vercel-composition-patterns

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/vercel-composition-patterns/SKILL.md

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.

The body is well-structured and concise as an index of composition rules, but it lacks concrete executable guidance and its file references point to paths that are not part of the bundle. Actionability and progressive disclosure are the main weaknesses.

Suggestions

Inline at least one concrete code example per rule (or a representative before/after snippet) so the skill is actionable without depending on rule files that are not bundled.

Add the referenced bundle files (rules/*.md and AGENTS.md) or remove/qualify the references so progressive disclosure points to real, loadable material.

Replace the loose 'How to Use' pointer with an explicit short workflow (e.g., identify the rule category → read the matching rule file → apply the correct example) so the lookup path is unambiguous.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's knowledge of React, using terse rule one-liners and a priority table rather than restating concepts; only minor padding (the extended-reference blockquote and the intro re-summarizing the description).	4 / 5
Actionability	Provides rule names and one-line glosses but no executable code, commands, or concrete steps; guidance defers to rule files ('Read individual rule files for detailed explanations and code examples') that are not present in the bundle.	2 / 5
Workflow Clarity	As a reference catalog it has a loose lookup sequence ('How to Use' → rule files), but there is no real multi-step workflow and no validation checkpoints, so the sequence is present yet shallow.	3 / 5
Progressive Disclosure	The overview points one level deep to AGENTS.md and rules/*.md with clear signaling, but those referenced paths do not exist in the bundle, leaving dangling references that undermine navigation.	3 / 5
	Total	12 / 20 Passed

Description

83%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, well-targeted description that clearly states both the skill's purpose and explicit usage triggers with concrete, natural terminology. Minor room for more exhaustive synonym coverage and tighter specificity.

Dimension	Reasoning	Score
Specificity	Names the React composition domain and several concrete concepts (compound components, render props, context providers, boolean prop proliferation) plus refactoring/building/designing actions, with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('React composition patterns that scale') and when ('Use when refactoring...', 'Triggers on tasks involving...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural-term coverage ('refactoring components', 'compound components', 'render props', 'context providers', 'component architecture') that users would plausibly say, missing only a few synonyms.	4 / 5
Distinctiveness Conflict Risk	Clear niche in React component architecture with distinct triggers, with only minor overlap risk against general React or component-library skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/vercel-composition-patterns/SKILL.md
Commit: 1bab711

Reviewed: about 20 hours ago

Table of Contents

Discovery Implementation Validation

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.