data-fetching

Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, axios, React Query, SWR, error handling, caching strategies, offline support.

Quality

74%

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 ./src/ii_agent/agents/skills/builtin/expo-data-fetching/SKILL.md

Quality

Content

65%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 examples and a useful decision tree, but the single-file length, mild redundancy, and missing validation/feedback loops in risky workflows (auth, offline, retries) hold it back from the top tier.

Suggestions

Add explicit validation/recovery checkpoints to risky workflows — e.g., after token refresh, validate the new token before use; after offline queue replay, confirm successful sync before clearing.

Trim redundancy in the Environment Variables section by stating the EXPO_PUBLIC_ build-time-inlining rule once instead of restating it across 'Important notes' and inline comments.

Split the bulkier topics (full React Query guide, environment-variable reference) into reference files and point to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-forward sections, but the document is long (~490 lines) with some redundancy — e.g., environment-variable guidance repeats the EXPO_PUBLIC prefix point across subsections, and the 'Important notes' restate build-time inlining already implied.	3 / 5
Actionability	Fully executable, copy-paste-ready code across fetch, React Query setup/queries/mutations, error handling with retries, SecureStore auth, NetInfo offline, AbortController, and an API client — covering the common cases concretely.	5 / 5
Workflow Clarity	The decision tree sequences choices clearly, but workflows involving risky operations (token refresh, offline persistence, auth fetch) lack explicit validation checkpoints or error-recovery feedback loops, which caps this at 3 per the destructive/batch validation guidance.	3 / 5
Progressive Disclosure	Well-sectioned single file with a navigable decision tree, but it is a monolithic wall with no external references and inlines ~490 lines that could be split (e.g., full React Query guide, env-var reference) into separate files; some structure present but not split.	3 / 5
	Total	14 / 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 description with explicit 'Use when' trigger guidance and concrete library coverage that clearly answers both what and when. Minor gaps in synonyms and a slight over-claim on axios (the body says to avoid it) keep it just below perfect.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'fetch API, axios, React Query, SWR, error handling, caching strategies, offline support' — covering the domain well, though 'error handling' and 'caching strategies' are slightly generic compared to the concrete library names.	4 / 5
Completeness	Explicitly answers both 'when' ('Use when implementing or debugging ANY network request, API call, or data fetching') and 'what' ('Covers fetch API, axios, React Query, SWR, error handling, caching strategies, offline support') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ('network request', 'API call', 'data fetching') plus library names users say, but missing common synonyms like 'HTTP request', 'REST', or 'endpoints'.	4 / 5
Distinctiveness Conflict Risk	Largely distinct niche (Expo/RN networking with named libraries) with minor overlap risk against generic fetch or auth skills; the 'ANY network request' breadth slightly raises conflict risk.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Intelligent-Internet/ii-agent
Path: src/ii_agent/agents/skills/builtin/expo-data-fetching/SKILL.md
Commit: 28563d6

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.