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

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable reference with executable code across all major networking concerns and good progressive disclosure via a real, well-signaled reference file. It loses points on conciseness from redundant restatement and on workflow clarity from missing explicit validation checkpoints in the auth/token-refresh flows.

Suggestions

Trim the "Example Invocations" and "Common Mistakes" sections, which restate the decision tree and inline code, to recover token budget.

Add an explicit validation checkpoint to the token-refresh flow (e.g., confirm the new token is valid before retrying the original request) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — it leads with executable code and avoids explaining concepts Claude already knows — but the "You MUST use this skill for ANY networking work" mandate and the "Example Invocations"/"Common Mistakes" sections restate guidance already covered by the decision tree and code above. Not score 3 because some sections could be tightened; not score 1 because there is no conceptual padding.	2 / 3
Actionability	Provides complete, copy-paste-ready code for fetch, React Query setup/mutations, error handling with retry, SecureStore auth, NetInfo offline, env config, and AbortController cancellation. Not score 2 because examples are executable rather than pseudocode with all key details present.	3 / 3
Workflow Clarity	The decision tree sequences routing decisions clearly and the error-handling/retry section includes a feedback loop, but there are no explicit validation checkpoints for fragile flows like token refresh (e.g., verify the refreshed token before use). Not score 3 because checkpoints are implicit; not score 1 because steps are clearly listed and sequenced.	2 / 3
Progressive Disclosure	A clearly signaled one-level-deep reference — references/expo-router-loaders.md (a real file) — is listed in the References section and decision tree, with the route-loader detail appropriately split out of SKILL.md. Not score 2 because navigation is explicit and content is properly split rather than inlined.	3 / 3
	Total	10 / 12 Passed

Description

92%Weight 40%Scale 1-3

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 description with explicit trigger guidance and a concrete capability list, weakened only by an overly broad "ANY networking" scope that raises conflict risk with general data-fetching skills.

Suggestions

Narrow the trigger scope so it fires for Expo/React Native networking specifically rather than "ANY network request", reducing overlap with generic fetch skills.

Lead with the differentiating capability (Expo Router loaders, expo/fetch, SecureStore token handling) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders" — matching the anchor for several specific actions. Not score 2 because it goes beyond naming a domain plus a few actions into a comprehensive list.	3 / 3
Completeness	Explicitly answers both "what" ("Covers fetch API, React Query, SWR...") and "when" ("Use when implementing or debugging ANY network request..."). Not score 2 because the "Use when..." trigger is explicit rather than implied.	3 / 3
Trigger Term Quality	Natural user phrasing like "network request, API call, or data fetching" gives good coverage of terms a user would actually say. Not score 2 because it captures common variations rather than relying on jargon alone, though "useLoaderData" is somewhat technical.	3 / 3
Distinctiveness Conflict Risk	Has a clear Expo-specific niche (Expo Router loaders, expo/fetch) but the "ANY network request, API call, or data fetching" framing is broad and could overlap with general networking or web-fetch skills. Not score 3 because the sweeping scope weakens distinctiveness; not score 1 because the Expo/RN specifics still carve out a niche.	2 / 3
	Total	11 / 12 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: 11c74d6

Reviewed: 17 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.