← ClaudeAtlas

figma-blame-nodelisted

Find which Figma version introduced a specific change — a component property or a child node — via a binary search over version history (~log2(N) API calls instead of N). Answers 'who added this and when'. Use when the user wants git-blame-style attribution for a Figma design — triggers: 'when was this component property added', 'which version introduced this variant', 'who added this node', 'blame this Figma element', 'find when this was created', 'git blame for Figma', 'when did this property first appear'. 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 full diff between two versions use figma-version-history; for prose release notes use figma-generate-changelog.
whiskfernlowdensitylipoprotein154/figma-console-mcp-skills · ★ 0 · AI & Automation · score 75
Install: claude install-skill whiskfernlowdensitylipoprotein154/figma-console-mcp-skills
# figma-blame-node — binary-search which version introduced a change Like `git blame`, but for Figma. Given a node and a target (a `componentPropertyDefinitions` key or a descendant child node id), this localizes the **version that first introduced** the target and returns that version's label, author handle, and timestamp. > **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. ## Why binary search A naive walk would fetch the node at every version — `N` API calls for `N` versions. Existence of a target is **monotonic** (added once, then present in every newer version up to HEAD), so we binary search: probe the midpoint, check whether the target exists there, then narrow to the older or newer half. That's **~log2(N)** calls — e.g. ~8 probes across 200 versions instead of 200. This is the rate-limit-friendly approach: Figma REST is throttled per token, and