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.

76

2.50x
Quality

66%

Does it follow best practices?

Impact

95%

2.50x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

57%

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, mostly lean workflow with executable commands and well-structured one-level references to real bundle files. Its main weaknesses are a dangling 'Common Development Tasks' reference and the absence of validation checkpoints.

Suggestions

Add or correctly link the missing 'Common Development Tasks' section referenced in Step 2, so the core development step has concrete guidance.

Introduce an explicit verification step after bundling (e.g., open bundle.html / run a quick smoke check) instead of marking all testing as optional.

Collapse the duplicated five-step list so the workflow appears once, either as a brief overview or as the expanded Quick Start.

DimensionReasoningScore

Conciseness

The body is action-oriented without teaching basic concepts, but the five-step workflow is presented twice (a top-level numbered list then re-expanded under Quick Start), which could be tightened.

2 / 3

Actionability

Init and bundle steps give fully executable commands, but Step 2 ('Develop Your Artifact') points to a 'Common Development Tasks' section that does not exist in the body, leaving the core development step under-specified.

2 / 3

Workflow Clarity

The five steps are clearly sequenced, but there are no validation/verification checkpoints (testing is optional and deferred), and the broken 'Common Development Tasks' reference interrupts the sequence.

2 / 3

Progressive Disclosure

The body is a concise overview with well-signaled one-level-deep references to real bundle scripts (scripts/init-artifact.sh, scripts/bundle-artifact.sh) and an external shadcn docs link, all of which resolve to real files.

3 / 3

Total

9

/

12

Passed

Description

75%

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 defines a niche with explicit use/avoid triggers and a concrete tech stack, answering both what and when. It is slightly held back by a single action verb and moderately jargony trigger phrasing.

Suggestions

Add more concrete action verbs (e.g., 'Build, scaffold, and bundle multi-component claude.ai artifacts') to broaden the action coverage beyond just 'creating'.

Include more natural user phrasings such as 'React app', 'web dashboard', or 'interactive artifact' alongside the technical terms.

DimensionReasoningScore

Specificity

Names the domain ('claude.ai HTML artifacts') and concrete technologies (React, Tailwind CSS, shadcn/ui), but the only action verb is 'creating', so it is not a comprehensive list of multiple concrete actions as a score of 3 requires.

2 / 3

Completeness

It states what the skill does and gives an explicit 'Use for ... - not for ...' trigger clause, clearly answering both 'what' and 'when'.

3 / 3

Trigger Term Quality

Relevant terms like 'claude.ai HTML artifacts', 'state management', 'routing', and 'shadcn/ui' appear, but the phrasing ('elaborate, multi-component ... modern frontend web technologies') is somewhat jargony and misses common user variations like 'React app' or 'dashboard'.

2 / 3

Distinctiveness Conflict Risk

The explicit negative boundary ('not for simple single-file HTML/JSX artifacts') and narrow niche (multi-component artifacts needing state management/routing/shadcn) make it clearly distinguishable and unlikely to trigger for the wrong skill.

3 / 3

Total

10

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.