CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

senior-frontend

Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.

Quality

71%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/senior-frontend/SKILL.md

The canonical home for this skill is senior-frontend in administrakt0r/AI-Agents-Safe-Coding-Skills

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.

Strong script-driven workflows with exact commands, option tables, and a genuine fix-and-re-run feedback loop in bundle analysis. However, the file duplicates large amounts of reference-file content teaching React/Next.js concepts Claude already knows, inflating token cost and undermining the overview-plus-references structure.

Suggestions

Move the inline Compound Components, Render Props, Server/Client Components, image optimization, and accessibility/testing code out of SKILL.md into the existing references/*.md files, keeping one-line pointers per topic — this fixes both the conciseness and progressive_disclosure issues.

Trim the Quick Reference section (cn() conditional classes, generic TypeScript List component) — this is knowledge Claude already has and adds pure token cost.

Fix non-executable snippets (e.g. the invalid '("use client")' syntax and the Tabs example missing imports and TabsContext) or drop them in favor of the reference files.

DimensionReasoningScore

Conciseness

Roughly half the file re-teaches concepts Claude already knows — Compound Components, Render Props, useDebounce, Server vs Client Components, Suspense streaming, generic TypeScript List patterns, focus-visible styling — despite reference files existing for exactly these topics. This is 'several unnecessary explanations or padded sections' (anchor 2); not 3 because the duplication spans four-plus sections rather than isolated instances, not 1 because the script-workflow sections are lean and command-focused.

2 / 5

Actionability

The tool workflows are fully executable with exact commands and flags ('python scripts/frontend_scaffolder.py my-app --template nextjs', 'python scripts/component_generator.py Button --dir src/components/ui') plus options tables and sample output. Not 5 because several inline snippets are broken as written — '("use client")' is invalid directive syntax and the Tabs example lacks imports and context definitions; not 3 because the core workflows are copy-paste ready.

4 / 5

Workflow Clarity

Workflows are numbered with exact commands; bundle analysis includes a feedback loop ('Apply the recommended fixes... Re-run with verbose mode') and scaffolding ends with starting the dev server. Not 5 because there are no explicit validation checkpoints and component generation lacks any verification step; not 3 because sequences are complete and the operations are generative/read-only, so the destructive/batch validation cap does not apply.

4 / 5

Progressive Disclosure

All three references are real, one level deep, and clearly signaled ('Reference: references/react_patterns.md') with a TOC, but about half the body inlines the very content those reference files hold (React patterns, Next.js optimization, accessibility/testing) — 'content that should be separate is inline' at a major scale. Not 4 because the duplication is not a minor gap; not 2 because structure is good and references are clearly signaled, not buried.

3 / 5

Total

13

/

20

Passed

Description

75%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 solid description with an explicit six-trigger 'Use when' clause and a clearly named technology stack. The 'what' half is a domain label rather than a list of concrete capabilities, and a few natural trigger terms (hooks, testing, UI) are missing.

Suggestions

Replace the domain-label opening with concrete capabilities, e.g. 'Provides project scaffolding, component generation, and bundle analysis scripts plus React/Next.js optimization patterns... Use when...' — this would raise completeness to a 5.

Add missing natural trigger terms such as 'custom hooks', 'testing', and 'frontend performance' to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists six verb+object actions ('building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality'), matching the 'several specific actions; minor gaps' anchor. Not 5 because body-covered capabilities like custom hooks and testing strategies are absent; well above 3 since it goes far beyond 1-2 actions.

4 / 5

Completeness

Explicit 'Use when...' clause with six concrete triggers satisfies the 'when' strongly, but the 'what' is only a domain label ('Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications') rather than concrete capabilities. Sits between anchors 4 and 5: the 'when' exceeds anchor 4's expectations, but the 'what' does not meet anchor 5's 'clearly and explicitly answers both'.

4 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say ('React components', 'bundle sizes', 'scaffolding', 'accessibility', 'code quality') plus the full stack names. Not 5 because common variations like 'hooks', 'UI', or 'web app' are missing; above 3 since coverage is good, not just 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The named stack (React, Next.js, TypeScript, Tailwind CSS) creates a clear niche with distinct triggers. Not 5 because broad phrases like 'reviewing frontend code quality' and 'frontend development' leave minor overlap risk with general web-dev, CSS, or testing skills; clearly above anchor 3.

4 / 5

Total

16

/

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.

Validation — 15 / 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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/senior-frontend/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.