CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

69%

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

56%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 offers strong, specific production rules and a well-sequenced gated workflow, but it suffers from substantial duplication (capabilities comment, repeated reference listings, repeated version notes) and delegates to reference files that are absent from the bundle. Tightening the inline material and consolidating reference navigation would materially improve it.

Suggestions

Remove the CAPABILITIES_SUMMARY/COLLABORATION HTML comment block — its content is already duplicated in Framework Coverage, Recipes, and the Collaboration section — and consolidate the four separate reference-file listings into the Reference Map.

Move time-sensitive version and date details (Vue 3.5.x/3.6 beta status, React CVE-2025-55182 pin lists, Zod v4 / TanStack Form release notes) into a single dedicated reference or version-pin section instead of repeating them inline.

Ensure all cited reference/*.md and _common/*.md files actually exist in the bundle; the Reference Map currently points to roughly 14 files that are not present.

DimensionReasoningScore

Conciseness

The body is noticeably padded with redundant material: a ~35-line CAPABILITIES_SUMMARY HTML comment that duplicates Framework Coverage and Recipes, collaboration partners listed twice (comment + Collaboration section), reference files listed in four separate tables (Workflow, Output Routing, Recipes, Reference Map), and time-sensitive version/date details (Vue 3.5/3.6 beta with "[2026-05]" source dates, Zod v4 speed claims, React CVE pin lists) repeated inline rather than isolated. This fits "several unnecessary padded sections" better than the mostly-efficient 3.

2 / 5

Actionability

Guidance is concrete and executable in rule form: named APIs ("useEffectEvent", "useFormStatus in a child of <form>"), exact thresholds (WCAG targets "≥ 24×24px", "INP < 200ms", "scheduler.yield()" for >50ms handlers), and version pins for CVE-2025-55182. It is not fully copy-paste ready since no worked code examples appear inline and all executable detail is delegated to reference files that are not present in the bundle.

4 / 5

Workflow Clarity

ANALYZE → DESIGN → IMPLEMENT → VERIFY → HANDOFF is clearly sequenced with a phase table, per-recipe VERIFY gates, a completion checklist, and the CODE_QUALITY_GATE before done. It stops short of a 5 because error-recovery feedback loops (what to do when a VERIFY gate fails) are only implicit — gates block completion but no fix-and-revalidate loop is described.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep (Reference Map with "Read this when", Recipes "Read First" column), but the bundle contains none of the ~14 cited reference/ and _common/ files, so navigation cannot be verified, and substantial detail that belongs in those references (capability summaries, version/date pins, handoff tables) is inlined. This is "some structure but could be better organized" rather than the well-split 4.

3 / 5

Total

13

/

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 communicates a clear, specific capability set with strong framework-name triggers, but it lacks an explicit "Use when..." trigger clause, which caps completeness and weakens invocation guidance. Adding a trigger clause covering frontend production work and prototype conversion would resolve the main gap.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when implementing production React, Vue, or Svelte components, or when converting a prototype into production-quality UI."

Include accessibility and TypeScript strictness in the description, since the body presents them as non-negotiable parts of every deliverable.

Add common trigger synonyms such as "component", "UI", and "front-end" to improve natural-term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("hooks design, state management, Server Components, form handling, data fetching") plus prototype conversion. It falls short of comprehensive because it omits accessibility, TypeScript strictness, and styling, which the body itself treats as core non-negotiable deliverables.

4 / 5

Completeness

It clearly answers "what" ("Implementing production frontend code for React/Vue/Svelte: hooks design, state management, Server Components, form handling, data fetching") but has no "Use when..." clause — "Converts Forge prototypes to production quality" describes an action, not when to invoke the skill, so completeness is capped at 3.

3 / 5

Trigger Term Quality

"React/Vue/Svelte", "hooks", "state management", "form handling", and "data fetching" are natural terms users would say for frontend work. A few common variations are missing ("component", "UI", "front-end"), so it does not reach the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

"production frontend code for React/Vue/Svelte" plus prototype-to-production conversion is a distinct niche with unlikely wrong-skill triggers. Minor overlap risk remains with closely related skills (general web development, mockup-to-code, or performance skills) since terms like "form handling" and "data fetching" are broadly applicable.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

simota/agent-skills

Path

artisan/SKILL.md

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.