CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

80

1.25x
Quality

Does it follow best practices?

Impact

78%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and gives real commands for initialization and bundling, but its actionability and navigation suffer because the referenced scripts and "Common Development Tasks" guidance do not exist, and the workflow lacks any verification checkpoints.

Suggestions

Provide the referenced scripts (scripts/init-artifact.sh, scripts/bundle-artifact.sh) or a Common Development Tasks section/file so the core development step has concrete guidance instead of a dangling reference.

Add validation/verification checkpoints — e.g. confirm the project scaffold built, verify bundle.html was produced and opens — to lift workflow clarity above 2.

Move the 40+ shadcn/ui component usage guidance into a one-level-deep reference file (e.g. references/shadcn-components.md) linked from the body, rather than relying on a single external URL.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence (no explanations of what React/Tailwind are), and each section delivers concrete configuration or command detail; the top step list functions as a navigation summary rather than filler.

3 / 3

Actionability

Concrete commands exist for init and bundle (e.g. `bash scripts/init-artifact.sh <project-name>`), but the central development step points to a "Common Development Tasks" section that does not exist, leaving the most important action under-specified.

2 / 3

Workflow Clarity

The five steps are clearly sequenced, but there are no validation or verification checkpoints (e.g. confirming the project initialized or that bundle.html renders), which caps clarity at 2 for a build workflow.

2 / 3

Progressive Disclosure

Sections are organized, but the body references files and a section that are absent from the bundle (no scripts/ directory, no Common Development Tasks section, no local reference file for shadcn usage), so navigation is partly broken.

2 / 3

Total

9

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description: third person, concise, with explicit positive and negative triggers and natural keywords. Its only weak spot is specificity, since it frames a single broad action rather than listing several concrete capabilities.

DimensionReasoningScore

Specificity

It names the domain (claude.ai HTML artifacts) and the concrete stack (React, Tailwind, shadcn/ui) but essentially describes one action ("creating") rather than enumerating multiple distinct actions like the level-3 anchor requires.

2 / 3

Completeness

It answers both "what" ("creating elaborate, multi-component claude.ai HTML artifacts") and "when" with an explicit "Use for..." clause plus a negative "not for simple single-file HTML/JSX artifacts" trigger.

3 / 3

Trigger Term Quality

It surfaces natural terms users actually say when requesting this work — "HTML artifacts", "React", "Tailwind", "shadcn/ui", "JSX", "state management", "routing" — giving good coverage of likely phrasings.

3 / 3

Distinctiveness Conflict Risk

The claude.ai-artifact + React/Tailwind/shadcn/ui niche is specific, and the negative trigger ("not for simple single-file HTML/JSX artifacts") actively disambiguates it from generic HTML skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
majiayu000/claude-skill-registry
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.