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

78%

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%

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

A highly actionable, code-complete networking reference that earns its strength on executable examples, but it is a long monolithic file with redundant summary sections and lacks the validation checkpoints and split-file references the top anchors reward.

Suggestions

Move the detailed subsections (React Query, auth/token refresh, offline, env vars) into reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links, improving progressive disclosure.

Remove or condense the 'Common Mistakes' and 'Example Invocations' sections, which restate the decision tree and earlier code, to recover token budget.

Add explicit validation/feedback steps to the riskier multi-step flows (e.g. verify a refreshed token before retrying, confirm NetInfo state before queueing) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and mostly avoids explaining concepts Claude already knows, but at ~480 lines the 'Common Mistakes' and 'Example Invocations' sections largely restate patterns already shown in the numbered sections and decision tree, so it could be tightened.	2 / 3
Actionability	Every section ships complete, copy-paste-ready code: fetch GET/POST, QueryClient setup, typed ApiError class, retry-with-backoff, SecureStore auth wrappers, NetInfo hooks, EXPO_PUBLIC_ config, and AbortController cancellation.	3 / 3
Workflow Clarity	The decision tree gives a clear routing sequence, but there are no explicit validation checkpoints, feedback loops, or checklists for the multi-step flows (e.g. token refresh, retry/backoff), which the anchor-3 level requires.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the file is a single ~480-line monolith with no references/ or bundle files; detailed subtopics (React Query guide, auth patterns, env config) that could live one level deep are all inlined.	2 / 3
	Total	9 / 12 Passed

Description

92%

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, trigger-rich description with explicit 'what' and 'when' guidance, but it over-broadens by omitting the Expo/React Native niche the skill actually targets, raising conflict risk with generic web networking skills.

Suggestions

Scope the description to Expo/React Native (e.g. 'Use when implementing network requests in Expo or React Native apps') to reduce overlap with generic web networking skills.

Drop the capitalized 'ANY' emphasis and the axios mention if the skill prefers expo/fetch, so the description matches the body's stated preference and doesn't over-claim.

Add an Expo-specific trigger term (e.g. 'expo-secure-store', 'NetInfo', 'EXPO_PUBLIC_') to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities and domains: 'implementing or debugging ANY network request, API call, or data fetching' plus 'fetch API, axios, React Query, SWR, error handling, caching strategies, offline support' — a concrete, multi-action inventory rather than vague language.	3 / 3
Completeness	Explicitly answers both halves: 'Use when implementing or debugging...' gives the trigger, and 'Covers fetch API, axios, React Query, SWR, error handling, caching strategies, offline support' states what it does.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered: 'network request', 'API call', 'data fetching' alongside library names (fetch, axios, React Query, SWR) that users actually say when asking for networking help.	3 / 3
Distinctiveness Conflict Risk	The description is generic web/React networking (fetch, axios, React Query, SWR) with no Expo/React Native scoping despite the skill body being Expo-specific, so it would readily trigger for ordinary web projects and overlap with general networking skills.	2 / 3
	Total	11 / 12 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: 0e57985

Reviewed: about 16 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.