figma-rest-sync
Skill1 starsChanged 3 months agoMITView on GitHub
Read, validate, cache, search, and export Figma design data through the Figma REST API for Claude Code workflows. Use when Claude Code needs the latest Figma UI prototype data, frame lookup, design text search, comments/notes retrieval, frame image export, or a local searchable index from Figma design files. This skill requires a Figma Personal Access Token on first use and must stop if the online Figma version cannot be verified or differs from the local cache.
In this repository22 other files it gives its agents.
- analysis-skillSkill
- auto-testcase-generatorSkill
- create-agent-skillSkill
- create-skillSkill
- development-systemSkill
- domain-modelingSkill
- grill-systemSkill
- grill-with-docsSkill
- rag-change-impactSkill
- rag-downstream-handoffSkill
- rag-governanceSkill
- rag-intakeSkill
- rag-querySkill
- rag-schemaSkill
- rag-structure-fidelitySkill
- rag-systemSkill
- researchSkill
- session-handoffSkill
- skill-packagerSkill
- task-understanding-routerSkill
- ui-testSkill
- write-requirements-prdSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 6 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill to work with Figma files through the REST API while preserving strict version consistency.
- Distinctive: line 13
Before any cache-backed query, image export, or brief generation, call online version check first.
- Distinctive: line 14
Stop if the online Figma file cannot be reached, token is invalid, access is denied, file is missing, or request times out.
- Very specific: line 15
Stop if local meta.version differs from remote version.
- Distinctive: line 16
Do not use stale cache as fallback.
- Distinctive: line 17
Do not print tokens, write tokens into outputs, or place tokens in skill files.
- Very specific: line 22
Run scripts/figma_sync.py check --file <figma-url-or-file-key> to validate token and read remote version.
- Very specific: line 23
If no local cache exists, run scripts/figma_sync.py sync --file <figma-url-or-file-key> after user confirms first sync.
- Distinctive: line 29
All query commands enforce online version validation before reading local cache.
- Very specific: line 33
Read references/error_policy.md when handling token, network, permission, cache, or version failures.
- Very specific: line 34
Read references/cache_schema.md when implementing or reviewing cache/index changes.
- Very specific: line 35
Read references/test_matrix.md before validating this skill or adding new Figma commands.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Figma REST Sync
Use this skill to work with Figma files through the REST API while preserving strict version consistency. The online Figma file is the source of truth. Local cache only accelerates queries after the online version is verified.
Hard Rules
- Require
FIGMA_TOKENbefore any Figma API call. If missing, ask the user for a Figma Personal Access Token and stop. - Before any cache-backed query, image export, or brief generation, call online version check first.
- Stop if the online Figma file cannot be reached, token is invalid, access is denied, file is missing, or request times out.
- Stop if local
meta.versiondiffers from remoteversion. - Do not use stale cache as fallback.
- Do not print tokens, write tokens into outputs, or place tokens in skill files.
Workflow
- Parse the Figma URL into
file_keyand optionalnode_id. - Run
scripts/figma_sync.py check --file <figma-url-or-file-key>to validate token and read remote version. - If no local cache exists, run
scripts/figma_sync.py sync --file <figma-url-or-file-key>after user confirms first sync. - For lookup, run
scripts/figma_sync.py search --file <figma-url-or-file-key> --query "<keywords>". - For a selected frame, run
scripts/figma_sync.py frame --file <figma-url>. - For image export, run
scripts/figma_sync.py image --file <figma-url> --scale 0.5. - For Claude-ready output, run
scripts/figma_sync.py brief --file <figma-url>.
All query commands enforce online version validation before reading local cache.
References
- Read
references/error_policy.mdwhen handling token, network, permission, cache, or version failures. - Read
references/cache_schema.mdwhen implementing or reviewing cache/index changes. - Read
references/test_matrix.mdbefore validating this skill or adding new Figma commands.
Output Expectations
Return concise Markdown for Claude Code:
- file name and
file_key - remote version and local version
- selected
node_id - matched frame/page name
- relevant text snippets or comments
- local image path when exported
- clear blocking error and user recovery step when validation fails
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.