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.
Implement a frontend from a UI screenshot or design image in an existing project or a runnable standalone page.
Install Dev Image To Code
$ npx skills add hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-image-to-code --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code .claude/skills/dev-image-to-code && 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 "dev-image-to-code" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code into .claude/skills/dev-image-to-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-image-to-code", 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/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-codeType 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 hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-image-to-code --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code .agents/skills/dev-image-to-code && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dev-image-to-code" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code into .agents/skills/dev-image-to-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-image-to-code", 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 hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-image-to-code --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code .cursor/skills/dev-image-to-code && 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 "dev-image-to-code" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code into .cursor/skills/dev-image-to-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-image-to-code", 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/hashgraph-online/awesome-codex-plugins.git --path plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code--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 hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-image-to-code --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code .gemini/skills/dev-image-to-code && 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 "dev-image-to-code" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code into .gemini/skills/dev-image-to-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-image-to-code", 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 hashgraph-online/awesome-codex-plugins dev-image-to-codeInstalls 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 hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code .github/skills/dev-image-to-code && 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 "dev-image-to-code" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code into .github/skills/dev-image-to-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-image-to-code", 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 hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-image-to-code --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code .opencode/skills/dev-image-to-code && 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 "dev-image-to-code" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code into .opencode/skills/dev-image-to-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-image-to-code", 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
dev-image-to-code- GitHub stars
- 1.2k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 664 words
- Files
- 11 (incl. scripts, references)
- Skills in repo
- 686
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Implement a frontend from a UI screenshot or design image in an existing project or a runnable standalone page.
- Works in 4 steps: Inspect the target route, nearby… → Identify the image's layout, text,… → Match geometry and hierarchy first, then… → …
- Screenshot to code
- SKILL.md covers Load Baseline, Inputs And Decisions, Reconstruct and Control Semantics, plus 2 more sections
- Runs JavaScript scripts from its folder
What it does
Dev Image To Code is an agent skill from hashgraph-online/awesome-codex-plugins. Implement a frontend from a UI screenshot or design image in an existing project or a runnable standalone page. Use for "UI图生成代码", "看图写页面", "根据设计图实现", "screenshot to code", or "image to code" requests. Preserve visual fidelity and working control semantics, then verify in a real renderer. Not for redesigns without a reference image.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/dev-baseline.md` and `references/image-analysis.md`).
It sits in Frontend & Design, covering Design to code. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
When your agent uses it
- Screenshot to code
- Image to code requests
Example prompts
- “UI图生成代码”
- “根据设计图实现”
- “screenshot to code”
- “/dev-image-to-code”
Requirements
- Node.js
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Inspect the target route, nearby screens, local design tokens, icon libraries,
- Identify the image's layout, text, assets, visual tokens, visible states, and
- Match geometry and hierarchy first, then typography, spacing, colors, and
- Implement semantic controls and the evidenced states. Use conservative
What it can do on your machine
Read from SKILL.md and the folder at commit 78497e5. 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
Ships 4 files in scripts/ (JavaScript), which the agent can run.
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
Dev Image To Code loads about 1.4k tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 664 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); the scripts in this folder are not scanned.
SKILL.md
The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 664 words, ~1,389 tokens.
Download SKILL.mdSave it as
.claude/skills/dev-image-to-code/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.- name
- dev-image-to-code
- description
- Implement a frontend from a UI screenshot or design image in an existing project or a runnable standalone page. Use for "UI图生成代码", "看图写页面", "根据设计图实现", "screenshot to code", or "image to code" requests. Preserve visual fidelity and working control semantics, then verify in a real renderer. Not for redesigns without a reference image.
Dev Image To Code
Use the image as the visual source of truth, the design size as the coordinate baseline, and a rendered screenshot as verification evidence. Match the supplied design before adding any user-requested improvements.
Load Baseline
Read references/dev-baseline.md once per task. Keep changes scoped to the
requested screen and reuse the project's components, themes, wrappers, state,
i18n, routing, and tests.
Inputs And Decisions
- A UI image is required. Inspect it directly, including important small details.
- Use a supplied design size. Otherwise inspect image metadata and use its pixel
dimensions as a provisional baseline; record
inferred-from-image-pixels. Ask about size only when cropping, scaling, or device pixel ratio would materially change the reconstruction. - Infer the stack from the target project. For a standalone request without a stack, use minimal runnable HTML/CSS/JS.
- Resolve uncertainty from the image, project code, assets, and user notes first. Make reversible visual choices using that evidence and state consequential assumptions. Ask only when missing information materially affects scope, business meaning, fidelity requirements, or an action's effects. Continue independent work while the affected decision waits.
- Do not invent hidden backend behavior, permissions, payments, data contracts, routes, or business-critical copy from a static image.
Read input-contract.md for ambiguous intake, missing assets, or uncertain dimensions.
Reconstruct
- Inspect the target route, nearby screens, local design tokens, icon libraries, and layout/scaling conventions before choosing implementation primitives.
- Identify the image's layout, text, assets, visual tokens, visible states, and controls. Keep concise working notes; use the structured inventory in image-analysis.md for dense or multi-state UIs.
- Match geometry and hierarchy first, then typography, spacing, colors, and details. Preserve readable source copy and use source assets when available. Identify missing assets or unreadable text without presenting approximations as source facts.
- Implement semantic controls and the evidenced states. Use conservative responsive constraints while preserving the supplied breakpoint; one image cannot prove unshown breakpoint fidelity.
For framework, mobile, chart, or standalone choices, read implementation-paths.md.
Control Semantics
Do not turn visible controls into inert boxes. Buttons and form fields must be real native or project controls, with appropriate focus, keyboard, selected, disabled, and expanded behavior. Tabs, menus, accordions, dialogs, and steppers need stateful components. Tabular data needs table/grid semantics.
Separate control semantics from hidden business behavior. Implement editing, selection, and expansion when the relevant values or content are known. For an unknown action or hidden panel, preserve the visible control and document the missing behavior; do not fabricate a successful submission or destination. Prototype mocks are acceptable within the requested prototype scope, but must be reported as mocks. A no-op handler is a gap, not a completed interaction.
Show full SKILL.md (230 more words)Show less
Verify And Deliver
Render at the design width and height, inspect an actual screenshot, and compare it to the source. Check missing assets, clipping, overlap, text, and runtime errors. Smoke-test implemented controls with assertions about their visible effects, not just successful clicks. Verify requested additional viewports in the real renderer. For Flutter or native apps, use their platform renderer.
Fix visible drift and rerun affected checks. Report remaining input or runtime limitations explicitly; code inspection alone cannot establish visual fidelity. Do not claim exact pixel matching from an approximate baseline or incomplete assets.
Keep evidence proportional: screenshot paths, relevant commands, and a brief
comparison with known gaps usually suffice. Create UI_RECON.md, token files,
component maps, or VISUAL_REPORT.md only when complexity, repeated review, or
the user calls for them. Do not create empty templates or mandatory scorecards.
Read visual-verification.md for commands,
interaction assertions, optional report templates, and diff interpretation.
Bundled Tools
Resolve script paths from the absolute directory containing this SKILL.md.
scripts/image-metadata.mjs: Read source image dimensions.scripts/screenshot-page.mjs: Capture the web page at a chosen viewport.scripts/visual-diff.mjs: Write an image comparison and optional diff image.scripts/interaction-smoke.mjs: Run focus/click/fill/select checks with optional value, focus, or attribute assertions; inspect the JSON results.
The browser helpers require Playwright and a working browser runtime. Use existing project tooling when equivalent. Report an unavailable renderer as a verification limitation rather than replacing screenshot evidence with a claim.
© hashgraph-online, Apache-2.0. 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 10 other files (scripts, references) in plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code of hashgraph-online/awesome-codex-plugins.
- SKILL.md
- agents/openai.yaml
- references/dev-baseline.md
- references/image-analysis.md
- references/implementation-paths.md
- references/input-contract.md
- references/visual-verification.md
- scripts/image-metadata.mjs
- scripts/interaction-smoke.mjs
- scripts/screenshot-page.mjs
- scripts/visual-diff.mjs
Open the folder on GitHubat commit 78497e5
Compare with similar skills
Dev Image To Code 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 |
|---|---|---|---|---|---|---|
| Dev Image To Code this skillhashgraph-online/awesome-codex-plugins | 1.2k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Design to Codewarpdotdev/warp | 65k | 4 repos | ~2.9k | Automated safety check: Pass | AGPL-3.0 | |
| Scalar Design Systemscalar/scalar | 16k | — | ~2.7k | Automated safety check: Pass | MIT | |
| Figma Design System Rules Generatorwarpdotdev/warp | 65k | 3 repos | ~4.6k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Code Connect Componentswarpdotdev/warp | 65k | 2 repos | ~4.2k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
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.
Scalar Design System
scalar/scalar
Scalar's design system — design tokens, theming (@scalar/themes), CSS variables, and the @scalar/components library.
Figma Design System Rules Generator
warpdotdev/warp
Creates project-specific design system rules from your codebase so coding agents implement Figma designs with your components, naming and tokens.
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.
Design To Code
MigoXLab/coderio
Pixel-perfect Figma to React conversion using coderio. An agent skill from MigoXLab/coderio.
More from hashgraph-online/awesome-codex-plugins
All 736 skills in this repoAnime Reaction Gif
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
Calibredb
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
Rust API Test Harness
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
Art
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
Calle
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
Game Balance Economy
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Related
Categories
Questions about Dev Image To Code
What does Dev Image To Code do?
Implement a frontend from a UI screenshot or design image in an existing project or a runnable standalone page. Dev Image To Code is an agent skill from hashgraph-online/awesome-codex-plugins. Implement a frontend from a UI screenshot or design image in an existing project or a runnable standalone page.
When should I use Dev Image To Code?
Dev Image To Code fits situations like: screenshot to code; image to code requests.
How do I install Dev Image To Code in Claude Code?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a claude-code`. Or copy the skill folder (plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code in hashgraph-online/awesome-codex-plugins) into .claude/skills/dev-image-to-code in your project. Claude Code loads it when a task matches its description.
How do I install Dev Image To Code in Codex?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a codex`. Or copy the skill folder (plugins/Jason-chen-coder/dev-skills/skills/dev-image-to-code in hashgraph-online/awesome-codex-plugins) into .agents/skills/dev-image-to-code in your project. Codex loads it when a task matches its description.
Can I use Dev Image To Code 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 hashgraph-online/awesome-codex-plugins --skill dev-image-to-code -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dev-image-to-code, .gemini/skills/dev-image-to-code, .github/skills/dev-image-to-code and .opencode/skills/dev-image-to-code in your project.
What does Dev Image To Code need to run?
Going by SKILL.md and its folder, Dev Image To Code needs JavaScript for the scripts in its folder. Our summary lists: Node.js.
Does Dev Image To Code 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 Dev Image To Code 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Dev Image To Code use?
Dev Image To Code is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Dev Image To Code use?
About 1.4k tokens (SKILL.md is roughly 5.6k 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 5.7k tokens, read only when the agent opens those files.
What are the alternatives to Dev Image To Code?
Skills that share tags, products or a category with Dev Image To Code: Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), Figma Design to Code (warpdotdev/warp, 65k stars), Scalar Design System (scalar/scalar, 16k stars) and Figma Design System Rules Generator (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 Dev Image To Code?
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.