when:

  • contract.md has every template heading (including always, ask, and never hints and Unresolved questions)
  • Keep, Change, and Do not copy must each be non-empty for product analogies, third-party URLs, and third-party screenshots or designs. For first-party user-owned assets, only Do not copy may say none, first-party owned, with an ownership note.
  • at least one license and brand risk line exists (none identified only for pure first-party assets the user owns)

3. Emit and stop

Write:

text
.scratch/<run>/reference/contract.md
.scratch/<run>/reference/manifest.json
.scratch/<run>/reference/assets/   # optional

Optional disposable example.html may be generated under reference/ only as a later preview input. It is not a Fill source (same hard boundary as preview/round-*.html).

Stop. Do not write spec.md, do not pick components, do not implement UI.

Done when: both contract.md and manifest.json exist. Steps 1 and 2 Done-when criteria still hold in the files.

Scope fence

InOut of scope
Source inventory + hashesL6 acceptance belongs to ux-spec
Keep / Change / Do not copytemplate and component identity belongs to ui-picker
Functional constraints derived from referencecoding / Fill
License and brand risk notesvisual similarity score as gate
third-party skill or brand-kit port into the plugin

Handoff

After emit, the orchestrator continues to ux-spec? (or plan? when spec already exists). Consumers must cite reference/contract.md rather than re-describing the screenshot from memory.

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 Reference Intake AI skill do?

Reference intake contract from screenshot, URL, design file, or product analogy. Use when the user supplies a visual or product reference before build. Also use when Keep, Change, and Do not copy boundaries are missing.

Why use Reference Intake on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Bandersnatch0x/design-playbook/tree/main/packages/design-playbook/skills/reference-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 Reference 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 Reference Intake?

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

Is the Reference Intake AI skill free?

It is published on GitHub by Bandersnatch0x. Check the repository for licensing terms. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇