native-data-fetching

Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (`useLoaderData`).

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

68%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.

Highly actionable with comprehensive executable code and good progressive-disclosure structure that offloads the route-loader topic to a real reference file. It loses points on conciseness (redundant prose) and workflow clarity (no explicit validation checkpoints, as expected for a catalog-style skill).

Suggestions

Trim redundant explanatory prose such as the 'Important notes' build-time restatement and the 'React Query automatically cancels requests' placeholder section to improve conciseness.

Add a short, explicit verification step where workflows warrant it (e.g., confirming a token-refresh flow re-fetches, or validating that offline-queued mutations flush on reconnect) to strengthen workflow clarity.

Consider splitting the large environment-variables section into its own reference file to keep SKILL.md a lean overview, consistent with how the loaders topic is already externalized.

Dimension	Reasoning	Score
Conciseness	The ~500-line body is dominated by useful executable code, but several prose passages restate what Claude already knows ('inlined at build time and available in your JavaScript code', 'React Query automatically cancels requests', the 'Important notes' restating build-time inline), so it is mostly efficient with padding that could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready, executable code across all seven topics (fetch, React Query setup/mutations, error handling, retry, auth, offline, env vars, cancellation), fully covering the common cases.	5 / 5
Workflow Clarity	A decision tree supplies sequencing and Common Mistakes gives wrong/right patterns, but as a reference catalog there is no explicit sequenced workflow with validation checkpoints or feedback loops, so sequence is present but checkpoints are implicit.	3 / 5
Progressive Disclosure	The real one-level-deep references/expo-router-loaders.md is listed in a References section and routed to via the decision tree, with the bulk loader detail correctly split out; topical sections are well-headed, though only one reference file exists and several topics remain fully inlined.	4 / 5
	Total	15 / 20 Passed

Description

96%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, concrete description that clearly states both capabilities and trigger conditions with comprehensive natural terms. Its only weakness is the broad 'ANY network request' scope, which slightly raises overlap risk with non-Expo networking skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('implementing or debugging', 'network request, API call, or data fetching') and a comprehensive domain list (fetch API, React Query, SWR, error handling, caching, offline, Expo Router loaders), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' ('Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders') and 'when' ('Use when implementing or debugging ANY network request, API call, or data fetching') with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural user phrases ('network request', 'API call', 'data fetching', 'debugging') with good synonym coverage; the 'useLoaderData' jargon is minor relative to the broad natural-term set.	5 / 5
Distinctiveness Conflict Risk	The Expo-specific framing (Expo Router loaders, useLoaderData) gives a clear niche, but 'ANY network request, API call, or data fetching' is broad enough to risk overlap with a generic networking skill, so it sits just below the minimal-conflict anchor.	4 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (508 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/expo/skills/native-data-fetching/SKILL.md
Commit: 1dc1958

Reviewed: 5 days 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.