CtrlK
BlogDocsLog inGet started
Tessl Logo

web-artifacts-builder

Build complex claude.ai HTML artifacts with React and Tailwind. Anthropic's reference workflow for shipping rich, embeddable artifacts.

44

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/web-artifacts-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

40%Weight 40%Scale 1-5

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

This is a catalogue pointer rather than a working skill: it advertises an upstream bundle and tells the agent to install it, but provides no concrete install steps or actionable workflow. Structure and brevity are decent, but actionability and workflow clarity are weak.

Suggestions

Replace the `open <url>` block with actual install commands (e.g., clone/copy the upstream bundle into the skills directory) so the guidance is executable.

Spell out the install-then-invoke workflow as numbered steps with a verification checkpoint confirming the skill is registered before invocation.

Remove the verbatim description duplication and the 'Curated from...' blockquote to tighten the body.

DimensionReasoningScore

Conciseness

The body is short and mostly efficient, but it repeats the frontmatter description verbatim in 'What it does' and carries marketing filler ('Curated from Anthropic's official skills repository') that could be trimmed.

3 / 5

Actionability

Guidance is high-level ('install the upstream bundle into your active agent's skills directory') with no concrete install steps; the only code block is `open <url>`, which opens a browser rather than executing an install.

2 / 5

Workflow Clarity

A rough sequence exists (install upstream bundle, then invoke by name or trigger) but the install step is undefined and there are no validation checkpoints, leaving major gaps.

2 / 5

Progressive Disclosure

The body is well-organized into clear sections (What it does, Source, How to use) and points to a single clearly-signaled external reference, appropriate for a sub-50-line pointer skill.

4 / 5

Total

11

/

20

Passed

Description

53%Weight 40%Scale 1-5

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

The description clearly identifies a specific niche and tech stack but stops short of listing multiple concrete actions or providing explicit 'when to use' guidance. It reads more as a credential statement than a complete trigger description.

Suggestions

Expand beyond the single 'Build' action to list 2-3 concrete capabilities (e.g., scaffold, style with Tailwind, wire up React state).

Add an explicit 'Use when...' clause referencing natural trigger phrases like 'web artifacts', 'tailwind artifact', or 'react artifact'.

Drop the marketing line 'Anthropic's reference workflow...' which adds no trigger-relevant signal.

DimensionReasoningScore

Specificity

Names the concrete domain ('claude.ai HTML artifacts with React and Tailwind') and one action ('Build'), but offers only a single generic action with no breakdown of capabilities.

3 / 5

Completeness

Has a clear 'what' (build React/Tailwind HTML artifacts) but no 'Use when...' or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Contains relevant keywords ('HTML artifacts', 'React', 'Tailwind') but omits natural trigger variations users would actually say, like 'web artifact' or 'tailwind artifact' that appear in the separate triggers field.

3 / 5

Distinctiveness Conflict Risk

The 'claude.ai HTML artifacts with React and Tailwind' niche is specific and mostly distinct, with only minor overlap risk against general web-development skills.

4 / 5

Total

13

/

20

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.