Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ariaramin/flutter-skills --skill figma-to-flutter-expertgit clone --depth 1 https://github.com/ariaramin/flutter-skillsWrote 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/ariaramin/flutter-skills/figma-to-flutter-expert)<a href="https://agentmods.dev/skills/ariaramin/flutter-skills/figma-to-flutter-expert"><img src="https://agentmods.dev/badge/skills/ariaramin/flutter-skills/figma-to-flutter-expert/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/ariaramin/flutter-skills/figma-to-flutter-expert"><img src="https://agentmods.dev/badge/skills/ariaramin/flutter-skills/figma-to-flutter-expert.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 | $0.00121 | $0.09514 |
| Opus 5.5 | $0.00048 | $0.03806 |
| Sonnet 5.5 | $0.00024 | $0.01903 |
| Haiku 4.5 | $0.00012 | $0.00951 |
Grade A, and why
figma-to-flutter-expert 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 today.
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 — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma to Flutter
Implement the design as Flutter constraints, text, and assets. A Figma number is not a widget size until its coordinate system is known.
Label a rule when the choice matters:
- Documented: stated by current Flutter or Figma documentation, or by the Flutter framework source checked for this skill.
- Recommendation: derived from that evidence.
- Context-dependent: depends on the design, viewport, platform, or a measurement.
Research scope and source URLs: research notes. This skill does not claim to have read all of either doc site.
Purpose and scope
Use this skill to turn a Figma frame into maintainable Flutter that keeps the design's spacing, type, and hierarchy on the viewports the product actually ships. Phone, tablet, foldable, desktop, and web are in scope. Native look-and-feel that the design does not specify is not a reason to redraw the screen.
Reuse the repository's theme, widgets, and tests. Do not add a package, a second token system, or a screen-scale helper.
When to activate
Activate for a Figma URL, Dev Mode inspection, exported node JSON, a frame screenshot with measurements, or a Flutter screen that should match one of those. Also activate when a previous implementation multiplied sizes by devicePixelRatio, scaled every dp by screenWidth / frameWidth, or positioned a flow layout with Positioned.
Stay inactive for a one-off color tweak with no layout, a pure design-system generation task from DESIGN.md, and a performance trace with no design fidelity question. A measured jank bug follows a profiling loop; this skill only says which design-implementation choices are expensive.
Required engineering principles
- Inspect the repo and the design before editing. Missing measurements stay missing. Do not invent states, fonts, or assets.
- Five quantities stay distinct: a design measurement, a Flutter logical pixel, a physical pixel, an exported image's pixel size, and a responsive scale factor.
- Default layout mapping is 1:1 from a logical Figma frame into logical pixels.
devicePixelRatiois applied by Flutter during rasterization. Do not multiply layout by it. - Documented. Constraints go down. Sizes go up. The parent sets position. (Understanding constraints)
- Prefer the sizing mode the frame already has: fixed, hug, or fill. Absolute coordinates are for layers that are actually absolute.
- Preserve fidelity without freezing the phone frame onto every window. Fill and hug adapt. Fixed component sizes stay fixed only while they still fit.
- Change performance only to remove a documented cost or a measured problem. Do not drop a shadow, clip, or widget for an unmeasured gain.
- Report the checks that ran. Name tools, Figma fields, and platforms that were unavailable. Do not claim pixel-perfect parity or a measured speedup without evidence.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/optimized-widgets.md 6.4 KB
- examples/visual-regression-workflow.md 5.0 KB
- README.md 241 B
- references/design-to-widget-mapping.md 9.0 KB
- references/figma-inspection.md 7.2 KB
- references/flutter-performance.md 7.9 KB
- references/official-sources.md 5.4 KB
- references/pixel-perfect-validation.md 7.0 KB
- references/research-notes.md 10 KB
- references/responsive-cross-platform.md 4.9 KB
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.
- today Changed · +424 lines · +4 tokens per session 65c14bb5c458
- 15d ago First seen · 180 lines · 117 tokens per session scan A 2e496dbfad8e
figma-to-flutter-expert is a skill published in the GitHub repository ariaramin/flutter-skills (6 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 9,514 once invoked, about $0.0005 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 2026-10-11.
Other skills, from other repositories
frontend-design
Production-grade UI/UX guidance — not generic AI slop. Triggers on design, UI, frontend, component, styling, layout, make it look good.
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
omh-visual-qa
This is an OMH visual-qa workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
design-craft
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique. Use for new screens, landing pages, redesigns, typography/layout work, or UI that feels generic or AI-generated. For small fixes, preserve the existing design without starting a…
design-critique
Use this skill to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states, accessibility and copy, ending in a ranked fix list. Triggers: user says "review the design", "critique this UI", "why does this…
color-palette-generator
Create an HTML color palette from a mood, description, or image, with swatches, color codes, pairings, and contrast checks. Use for color schemes or brand colors.