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).

45

Quality

48%

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/artifacts-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 lean, well-organized catalogue/discovery entry rather than an executable skill: it cleanly routes to the upstream bundle but provides almost no actionable artifact-building guidance itself.

Suggestions

Replace the bare `open <url>` hint with concrete, executable install steps (e.g., the actual clone/copy commands and target skills-directory path).

Inline a minimal quick-start snippet (a basic React/Tailwind/shadcn artifact skeleton) so the skill is useful before the upstream bundle is fetched.

Add local reference files (e.g., a scaffold template or component-patterns doc) and link them with one-level-deep navigation instead of offloading everything to an external repository.

DimensionReasoningScore

Conciseness

The body is short and free of padded explanations of concepts Claude already knows, with the only trimmable redundancy being the verbatim duplication of the description in 'What it does'.

4 / 5

Actionability

The only concrete guidance is an `open <github-url>` command and 'ask the agent to invoke this skill'; it provides high-level hints but no specific steps or code for actually building artifacts.

2 / 5

Workflow Clarity

A rough three-step sequence is present (inspect upstream README, install the bundle, invoke by name/trigger) but steps are vague with no checkpoints or concrete install commands.

3 / 5

Progressive Disclosure

Sections are clearly organized and point to a single-level upstream URL, but all substantive content is deferred to an external repo with no local reference files present.

3 / 5

Total

12

/

20

Passed

Description

46%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 is clear and third-person with a well-defined niche, but it states only one action verb and lacks any explicit 'Use when...' trigger guidance, capping completeness and leaving trigger-term coverage thin.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases (e.g., 'Use when building React/Tailwind/shadcn artifacts for claude.ai, multi-component HTML artifacts, or interactive web demos').

Expand the action list beyond 'creating' to concrete verbs like scaffold, style, compose, and preview multi-component artifacts.

Include common synonyms/file cues users actually say (e.g., 'HTML artifact', 'React component', 'shadcn UI') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"creating elaborate, multi-component claude.ai HTML artifacts" names the domain plus a concrete action and lists specific technologies (React, Tailwind CSS, shadcn/ui), but offers only one action verb with no comprehensive action list.

3 / 5

Completeness

It clearly answers 'what' (suite of tools for creating multi-component HTML artifacts) but provides no 'Use when...' trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

The description surfaces technology names (React, Tailwind, shadcn/ui) as a couple of relevant keywords but omits natural user phrases like 'build an artifact' or 'React component', matching the 'one or two generic keywords; missing natural phrases' anchor.

2 / 5

Distinctiveness Conflict Risk

The claude.ai HTML artifacts niche scoped to a specific React/Tailwind/shadcn stack is mostly distinct with only minor overlap risk against generic web-development skills.

4 / 5

Total

12

/

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.