Chalk Labs
Need help deploying vectorize?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mohamedabdallah-14-vectorize
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/vectorize
What's inside
- Skill name
vectorize- Description
- Convert a raster image to SVG. Three paths — Recraft hosted vectorization, vtracer (multi-color polygon), potrace (1-bit). Optimizes with SVGO; validates path count as a quality signal.
- License
- MIT
- Instructions
- 97 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Vectorize
## Three paths
### 1. Recraft `/vectorize` (hosted, highest quality)
Input: any raster. Output: clean SVG, typically 20–100 paths for a mark, 200–500 for an illustration. Commercial tier only.
```ts
const svg = await recraft.vectorize({ image: pngBuffer });
```
### 2. `vtracer` (local, multi-color polygon)
- Rust binary; `npm install vtracer` for the Node wrapper.
- Modes: `polygon` (recommended for logos), `spline` (smoother curves), `pixel` (blocky).
- Color count controlled upstream via K-means quantization before vectorization.
```
pipeline:
raster 1024²
→ BiRefNet matte (alpha the background)
→ K-means LAB 6-color palette
→ vtracer --mode polygon --filter-speckle 4 --color-precision 6
→ SVGO (conservative preset)
```
### 3. `potrace` (local, 1-bit)
- Classical Stan Ford vectorizer; binary output only (no color).
- Best for: icon packs (single-color), typography work, line art.
- Multi-color workaround: separate each color into its own 1-bit layer, vectorize each, stack SVG `<g>`s.
```
pipeline:
raster 1024²
→ BiRefNet matte
→ per-color mask (binary threshold per palette entry)
→ potrace per mask → <g> wrapper
→ combine into single SVG
→ SVGO
```
## Choosing the path
| Use case | Path |
|---|---|
| Budget available, one-shot quality | Recraft vectorize |
| Multi-color logo, local | vtracer (polygon mode) |
| Single-color icon pack | potrace |
| Photorealistic illustration → vector | don't — keep as PNG/WebP. Vectorization of photoreal is lossy noise. |
## Path-count quality signal
After vectorization, count `<path>` elements:
- **≤40 paths** → clean, production-ready mark.
- **40–200 paths** → likely acceptable; scan for overlapping slivers.
- **>200 paths** → probably bad. Either the input has noise (regenerate), too many colors (reduce K-means), or the subject is inappropriate for vectorization (keep as raster).
## SVGO configuration
Conservative preset — **preserve:** viewBox, IDs, classes. **Strip:** metadata, editor comments, hidden elements.
```js
{
multipass: true,
plugins: [
{ name: 'preset-default', params: {
overrides: { removeViewBox: false, cleanupIds: { minify: false } } } },
'removeDimensions', // prefer viewBox-only
'sortAttrs',
'removeScriptElement' // security
]
}
```
Never enable `convertPathData` with default `floatPrecision` — it collapses small strokes.
## Validation
- SVG parses with `@resvg/resvg-js` without errors.
- `<path>` count ≤ 200 for logos, ≤ 500 for illustrations.
- No `<image>` tags (sneaking raster into SVG).
- No `<script>` tags.
- viewBox present.
- Rasterized at 1024 × 1024 should be visually identical (SSIM > 0.95) to source raster.
## Output
```
vector/
├── mark.svg # primary vectorization
├── mark.svg.orig # pre-SVGO original (for debugging)
└── meta.json # paths_count, colors_used, svgo_savings_bytes
```From MohamedAbdallah-14/prompt-to-asset, MIT.
More from MohamedAbdallah-14/prompt-to-asset
- 0.539score
ui-mockup-prompt
MohamedAbdallah-14
Translate a UI brief (a page, a screen, a single component, a feature) into a paste-ready prompt for Nano Banana Pro / gpt-image-2 / Ideogram / Flux 2 /…
SkillCFreshness: C★ 24Claude Code +9 - 0.528score
Prompt To Asset
MohamedAbdallah-14
Generate app icons, favicons, OG images, and logos by routing across 30+ image models.
ConnectorCFreshness: CLocal★ 24Claude Code +5 - 0.472score
t2i-prompt-dialect
MohamedAbdallah-14
Rewrite an asset brief into the exact prompt dialect of the target image model (OpenAI gpt-image-1, Google Imagen/Gemini, SDXL, Flux.1/Flux.2, Midjourney…
SkillDFreshness: D★ 24Claude Code +9 - 0.472score
asset-validation-debug
MohamedAbdallah-14
Diagnose and repair asset-generation failures.
SkillDFreshness: D★ 24Claude Code +9 - 0.472score
brand-consistency
MohamedAbdallah-14
Maintain visual coherence across a multi-asset brand set (logo + app icon + favicon + illustrations).
SkillDFreshness: D★ 24Claude Code +9 - 0.472score
svg-authoring
MohamedAbdallah-14
Author production-grade inline SVG (logos, favicons, icon packs, stickers, transparent marks) when the P2A `inline_svg` execution mode is selected.
SkillDFreshness: D★ 24Claude Code +9 - 0.472score
asset-enhancer
MohamedAbdallah-14
Classify a software-asset brief (logo, app icon, favicon, OG image, illustration, splash, icon pack, transparent mark), route to the right image model…
SkillDFreshness: D★ 24Claude Code +9 - 0.469score
favicon
MohamedAbdallah-14
Generate a full favicon bundle — favicon.ico (16/32/48 multi-res), icon.svg with prefers-color-scheme dark support, apple-touch-icon.png 180×180 opaque, and…
SkillDFreshness: D★ 24Claude Code +9 - 0.469score
app-icon
MohamedAbdallah-14
Generate an app icon from a single 1024² master and fan out to iOS (AppIcon.appiconset with squircle-ready 1024 opaque), Android (adaptive foreground +…
SkillDFreshness: D★ 24Claude Code +9 - 0.469score
illustration
MohamedAbdallah-14
Generate an in-product illustration (empty state, onboarding, hero, spot art) that obeys a brand bundle.
SkillDFreshness: D★ 24Claude Code +9 - 0.469score
logo
MohamedAbdallah-14
Generate a production-grade logo (primary brand mark).
SkillDFreshness: D★ 24Claude Code +9 - 0.469score
og-image
MohamedAbdallah-14
Generate an Open Graph / Twitter Card social unfurler image — 1200×630 JPEG/PNG, <5MB, with deterministic typography.
SkillDFreshness: D★ 24Claude Code +9
Signals
- Stars
- 24
- Forks
- 3
- Open issues
- 3
- Contributors
- 2
- Last commit (this folder)
- Apr 20, 2026 (6 months ago)
- Last release
- Apr 26, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from MohamedAbdallah-14
- 0.715score
unslop
MohamedAbdallah-14
Humanize LLM output so it reads like a careful human wrote it.
SkillBFreshness: B★ 161Claude Code +9 - 0.710score
unslop-file
MohamedAbdallah-14
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL…
SkillBFreshness: B★ 161Claude Code +9 - 0.709score
unslop-reasoning
MohamedAbdallah-14
Strip AI-slop patterns from reasoning traces (chain-of-thought, extended thinking, agent decomposition) — not final prose.
SkillBFreshness: B★ 161Claude Code +9 - 0.709score
unslop-commit
MohamedAbdallah-14
Rewrites commit messages so they sound like a careful human engineer wrote them.
SkillBFreshness: B★ 161Claude Code +9 - 0.709score
unslop-review
MohamedAbdallah-14
Rewrites code review comments so they read like a human teammate wrote them.
SkillBFreshness: B★ 161Claude Code +9 - 0.706score
unslop-help
MohamedAbdallah-14
Quick-reference card for unslop modes, sub-skills, and slash commands.
SkillBFreshness: B★ 161Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get vectorize running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
vectorize skill. Agent Mart. https://agentmart.dev/skills/mohamedabdallah-14-vectorize (last updated 2026-10-24)