Figma use_figma Plugin API Rules
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
Inspects Figma designs through the figma CLI and Figma's MCP server to read variants, spacing, tokens and layouts and to extract assets for implementation.
Install Figma Design Inspector
$ npx skills add asgeirtj/system_prompts_leaks --skill figma -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install asgeirtj/system_prompts_leaks figma --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Meta/muse-agent/skills/figma .claude/skills/figma && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "figma" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/figma into .claude/skills/figma/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/figmaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add asgeirtj/system_prompts_leaks --skill figma -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install asgeirtj/system_prompts_leaks figma --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .agents/skills && cp -r skills-src/Meta/muse-agent/skills/figma .agents/skills/figma && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "figma" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/figma into .agents/skills/figma/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asgeirtj/system_prompts_leaks --skill figma -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install asgeirtj/system_prompts_leaks figma --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/Meta/muse-agent/skills/figma .cursor/skills/figma && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "figma" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/figma into .cursor/skills/figma/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/asgeirtj/system_prompts_leaks.git --path Meta/muse-agent/skills/figma--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add asgeirtj/system_prompts_leaks --skill figma -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install asgeirtj/system_prompts_leaks figma --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/Meta/muse-agent/skills/figma .gemini/skills/figma && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "figma" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/figma into .gemini/skills/figma/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install asgeirtj/system_prompts_leaks figmaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add asgeirtj/system_prompts_leaks --skill figma -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .github/skills && cp -r skills-src/Meta/muse-agent/skills/figma .github/skills/figma && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "figma" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/figma into .github/skills/figma/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asgeirtj/system_prompts_leaks --skill figma -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install asgeirtj/system_prompts_leaks figma --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/Meta/muse-agent/skills/figma .opencode/skills/figma && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "figma" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/Meta/muse-agent/skills/figma into .opencode/skills/figma/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
figma- GitHub stars
- 69k
- Token cost
- ~936 tokens
- SKILL.md length
- 438 words
- Files
- 7 (incl. references)
- Skills in repo
- 128
- Repo updated
- First seen
- Licence
- CC0-1.0
At a glance
Inspects Figma designs through the figma CLI and Figma's MCP server to read variants, spacing, tokens and layouts and to extract assets for implementation.
- Reading component variants, spacing and design tokens from a Figma file
- SKILL.md covers Load Figma's provider skills and Choose the workflow
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Extracting image assets from a design for implementation
What it does
The workflow starts with figma status. If the CLI is not connected, the agent runs figma authorize-url and shares only the returned connect_url with you, and credentials must never be requested in chat because OAuth runs through dynamic client registration and PKCE. figma list-tools shows the reviewed tools with their permission details, and figma call-tool runs one by name with a JSON argument object.
Before using a tool that requires a Figma skill, the agent fetches it with get_figma_skill from the Figma MCP server using a skill URI, consulting the index when unsure, and reads need only the designs.read permission. Changes to designs, files, assets, Code Connect, plugins and shaders need granular approval, and a failed or timed-out write is never retried automatically because it may have taken effect. References cover canvas editing, Code Connect, design to code and diagrams.
When your agent uses it
- Reading component variants, spacing and design tokens from a Figma file
- Extracting image assets from a design for implementation
- Inspecting layouts and design-system libraries before writing UI code
Example prompts
- “Inspect this Figma frame and list its spacing, colors and component variants.”
- “Export the image assets from the pricing screen in Figma.”
- “Connect to Figma and show which tools are available.”
Requirements
- The `figma` CLI, connected to your Figma account through OAuth
- Access to the Figma file you want to inspect
What it can do on your machine
Read from SKILL.md and the folder at commit 60d44cc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Figma Design Inspector loads about 936 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 438 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from asgeirtj/system_prompts_leaks at commit 60d44cc, republished under its CC0-1.0 licence (© asgeirtj). 438 words, ~936 tokens.
Download SKILL.mdSave it as
.claude/skills/figma/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- figma
- description
- Inspect Figma designs and generate implementation context for screens and interfaces. Use to read component variants, spacing and design tokens, inspect layouts and design-system libraries, and extract image assets for implementing a design through Figma's official MCP server.
- icon
- figma
- metadata.includeInPrompt
- false
Figma
Use the installed figma CLI. Start with figma status. If it reports
not_connected, run figma authorize-url and share only the returned
connect_url with the user.
OAuth uses Dynamic Client Registration and PKCE through authd. Figma issues a per-registration confidential client; authd stores its generated secret outside the runtime cell, so credentials must never be requested in chat.
Run figma list-tools to inspect the live provider catalogue and schemas,
then call an advertised tool with:
figma call-tool --name <tool> --arguments-json '<json-object>'list-tools exposes only reviewed Figma tools and includes each tool's
hatch_permission, hatch_action, and hatch_permission_label. Unknown or
new provider tools remain unavailable until reviewed. Read permissions follow
the user's connector settings; design, file, asset, Code Connect, plugin, and
shader changes require granular approval. Do not retry a failed or timed-out
write automatically because its side effect may have completed.
Load Figma's provider skills
Before calling a tool whose description requires a Figma skill, fetch that
skill with get_figma_skill and follow its prerequisites. These skill://
URIs refer to resources on Figma's MCP server. For example, before
create_new_file, read:
figma call-tool --name get_figma_skill --arguments-json '{"uri":"skill://figma/figma-create-new-file/SKILL.md"}'Use the skill URI advertised by the tool. If the relevant URI is unknown,
fetch skill://index.json with the same tool and select the matching skill.
Fetch supporting references only as needed, resolving relative paths against
the parent skill URI. Reuse guidance already loaded for the current task;
there is no need to install or copy these provider skills into the local
skill directory. Skill reads use the designs.read permission.
Call get_figma_skill only when advertised by list-tools. If the tool is
unavailable or Figma confirms that a skill is missing, continue using the
live tool description, schema, and local guides only when the skill is
optional (for example, "if it exists"). If the skill is required
unconditionally, stop the dependent operation and report the missing
guidance. Authentication failures, permission denials, timeouts, and other
read errors do not establish that a skill is missing. Avoid repeated failed
lookups; continue work that does not depend on the unavailable guidance.
Show full SKILL.md (111 more words)Show less
Choose the workflow
Read only the guide that matches the task before calling provider tools:
- Implement a Figma design in code: design-to-code
- Create or edit canvas content with
use_figma: canvas editing - Generate a FigJam diagram: diagrams
- Create Code Connect mappings: Code Connect
For a Figma URL, extract its fileKey and node-id; convert node IDs from URL
form (123-456) to API form (123:456). Inspect the live schema before
constructing arguments because Figma can add optional fields without changing
this skill.
Avoid redundant catalogue, context, screenshot, and validation calls. Figma applies account- and seat-dependent usage limits, and repeated reads can consume a user's small monthly allowance. Reuse results gathered earlier in the task.
© asgeirtj, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (references) in Meta/muse-agent/skills/figma of asgeirtj/system_prompts_leaks.
- SKILL.md
- connector_auth_config.yaml
- manifest.yaml
- references/canvas-editing.md
- references/code-connect.md
- references/design-to-code.md
- references/diagrams.md
Open the folder on GitHubat commit 60d44cc
Compare with similar skills
Figma Design Inspector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Figma Design Inspector this skillasgeirtj/system_prompts_leaks | 69k | — | ~936 | Automated safety check: Pass | CC0-1.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Screen Generatorwarpdotdev/warp | 65k | 2 repos | ~5k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Design to Codewarpdotdev/warp | 65k | 4 repos | ~2.9k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Code Connect Componentswarpdotdev/warp | 65k | 2 repos | ~4.2k | Automated safety check: Pass | AGPL-3.0 | |
| AnyDesignuxKero/anydesign | 216 | — | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
Figma Screen Generator
warpdotdev/warp
Builds or updates full Figma screens from code or a description by reusing the file's published design system components, variables and styles.
Figma Design to Code
warpdotdev/warp
Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.
Figma Code Connect Components
warpdotdev/warp
Maps published Figma components to their code implementations with Code Connect, using the Figma MCP suggestion and mapping tools.
AnyDesign
uxKero/anydesign
Extracts the design of a screenshot, website URL or Figma file into a design.md of tokens, components, layout and brand rules, or copies one element into element.md.
AnyDesign Design Analyzer
avelikiy/great_cto
Analyzes a screenshot, website or Figma file and writes a `design.md` with its token system, component inventory and reconstruction notes, or an `element.md` for one element.
More from asgeirtj/system_prompts_leaks
All 128 skills in this repoFleet Manager for Agent Sessions
asgeirtj/system_prompts_leaks
Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.
Muse Code Product Doctor
asgeirtj/system_prompts_leaks
Diagnoses a Muse Code installation's own failures from binary and session evidence, instead of treating the report as an ordinary repository bug.
DOCX
asgeirtj/system_prompts_leaks
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx).
Agents Project Coordinator
asgeirtj/system_prompts_leaks
Runs a goal as a project in which the agent coordinates separate agent threads, judging when to split the work, and interviews you first when nothing can be verified.
Muse Plugin Creator
asgeirtj/system_prompts_leaks
Creates and validates a new native Muse plugin package in the current workspace, limited to five capability families, and leaves installation to you.
Deep Research
asgeirtj/system_prompts_leaks
A skill your agent uses when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or…
Related
Works with
Categories
Questions about Figma Design Inspector
What does Figma Design Inspector do?
Inspects Figma designs through the figma CLI and Figma's MCP server to read variants, spacing, tokens and layouts and to extract assets for implementation. The workflow starts with figma status. If the CLI is not connected, the agent runs figma authorize-url and shares only the returned connect_url with you, and credentials must never be requested in chat because OAuth runs through dynamic client registration and PKCE.
When should I use Figma Design Inspector?
Figma Design Inspector fits situations like: reading component variants, spacing and design tokens from a Figma file; extracting image assets from a design for implementation; inspecting layouts and design-system libraries before writing UI code.
How do I install Figma Design Inspector in Claude Code?
Run `npx skills add asgeirtj/system_prompts_leaks --skill figma -a claude-code`. Or copy the skill folder (Meta/muse-agent/skills/figma in asgeirtj/system_prompts_leaks) into .claude/skills/figma in your project. Claude Code loads it when a task matches its description.
How do I install Figma Design Inspector in Codex?
Run `npx skills add asgeirtj/system_prompts_leaks --skill figma -a codex`. Or copy the skill folder (Meta/muse-agent/skills/figma in asgeirtj/system_prompts_leaks) into .agents/skills/figma in your project. Codex loads it when a task matches its description.
Can I use Figma Design Inspector in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add asgeirtj/system_prompts_leaks --skill figma -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/figma, .gemini/skills/figma, .github/skills/figma and .opencode/skills/figma in your project.
What does Figma Design Inspector need to run?
SKILL.md names no scripts, command-line tools or credentials: Figma Design Inspector is instructions for the agent only. Our summary lists: The `figma` CLI, connected to your Figma account through OAuth; Access to the Figma file you want to inspect.
Does Figma Design Inspector access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Figma Design Inspector safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Figma Design Inspector use?
Figma Design Inspector is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Figma Design Inspector use?
About 936 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.
What are the alternatives to Figma Design Inspector?
Skills that share tags, products or a category with Figma Design Inspector: Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), Figma Screen Generator (warpdotdev/warp, 65k stars), Figma Design to Code (warpdotdev/warp, 65k stars) and Figma Code Connect Components (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Figma Design Inspector?
asgeirtj (a GitHub user) maintains it in asgeirtj/system_prompts_leaks, which has 69,280 GitHub stars. The repository holds 128 skills in this directory. The repository was last updated on October 10, 2026.
Source: asgeirtj/system_prompts_leaks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.