SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

image-to-codeyuzhworkhard-wq/image-to-code

Break a design mockup or screenshot into editable text layers, vector shapes and bitmap assets,…

No ratings yet Rate this skill
Stars348
Forks43
Watchers348
Open Issues0

InstallOne-line install

Installable · 29 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add yuzhworkhard-wq/image-to-code

29 more are not listed — run npx skills@latest add yuzhworkhard-wq/image-to-code --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Break a design mockup or screenshot into editable text layers, vector shapes and bitmap assets, and produce a code-reproduction plan with a coordinate manifest, so the agent does not guess sizes from layout and distort the result. Key capabilities include: 1. Source-image bbox measurement: every bbox must be measured from the current source image rather than inferred from layout, so each element's position is traceable; 2. Unified scale conversion: scaled bboxes are computed from the same scale value, avoiding inconsistent ratios across elements; 3. Text layer reproduction: all text is converted to editable text or code text with matching content, font family, size, weight and line height; 4. Shape layering: simple vectors and regular shapes are drawn in code, bitmaps and icons are sliced, and complex charts and visualizations are handled as a separate category; 5. Asset and manifest output: slices go into assets/icons/ and layer info is written to layers.manifest.json for downstream use; 6. PNG asset audit: audit_png_assets.py verifies slice asset completeness to reduce missing or wrong images.

Use Cases

design-to-code conversion, screenshot to editable page, UI component library building, icon and bitmap slicing, chart visualization reproduction, visual QA and pixel-level diffing.

Target Roles

Frontend Developer, UI/UX & Visual Designer, Full-stack / Indie Developer, AI / Algorithm Engineer.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID2190
Data sourceGitHub
Repositoryyuzhworkhard-wq/image-to-code
CategoryAI & Agent Skills / Coding & Engineering Agent
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1260920967
Node IDR_kgDOSygghw
Rank#1691 (position within the source ranking)
Site-wide popularity rank#1898 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01002003004002026-09-222026-10-112026-09-22 · 3452026-10-11 · 348
  • Now348
  • Previous point · 09-22 345
  • vs previous point +3
  • 2 data points 19 days
02040602026-09-222026-10-112026-09-22 · 432026-10-11 · 43
  • Now43
  • Previous point · 09-22 43
  • vs previous point ±0
  • 2 data points 19 days

TimelineTimeline

Repository created2026-06-06 03:01:495 months ago
Data last updated2026-10-26 12:21:0221 days ago
Last commit2026-06-10 10:38:115 months ago

CommitLatest commit

Version [latest] committed by Donyzh. Update Category: Feature Addition & Enhancement. Commit details: Add README acknowledgement. This update introduces new capabilities and module extensions.

886c882 vlatest Donyzh 2026-06-06

Next stepsNext steps