CtrlK
BlogDocsLog inGet started
Tessl Logo

nextjs-react-expert

React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.

60

Quality

70%

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 ./.agents/skills/nextjs-react-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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.

Well-organized navigation and clear review workflows, but the skill is fundamentally broken as a progressive-disclosure artifact: all 9 referenced detail files are missing from the bundle, so Claude cannot load the rules it is directed to read. Redundant cross-reference sections add padding.

Suggestions

Ship the 9 referenced section files (1-async-eliminating-waterfalls.md through 9-cache-components.md) under references/, or inline their rules into SKILL.md — the current bundle makes the mandatory Selective Reading Rule unresolvable.

Consolidate the Content Map, Quick Decision Tree, Impact Priority Guide, Section Details, and Learning Path, which restate the same 9 sections five times; keep one navigation table and one symptom-to-section map.

Add an explicit feedback loop for the validation script (run react_performance_checker.py → review findings → fix → re-run) so performance reviews have a clear validate-and-iterate checkpoint.

DimensionReasoningScore

Conciseness

Avoids explaining basics Claude already knows, but restates the same 9 sections across five redundant structures (Content Map, Quick Decision Tree, Impact Priority Guide, Section Details, Learning Path), which could be consolidated.

3 / 5

Actionability

Provides some executable snippets (`Promise.all()`, `dynamic(() => import('./Heavy'))`, the validation script command) but the bulk of guidance is "Read Section X" pointers to files that are not present in the bundle, leaving the actual ruleset inaccessible.

3 / 5

Workflow Clarity

Clear sequenced workflows ("For Performance Reviews: 1...2...3...4") plus a pre-shipping checklist and validation script serving as checkpoints, though an explicit run-checker → fix → re-run feedback loop is not stated.

4 / 5

Progressive Disclosure

The SKILL.md is architected as an overview with a well-signaled Content Map pointing one level deep to 9 section files, but none of those referenced .md files exist in the bundle (no references/ directory), so the mandatory "Selective Reading Rule" directs Claude to load files that are absent and the disclosure structure is non-functional.

2 / 5

Total

12

/

20

Passed

Description

88%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 strong, specific description with explicit what/when structure and concrete trigger phrases. Minor gaps in synonym coverage and slight overlap risk with generic code-review skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "building React components", "eliminating waterfalls", "reducing bundle size", "reviewing code for performance issues", "implementing server/client-side optimizations" — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what ("React and Next.js performance optimization from Vercel Engineering") and when ("Use when building React components, optimizing performance, eliminating waterfalls...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-term coverage ("React components", "bundle size", "waterfalls", "performance") but misses some common user synonyms like "slow page load", "TTI", or "LCP" that a user would naturally say.

4 / 5

Distinctiveness Conflict Risk

Clear React/Next.js performance niche with distinct triggers, but "reviewing code for performance issues" creates minor overlap risk with general code-review or performance skills.

4 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
vudovn/ag-kit
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.