web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
91
70%
Does it follow best practices?
Impact
93%
1.72xAverage score across 10 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/anthropic-web-artifacts-builder/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 strong description that clearly defines its niche (complex multi-component HTML artifacts on claude.ai) with good technology-specific trigger terms and an explicit negative boundary that aids skill selection. The main weakness is that the 'what' portion describes the domain and technologies rather than listing specific concrete actions the skill enables. Overall it would perform well in a multi-skill selection scenario.
Suggestions
Add 2-3 specific concrete actions to improve specificity, e.g., 'Creates multi-page dashboards, builds interactive forms with validation, implements tabbed layouts with shared state'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (HTML artifacts) and some technologies (React, Tailwind CSS, shadcn/ui), and mentions state management and routing, but doesn't list specific concrete actions like 'create dashboards, build multi-page apps, implement form wizards'. The capabilities are described more as categories than specific actions. | 2 / 3 |
Completeness | Clearly answers both what ('creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies') and when ('Use for complex artifacts requiring state management, routing, or shadcn/ui components'), and even specifies when NOT to use it ('not for simple single-file HTML/JSX artifacts'), which is excellent for disambiguation. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'React', 'Tailwind CSS', 'shadcn/ui', 'HTML artifacts', 'state management', 'routing', 'multi-component', 'complex artifacts', 'claude.ai'. These cover the key terms a user would naturally mention when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear boundaries: specifically targets multi-component, complex claude.ai HTML artifacts with named technologies, and explicitly excludes simple single-file artifacts. The negative boundary ('not for simple single-file HTML/JSX artifacts') significantly reduces conflict risk with simpler artifact-generation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a clear high-level workflow for creating React-based Claude artifacts with concrete shell commands for initialization and bundling. However, it suffers from a missing 'Common Development Tasks' section that Step 2 references, lacks validation/error-recovery steps in the build pipeline, and includes some unnecessary detail about internal script mechanics while omitting the actual development guidance that would make it fully actionable.
Suggestions
Add the missing 'Common Development Tasks' section or link to a separate file covering how to edit components, add routes, manage state, etc.
Add validation checkpoints after the bundle step (e.g., verify bundle.html exists, check file size, common error messages and fixes)
Remove the internal details of what the bundle script does (parcel config, html-inline) since Claude just needs to run the command, not understand its internals
Make Step 4 concrete - show the exact mechanism for sharing bundle.html as an artifact (e.g., reading the file and outputting it in an artifact block)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary padding like the checklist of what the init script creates (✅ bullets) and explanations of what the bundle script does internally, which Claude doesn't need to know to use it. The 'AI slop' design guideline is useful but could be more concise. | 2 / 3 |
Actionability | The init and bundle commands are concrete and executable, but Step 2 ('edit the generated files, see Common Development Tasks below') references a section that doesn't exist in the content. Step 4 ('share the bundled HTML file') is vague with no concrete mechanism shown. The actual development guidance is missing. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and easy to follow. However, there are no validation checkpoints - no guidance on what to do if bundling fails, no verification that bundle.html was created correctly, and no error recovery steps for a process that involves multiple build tools. | 2 / 3 |
Progressive Disclosure | References an external shadcn/ui docs link and mentions 'Common Development Tasks' section that doesn't exist. The content is reasonably structured with clear sections, but the missing referenced section is a significant gap. The skill could benefit from splitting detailed bundling internals into a separate reference file. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- boisenoise/skills-collections
- Commit
431bfad
- 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.