CtrlK
BlogDocsLog inGet started
Tessl Logo

artisan

Implementing production frontend code for React/Vue/Svelte: hooks design, state management, Server Components, form handling, data fetching. Converts Forge prototypes to production quality.

58

Quality

66%

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 ./artisan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 with a clear phased workflow, explicit per-recipe verification gates, and a clean reference map, but it carries redundant capability/collaboration listings and inline source citations that hurt token efficiency, and its referenced bundle files are absent.

Suggestions

Remove the redundant CAPABILITIES_SUMMARY / COLLABORATION_PATTERNS / BIDIRECTIONAL_PARTNERS HTML comment block since the Framework Coverage, Output Routing, and Collaboration tables already cover that information.

Move the inline '[Source: ...]' citations and time-sensitive version pinning detail into the relevant reference files (or a dedicated 'versions/deprecations' section) to keep the overview lean.

Ensure the referenced reference/*.md files are present in the bundle so the progressive-disclosure structure is verifiable rather than aspirational.

DimensionReasoningScore

Conciseness

The core instructional content is expert-level and assumes Claude's competence, but there is noticeable redundancy — the top CAPABILITIES_SUMMARY/COLLABORATION comment block duplicates the later tables — and pervasive inline '[Source: ...]' citations and version-specific detail add tokens that could be tightened or moved to references.

3 / 5

Actionability

Guidance is concrete and actionable — e.g. 'Pin to patched versions (19.0.1+, 19.1.2+, or 19.2.1+; Next.js 15.1.4+)', 'useFormStatus in a child of <form>', and the branded-type snippet 'type UserId = string & { __brand: "UserId" }' — with minor gaps because most implementation patterns are deferred to reference files.

4 / 5

Workflow Clarity

The ANALYZE → DESIGN → IMPLEMENT → VERIFY → HANDOFF table gives a clear sequenced workflow with a dedicated VERIFY phase and per-recipe VERIFY gates, but the main workflow's validation is a phase gate rather than an explicit validate→fix→retry feedback loop within steps.

4 / 5

Progressive Disclosure

Structure is good with a Reference Map table signaling one-level-deep reference files and clear navigation, but some detail-heavy content (CVE pins, version specifics, INP rules) is inlined rather than delegated, and the referenced reference/*.md bundle files are not actually present to verify the structure.

4 / 5

Total

15

/

20

Passed

Description

66%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 specific and names a clear frontend-production niche with good natural trigger terms, but it omits any explicit 'Use when...' trigger guidance, which caps its completeness.

Suggestions

Append an explicit 'Use when...' clause (e.g. 'Use when converting Forge prototypes to production React/Vue/Svelte components, or building production-quality, accessible, type-safe UI') to satisfy the completeness/when dimension.

Add a couple of common synonyms a user might say ('component', 'UI', 'frontend') to round out trigger-term coverage toward 5.

Optionally surface accessibility/styling in the capability list so the described actions match the body's full scope.

DimensionReasoningScore

Specificity

Names the domain ('production frontend code for React/Vue/Svelte') and lists several concrete actions — 'hooks design, state management, Server Components, form handling, data fetching' plus 'Converts Forge prototypes to production quality' — with only minor coverage gaps (e.g. accessibility/styling are absent).

4 / 5

Completeness

It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Strong natural keywords users would actually say — 'React', 'Vue', 'Svelte', 'hooks', 'Server Components', 'form handling', 'data fetching' — but a few common variants/synonyms (e.g. 'component', 'UI', file extensions) are missing, so it is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The named frameworks plus the Forge-prototype-to-production niche make it mostly distinct with only minor overlap risk against closely related frontend skills (Forge, Pixel).

4 / 5

Total

15

/

20

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
simota/agent-skills
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.