Install
Quick install
npx skills add https://github.com/marsmike/feinschliffnpx skills add marsmike/feinschliff --agent claude-codenpx skills add marsmike/feinschliff --agent cursornpx skills add marsmike/feinschliff --agent codexnpx skills add marsmike/feinschliff --agent opencodenpx skills add marsmike/feinschliff --agent github-copilotnpx skills add marsmike/feinschliff --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add marsmike/feinschliffManual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/marsmike/feinschliff.gitcp -r feinschliff ~/.claude/skills/Svg
Use when authoring custom data viz that doesn't fit a predefined chart layout — brand-aware SVG infographics via compact DSL.
---
name: svg
description: Use when authoring custom data viz that doesn't fit a predefined chart layout — brand-aware SVG infographics via compact DSL.
---
SVG Infographic Authoring
Generate brand-perfect SVG infographics using a compact DSL. Colors resolve against the active feinschliff brand pack — no per-skill palette. Use when the predefined chart layouts (bar-chart, stacked-bar, kpi-grid, scorecard, funnel) don't fit and a custom viz is needed.
Quick start
Author a .svg.dsl file, expand it, then render. The default brand is feinschliff; override via --brand <name>, FEINSCHLIFF_BRAND=<name>, or an inline @brand <name> directive at the top of the DSL.
cd /path/to/feinschliff
uv run python -m lib.diagrams.svg_expand chart.svg.dsl # add --brand <name> to override
uv run python -m lib.diagrams.render chart.svg # → chart.png
Inspect the PNG. If something is off, adjust the DSL (positions, sizes, semantic colors) and re-run. One fix loop max — escalate to references if more is needed.
References
- [DSL reference](references/dsl-reference.md) — primitives, semantic colors, layout
- [Examples](references/examples.md) — small / medium / complex fixtures
SVG Infographic Authoring
Generate brand-perfect SVG infographics using a compact DSL. Colors resolve against the active feinschliff brand pack — no per-skill palette. Use when the predefined chart layouts (bar-chart, stacked-bar, kpi-grid, scorecard, funnel) don't fit and a custom viz is needed.
Quick start
Author a .svg.dsl file, expand it, then render. The default brand is feinschliff; override via --brand <name>, FEINSCHLIFF_BRAND=<name>, or an inline @brand <name> directive at the top of the DSL.
cd /path/to/feinschliff
uv run python -m lib.diagrams.svg_expand chart.svg.dsl # add --brand <name> to override
uv run python -m lib.diagrams.render chart.svg # → chart.png
Inspect the PNG. If something is off, adjust the DSL (positions, sizes, semantic colors) and re-run. One fix loop max — escalate to references if more is needed.
References
- [DSL reference](references/dsl-reference.md) — primitives, semantic colors, layout
- [Examples](references/examples.md) — small / medium / complex fixtures
---
Source: https://github.com/marsmike/feinschliff
Author: marsmike
Discovered via: skillsdirectory.com
Genre: ai-agents
SKILL.md source
---
name: Svg
description: Use when authoring custom data viz that doesn't fit a predefined chart layout — brand-aware SVG infographics via compact DSL.
---
# Svg
Use when authoring custom data viz that doesn't fit a predefined chart layout — brand-aware SVG infographics via compact DSL.
---
name: svg
description: Use when authoring custom data viz that doesn't fit a predefined chart layout — brand-aware SVG infographics via compact DSL.
---
# SVG Infographic Authoring
Generate brand-perfect SVG infographics using a compact DSL. Colors resolve against the active feinschliff brand pack — no per-skill palette. Use when the predefined chart layouts (`bar-chart`, `stacked-bar`, `kpi-grid`, `scorecard`, `funnel`) don't fit and a custom viz is needed.
## Quick start
Author a `.svg.dsl` file, expand it, then render. The default brand is `feinschliff`; override via `--brand <name>`, `FEINSCHLIFF_BRAND=<name>`, or an inline `@brand <name>` directive at the top of the DSL.
```bash
cd /path/to/feinschliff
uv run python -m lib.diagrams.svg_expand chart.svg.dsl # add --brand <name> to override
uv run python -m lib.diagrams.render chart.svg # → chart.png
```
Inspect the PNG. If something is off, adjust the DSL (positions, sizes, semantic colors) and re-run. One fix loop max — escalate to references if more is needed.
## References
- [DSL reference](references/dsl-reference.md) — primitives, semantic colors, layout
- [Examples](references/examples.md) — small / medium / complex fixtures
38:["$","div",null,{"className":"flex flex-wrap items-center gap-3 mb-8","children":[["$","$L3b",null,{"skillId":"f19a2e7f-ed6d-47fc-9ed4-27afe5a37069","content":"$3c"}],["$","a",null,{"href":"/api/skills/marsmike-svg/download","target":"_blank","rel":"noopener noreferrer","className":"inline-flex items-center justify-center gap-2 px-4 py-2 text-sm font-medium border border-input bg-background hover:bg-accent hover:text-accent-foreground transition-colors","children":[["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":16,"height":16,"fill":"currentColor","viewBox":"0 0 256 256","transform":"$undefined","children":[false,"$undefined",["$","path",null,{"d":"M224,144v64a8,8,0,0,1-8,8H40a8,8,0,0,1-8-8V144a8,8,0,0,1,16,0v56H208V144a8,8,0,0,1,16,0Zm-101.66,5.66a8,8,0,0,0,11.32,0l40-40a8,8,0,0,0-11.32-11.32L136,124.69V32a8,8,0,0,0-16,0v92.69L93.66,98.34a8,8,0,0,0-11.32,11.32Z"}]]}],"Download Zip"]}],["$","$L3d",null,{"skillId":"f19a2e7f-ed6d-47fc-9ed4-27afe5a37069","skillSlug":"marsmike-svg","initialVoted":false}]]}]
3f:T4d9,---
name: svg
description: Use when authoring custom data viz that doesn't fit a predefined chart layout — brand-aware SVG infographics via compact DSL.
---
# SVG Infographic Authoring
Generate brand-perfect SVG infographics using a compact DSL. Colors resolve against the active feinschliff brand pack — no per-skill palette. Use when the predefined chart layouts (`bar-chart`, `stacked-bar`, `kpi-grid`, `scorecard`, `funnel`) don't fit and a custom viz is needed.
## Quick start
Author a `.svg.dsl` file, expand it, then render. The default brand is `feinschliff`; override via `--brand <name>`, `FEINSCHLIFF_BRAND=<name>`, or an inline `@brand <name>` directive at the top of the DSL.
```bash
cd /path/to/feinschliff
uv run python -m lib.diagrams.svg_expand chart.svg.dsl # add --brand <name> to override
uv run python -m lib.diagrams.render chart.svg # → chart.png
```
Inspect the PNG. If something is off, adjust the DSL (positions, sizes, semantic colors) and re-run. One fix loop max — escalate to references if more is needed.
## References
- [DSL reference](references/dsl-reference.md) — primitives, semantic colors, layout
- [Examples](references/examples.md) — small / medium / complex fixtures
41:[]
---
**Source**: https://github.com/marsmike/feinschliff
**Author**: marsmike
**Discovered via**: skillsdirectory.com
**Genre**: ai-agents
Related skills 6
running-claude-code-via-litellm-copilot
Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.
skills-cli
Use when users ask to discover, install, list, check, update, remove, back up, restore, sync, or initialize Agent Skills, mention `bunx skills`, `npx skills`, `skills.sh`, or `skills-lock.json`, ask "find a skill for X", or want help extending agent capabilities with installable skills.
repo-intake-and-plan
Narrow RigorPilot helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
image-to-video
Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning ite...
video-edit
Edit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets...
nano-banana-2
Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream in...