pixel-art
Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/pixel-art/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly defines its niche (pixel art SVG illustrations) and provides excellent trigger term coverage including multilingual terms. The main weakness is that the 'what' portion could be more specific about the range of concrete actions beyond just 'generate'. Overall, it would perform well in skill selection among a large pool of skills.
Suggestions
Expand the capability list with more specific actions, e.g., 'Generate pixel art SVG illustrations including characters, icons, banners, and scene art for READMEs, docs, or slides.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (pixel art SVG illustrations) and mentions use cases (READMEs, docs, slides), but doesn't list multiple concrete actions beyond 'generate'. It could specify more actions like 'design characters', 'create icons', 'animate sprites', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate pixel art SVG illustrations for READMEs, docs, or slides) and 'when' with an explicit 'Use when...' clause listing specific trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including multilingual support ('画像素图'), common English phrases ('pixel art', 'make an SVG illustration', 'README hero image'), and the casual 'cute visual'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining pixel art + SVG + illustration purposes. The specific trigger terms like 'pixel art' and '画像素图' are unlikely to conflict with general SVG or image generation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent concrete examples including exact pixel dimensions, color palettes, and copy-paste SVG snippets. Its main weaknesses are the lack of validation checkpoints in the workflow (e.g., checking SVG renders correctly before proceeding) and some minor verbosity in the workflow steps that Claude could infer. The domain-specific knowledge like the character template, bubble recipes, and common pitfalls section are genuinely valuable additions to Claude's capabilities.
Suggestions
Add an explicit validation step in the workflow, e.g., 'Verify viewBox dimensions match content bounds before showing to user' or a quick self-check list before preview.
Trim the workflow Step 1 questions — Claude can infer what to ask; instead, focus on non-obvious constraints or defaults to apply when the user doesn't specify.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is fairly detailed and mostly earns its place with specific pixel values, color codes, and SVG snippets. However, some sections like the workflow steps (Step 1: 'What characters/objects to draw?') are somewhat obvious for Claude and could be trimmed. The character template and recipes are valuable domain-specific knowledge. | 2 / 3 |
Actionability | Highly actionable with executable SVG code snippets for chat bubbles, arrows, character templates with exact pixel dimensions, specific color hex codes, and copy-paste ready XML structures. The character template gives exact row-by-row pixel layouts. | 3 / 3 |
Workflow Clarity | The 4-step workflow is clearly sequenced and includes iteration with the user, but lacks explicit validation checkpoints. There's no verification step to check SVG validity, no error recovery for malformed SVG, and the 'open <file.svg> for preview' step doesn't describe what to validate in the preview. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a fairly long monolithic file (~120 lines of substantive content). The multiple scene composition types and recipes could be split into referenced files. However, for a creative/generative skill, having everything inline is somewhat justified. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
dc00dfb
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.