Figma Version History logo

Figma Version History

Organization
southleft
figma-version-history

List a Figma file's version history, snapshot the file at any past version, and diff two versions (added/removed/renamed pages plus deep per-component changes). Use when the user wants to inspect Figma history — triggers: 'list Figma versions', 'what versions does this file have', 'show version history', 'snapshot this file at version X', 'get the file as it was last week', 'diff two Figma versions', 'what changed between these versions', 'compare version A and B', 'did this component change between releases'. Uses the Figma REST API + a personal access token because version history is NOT reachable via the Plugin API / use_figma / the native Figma MCP. For a prose release-notes writeup use figma-generate-changelog; to find which version introduced a change use figma-blame-node.

Overview

Publishersouthleft
Repositoryfigma-console-mcp-skills
Skill namefigma-version-history
Stars
94
Forks
4
Bundled files
3
LicenseMIT
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by southleft on GitHub. Read the source before you install it.

Installation

Install the Figma Version History 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/southleft/figma-console-mcp-skills/tree/main/skills/figma-version-history
  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/southleft/figma-console-mcp-skills.git /tmp/figma-console-mcp-skills
mkdir -p .claude/skills
cp -r /tmp/figma-console-mcp-skills/skills/figma-version-history .claude/skills/figma-version-history
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Figma Version History 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 Figma Version History 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 Figma Version History 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.

figma-version-history — list, snapshot & diff Figma versions

Version history lives only in Figma's REST API, so this skill calls REST directly with a personal access token (PAT). It does three things:

  1. List a file's version history (label, description, author, timestamp, version id).
  2. Snapshot the file (or just some nodes) as it existed at a given version_id.
  3. Diff two versions — a cheap page-structure diff always, plus optional deep per-component diffs at depth=2.

Setup — terminal + token required. This skill runs shell commands, so it works in Claude Code (including the "Code" tab inside Claude Desktop), Cursor, Codex, or Gemini CLI — it does not run in plain Claude Desktop or claude.ai chat (no shell). The Figma connector's OAuth login does not authorize these REST calls, so you must supply your own Figma personal access token: in Figma go to Settings → Security → Personal access tokens, generate one with scope File content: read (plus File versions: read), then set it in your shell: export FIGMA_TOKEN="figd_…". The script reads it from the environment at runtime — never put the token in a skill file.

Setup & skill boundaries

  • All requests go to https://api.figma.com with the header X-Figma-Token: $FIGMA_TOKEN.
  • Endpoint reference: references/endpoints.md.

Derive the file key

The file key is the path segment after /design/ or /file/ in a Figma URL:

bash
FILE_URL="https://www.figma.com/design/ABC123def456/My-File"
FILE_KEY=$(echo "$FILE_URL" | sed -E 's#.*/(design|file)/([A-Za-z0-9]+).*#\2#')
echo "$FILE_KEY"   # ABC123def456

Workflow

  1. List versions to find the version_ids you care about. Run scripts/list-versions.sh:

    bash
    ./scripts/list-versions.sh ABC123def456              # labeled versions only (default)
    ./scripts/list-versions.sh ABC123def456 --autosaves  # include unlabeled auto-saves

    It auto-paginates (newest-first) and prints version_id | created_at | author | label. By default it filters out unlabeled auto-saves; pass --autosaves to keep them.

  2. Snapshot a version with a one-line curl (omit &version= for current/HEAD). Save to disk so you can diff repeatedly without re-fetching — past versions are immutable:

    bash
    # Whole file at a past version (depth=1 keeps it small for orienting)
    curl -s -H "X-Figma-Token: $FIGMA_TOKEN" \
      "https://api.figma.com/v1/files/$FILE_KEY?version=4096761871&depth=1" \
      > /tmp/v-4096761871.json
    
    # Just specific nodes at that version (much smaller payload)
    curl -s -H "X-Figma-Token: $FIGMA_TOKEN" \
      "https://api.figma.com/v1/files/$FILE_KEY/nodes?ids=695:313&version=4096761871&depth=2"
    
    # Current / HEAD — omit the version param entirely
    curl -s -H "X-Figma-Token: $FIGMA_TOKEN" \
      "https://api.figma.com/v1/files/$FILE_KEY?depth=1"
  3. Diff two versions with scripts/diff-versions.mjs. It fetches both snapshots, computes a page-structure diff (cheap, 2 calls), and — if you pass --components — deep per-node diffs at depth 2 (added/removed children, name/description changes, componentPropertyDefinitions changes for COMPONENT_SETs, and boundVariables deltas):

    bash
    # Page-structure diff only (2 API calls)
    node scripts/diff-versions.mjs --file ABC123def456 --from 4096761871 --to current
    
    # Deep diff of specific component sets (2 calls per node), detailed verbosity
    node scripts/diff-versions.mjs --file ABC123def456 --from 4096761871 --to 4096800000 \
      --components 695:313,420:88 --mode detailed

    Use current (or omit --to) to diff against HEAD. --mode is summary (counts only), standard (names + counts, default), or detailed (full property/binding detail).

What the diff DOES and does NOT track

The diff is honest about its blind spots — don't read "no changes" as "nothing changed":

  • Tracks: page structure (added/removed/renamed pages); on scoped nodes — children added/removed, componentPropertyDefinitions (added/removed/type/default change), name & description changes, and variable binding references.
  • Does NOT track: instances of components placed elsewhere on the canvas (only the nodes you pass as --components), raw layout props (hug-vs-fill, unbound paddings/widths/cornerRadius), unbound fills/strokes/effects, variable VALUE changes (Figma REST never exposes these), and style content. For forensic per-edit history including raw property changes, the live Desktop Bridge plugin's figma_get_design_changes is the complementary tool.

Notes

  • Figma's version pagination is cursor-style: after=<version_id> returns versions older in time (the list is newest-first). list-versions.sh handles this for you.
  • Old version_ids can be pruned by Figma's plan-tier retention policy — a 404 on snapshot usually means the version aged out, not that your key is wrong. Re-list to get valid IDs.
  • 403 on these endpoints means your PAT is missing the File versions: Read scope — reissue 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 Figma Version History AI skill do?

List a Figma file's version history, snapshot the file at any past version, and diff two versions (added/removed/renamed pages plus deep per-component changes). Use when the user wants to inspect Figma history — triggers: 'list Figma versions', 'what versions does this file have', 'show version history', 'snapshot this file at version X', 'get the file as it was last week', 'diff two Figma versions', 'what changed between these versions', 'compare version A and B', 'did this component change between releases'. Uses the Figma REST API + a personal access token because version history is NOT...

Why use Figma Version History on TypingMind?

Because you install it once and use it with any model. Figma Version History 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 Figma Version History in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/southleft/figma-console-mcp-skills/tree/main/skills/figma-version-history. 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 Figma Version History?

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 Figma Version History?

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

Is the Figma Version History AI skill free?

Yes. It is published on GitHub by southleft 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

Set up your own AI workspace now

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