CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

92

1.75x
Quality

Does it follow best practices?

Impact

93%

1.75x

Average score across 10 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 body is concise and provides executable commands for project setup and bundling, but the core 'develop your artifact' step is underspecified with a dangling cross-reference, and the workflow lacks validation checkpoints for fragile build operations.

Suggestions

Replace or fulfill the 'See Common Development Tasks below' reference with a concrete section (or a referenced file) giving actionable guidance for editing the generated artifact code.

Add validation/verification steps to the bundle workflow (e.g., confirm index.html exists and check the build succeeded before sharing bundle.html), turning it into a validate->fix->retry loop.

Provide at least one concrete code example for the development step (component scaffolding, routing setup, or state management) so the central task is as actionable as the init/bundle steps.

DimensionReasoningScore

Conciseness

The body is lean and actionable, with copy-paste bash commands and no padding explaining React/Tailwind/Vite concepts Claude already knows; the few feature bullet-lists state concrete available capabilities rather than teaching.

3 / 3

Actionability

The init and bundle steps give fully executable, parameterized commands, but the central 'Develop Your Artifact' step offers no concrete guidance and points to 'Common Development Tasks below' which is not present in the body — an incomplete, dangling reference for the core task.

2 / 3

Workflow Clarity

A clear five-step sequence is present, but there are no explicit validation/checkpoint steps for the fragile init and bundle operations; per the rubric, missing validation feedback loops for build/bundle operations caps workflow clarity at 2.

2 / 3

Progressive Disclosure

Sections are well-organized and the referenced scripts are real one-level-deep bundle files, but the dangling 'See Common Development Tasks below' cross-reference (no such section exists) and absence of a referenced development guide prevent fully clean navigation.

2 / 3

Total

9

/

12

Passed

Description

100%

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 strong description: it states concrete capabilities, lists the relevant tech stack, gives an explicit positive trigger, and adds a negative trigger to avoid misuse. It is concise without padding or over-claims.

DimensionReasoningScore

Specificity

Enumerates concrete capabilities — 'creating elaborate, multi-component claude.ai HTML artifacts', the React/Tailwind/shadcn/ui stack, and 'state management, routing, or shadcn/ui components' — matching the anchor that lists multiple specific concrete actions.

3 / 3

Completeness

States both what it does ('Suite of tools for creating elaborate, multi-component ... artifacts') and an explicit 'Use for ...' trigger plus a negative trigger ('not for simple single-file HTML/JSX artifacts'), clearly answering what AND when.

3 / 3

Trigger Term Quality

Covers the natural surface vocabulary for its niche ('HTML artifacts', 'shadcn/ui components', 'single-file HTML/JSX artifacts', 'state management', 'routing') that a user would plausibly say.

3 / 3

Distinctiveness Conflict Risk

A clear niche (multi-component claude.ai React artifacts) with a distinct negative trigger ruling out simple single-file artifacts, making overlap with generic HTML skills unlikely.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
boisenoise/skills-collections
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.