Figma Comments logo

Figma Comments

Organization
southleft
figma-comments

Read, post, reply to, and delete comments on a Figma file via the REST API — including pinning a comment to a specific node and threading replies. Use when the user wants to work with Figma comments programmatically — triggers: 'get Figma comments', 'read comments on this file', 'post a comment in Figma', 'leave a comment on this node', 'reply to a Figma comment', 'pin a comment to this element', 'delete a Figma comment', 'notify designers of drift', 'add a review note in Figma'. Uses the Figma REST API + a personal access token because comments are NOT reachable via the Plugin API / use_figma / the native Figma MCP.

Overview

Publishersouthleft
Repositoryfigma-console-mcp-skills
Skill namefigma-comments
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 Comments 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-comments
  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-comments .claude/skills/figma-comments
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Figma Comments 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 Comments 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 Comments 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-comments — read, post, reply & delete Figma comments

Comments live only in Figma's REST API — the Plugin API (use_figma) and the native Figma MCP can't touch them. This skill reads comment threads, posts new comments (optionally pinned to a node), replies to existing threads, and deletes comments.

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 Comments: read/write), 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 use X-Figma-Token: $FIGMA_TOKEN against https://api.figma.com.
  • @mentions are a Figma UI-only feature. Putting @name in a message renders as plain text, not a clickable mention, and does not trigger a Figma notification.

Derive the file key

bash
FILE_KEY=$(echo "$FILE_URL" | sed -E 's#.*/(design|file)/([A-Za-z0-9]+).*#\2#')

Read comments

scripts/get-comments.sh lists threads with author, message, timestamps, pinned node, and resolution state. Resolved threads are filtered out by default:

bash
./scripts/get-comments.sh ABC123def456                 # active comments only
./scripts/get-comments.sh ABC123def456 --include-resolved
./scripts/get-comments.sh ABC123def456 --md             # request markdown message bodies

Raw endpoint:

bash
curl -s -H "X-Figma-Token: $FIGMA_TOKEN" \
  "https://api.figma.com/v1/files/ABC123def456/comments?as_md=true"

Post a comment

scripts/post-comment.sh posts a top-level comment, a node-pinned comment, or a threaded reply:

bash
# Plain file-level comment
./scripts/post-comment.sh ABC123def456 "Heads up: the button radius drifted from code."

# Pinned to a node (appears on that element). x/y default to 0,0 if omitted.
./scripts/post-comment.sh ABC123def456 "Padding here should be 16, not 12." --node 695:313 --x 40 --y 12

# Reply to an existing thread (get IDs from get-comments.sh)
./scripts/post-comment.sh ABC123def456 "Fixed in the latest sync." --reply 123456789

The raw POST body shape:

bash
curl -s -X POST -H "X-Figma-Token: $FIGMA_TOKEN" -H "Content-Type: application/json" \
  -d '{"message":"Pinned note","client_meta":{"node_id":"695:313","node_offset":{"x":0,"y":0}}}' \
  "https://api.figma.com/v1/files/ABC123def456/comments"
  • Pinning: include client_meta with node_id and a node_offset ({x,y} relative to the node). Figma requires node_offset whenever node_id is present — the script defaults it to (0,0).
  • Replies: add comment_id (the id of the comment you're replying to) to the body. The script's --reply flag does this. Replies form a thread under the original comment.

Delete a comment

scripts/delete-comment.sh removes a comment by id (find ids via get-comments.sh):

bash
./scripts/delete-comment.sh ABC123def456 123456789

Raw:

bash
curl -s -X DELETE -H "X-Figma-Token: $FIGMA_TOKEN" \
  "https://api.figma.com/v1/files/ABC123def456/comments/123456789"

Notes

  • A 403 on post/delete means your PAT lacks Comments: Read and write — reissue the token.
  • Deleting a parent comment removes its whole thread. Delete replies first if you only want to prune part of a conversation.
  • A common workflow: detect design/code drift, then post-comment.sh --node <id> to leave an actionable note pinned to the offending element so designers see it in context.

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 Comments AI skill do?

Read, post, reply to, and delete comments on a Figma file via the REST API — including pinning a comment to a specific node and threading replies. Use when the user wants to work with Figma comments programmatically — triggers: 'get Figma comments', 'read comments on this file', 'post a comment in Figma', 'leave a comment on this node', 'reply to a Figma comment', 'pin a comment to this element', 'delete a Figma comment', 'notify designers of drift', 'add a review note in Figma'. Uses the Figma REST API + a personal access token because comments are NOT reachable via the Plugin API / use_fi...

Why use Figma Comments on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/southleft/figma-console-mcp-skills/tree/main/skills/figma-comments. 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 Comments?

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 Comments?

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

Is the Figma Comments 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 👇