Borrowing it
Nothing to install: this file belongs to aziontech/webkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aziontech/webkit/main/.claude/skills/figma-discover/SKILL.mdgit clone --depth 1 https://github.com/aziontech/webkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aziontech/webkit/figma-discover)<a href="https://agentmods.dev/skills/aziontech/webkit/figma-discover"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/figma-discover/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aziontech/webkit/figma-discover"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/figma-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.01198 |
| Opus 5.5 | $0.00016 | $0.00479 |
| Sonnet 5.5 | $0.00008 | $0.00240 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
figma-discover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: figma-discover
Purpose
Convert a Figma URL or nodeId into a structured JSON blob: colors, typography, spacing, radius, shadows, states (default/hover/active/focus/disabled), and identified regions (header/body/footer/actions). The downstream token-map skill consumes that JSON; this skill never decides anything beyond what Figma reports.
When to invoke
- Step 2 (parallel discovery) of
/component-create. - During
/spec-createwhen the user provided--figma <url>.
Inputs
- A Figma frame URL or
nodeId.
Workflow
- Load prerequisite skill. Invoke
figma:figma-usebefore any MCP call (mandatory per Figma plugin instructions). - Extract variables. Call
mcp__plugin_figma_figma__get_variable_defson the target node. Capture every named Figma variable along with its resolved value. - Extract design context. Call
mcp__plugin_figma_figma__get_design_contextfor the regions, states, and component anatomy. Capture the frame's component/node name raw (do not kebab or rewrite it) forcomponent_name. - Normalize. Emit a single JSON object:
{ "figma_node": "<url>", "component_name": "...", "variables": [ { "name": "color/surface", "value": "...", "kind": "color" }, { "name": "text/heading-md", "value": "...", "kind": "typography" } ], "regions": ["header", "body", "footer", "actions"], "states": ["default", "hover", "active", "focus", "disabled"] } - Print. Emit only the JSON. No prose.
Outputs
- A single JSON blob to stdout. Nothing else.
Rules
- Do not decide anything (regions ≠ structure decision; that's
structure-decide). - Do not map Figma → DESIGN.md; that's
token-map. - Do not echo the user's request — only emit structured data.
- Do not invoke
use_figma,create_new_file, or any write-side Figma tool.
Behavioral fidelity (the part that matters)
The discovery output drives the spec, which drives the .vue. The downstream consumers depend on you to capture Figma behavior, not just colors. Capture, when present in the frame:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 83 lines · 39 tokens per session scan A 044f61d9153c
figma-discover is a skill published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,198 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
design-component
Design a UI component spec to the house quality bar (anatomy, variants, sizes, the 8 states, token mapping, and accessibility). Use when the user wants to design or document a component (button, input, tabs, toast, combobox, date picker, modal, etc.) at the spec level before or alongside code. For generating framework…
design-doctrine
The house rules for ANY design or UI work - the verification protocol (run the gate, never claim a number), the absolute no-emoji rule, token by intent, one shared theme, the eight states, one thing leads, and output completeness. Load this FIRST whenever building, reviewing, or theming a screen, component, or token…
design-screen
Design or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this for "design a landing page", "build a settings screen", "make me a website", "design the onboarding", "ออกแบบหน้าเว็บ", "ทำหน้า landing", "ออกแบบ UI", "ทำแอป". It runs the pipeline no single skill…
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
grill-me
Interrogate the brief before a line is built. Ask only the questions whose answers change the work, and put every unasked decision on the record as a stated assumption.
scaffold-project
Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.