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.

79

1.25x
Quality

76%

Does it follow best practices?

Impact

78%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/03-developer-artifactsbuilder/SKILL.md

The canonical home for this skill is artifacts-builder in majiayu000/claude-skill-registry

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is well-structured and gives executable commands for the core workflow, but it is undermined by dangling references: cited scripts are not bundled and a referenced subsection is absent.

Suggestions

Ship the referenced `scripts/init-artifact.sh` and `scripts/bundle-artifact.sh` in a scripts/ bundle, or remove the script invocations in favor of inline commands.

Add the missing 'Common Development Tasks' section that Step 2 directs the reader to, or drop the forward reference.

Add a brief verification checkpoint after bundling (e.g., confirm `bundle.html` exists and opens) to strengthen the workflow.

DimensionReasoningScore

Conciseness

Largely lean with concrete commands and a compact stack line; the emoji checkmark list and a few explanatory asides (e.g., the testing-latency note) could be trimmed but are not severely padded.

4 / 5

Actionability

Provides copy-paste-ready commands (`bash scripts/init-artifact.sh <project-name>`, `bash scripts/bundle-artifact.sh`) and explains what the bundle step does, but Step 2 points to a 'Common Development Tasks' section that does not exist in the body.

4 / 5

Workflow Clarity

A clear five-step sequence (init → develop → bundle → display → optional test) is presented up front and expanded per step; no explicit verification that bundle.html was produced, but the operation is not destructive/batch so the validation cap does not apply.

4 / 5

Progressive Disclosure

Section structure is reasonable, but the body references `scripts/init-artifact.sh` and `scripts/bundle-artifact.sh` while no scripts/ bundle exists, and Step 2 cites a missing 'Common Development Tasks' section — references that do not resolve.

3 / 5

Total

15

/

20

Passed

Description

82%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.

A strong description that clearly states both purpose and triggering conditions, with a helpful negative boundary to avoid false triggers. It is slightly thin on enumerating distinct capabilities beyond 'creating'.

DimensionReasoningScore

Specificity

Names the domain (claude.ai HTML artifacts) and the concrete stack (React, Tailwind, shadcn/ui) but only surfaces one main action ('creating elaborate, multi-component' artifacts), so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts...') and when ('Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts'), with concrete triggers and a negative boundary.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('claude.ai HTML artifacts', 'React, Tailwind CSS, shadcn/ui', 'state management, routing', 'shadcn/ui components') with good coverage, though it omits synonyms and file extensions like .html.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (React + shadcn/ui claude.ai artifacts) with distinct triggers and an explicit exclusion ('not for simple single-file HTML/JSX artifacts') that minimizes overlap with simpler artifact skills.

5 / 5

Total

17

/

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

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
majiayu000/claude-skill-registry-data
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.