CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

64

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/native-data-fetching/SKILL.md

The canonical home for this skill is native-data-fetching in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

64%Scale 1-5

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

This skill provides excellent, actionable code examples covering a wide range of Expo networking scenarios, making it highly useful as a reference. However, it suffers from being overly long and monolithic—much of the content could be split into reference files with the main skill serving as a concise overview and decision tree. The lack of explicit validation/debugging workflows is a notable gap given the skill's stated coverage of network debugging.

Suggestions

Extract detailed code examples (React Query setup, auth/token management, offline support, env vars) into separate reference files and keep only concise summaries with links in the main SKILL.md

Remove explanations of concepts Claude already knows, such as what environment variables are, how fetch works at a basic level, and that React Query automatically cancels requests

Add explicit debugging/validation workflows for network failures (e.g., 'Check NetInfo status → inspect response headers → verify token validity → check CORS/SSL') with feedback loops

Trim the environment variables section significantly—the 'important notes' bullet list and TypeScript support subsection add bulk that could be in a reference file

DimensionReasoningScore

Conciseness

The skill is quite long (~300 lines) and includes several sections that explain concepts Claude already knows (e.g., basic fetch usage, how POST requests work, what environment variables are). The env vars section in particular has excessive explanation ('These are inlined at build time and available in your JavaScript code'). However, the code examples themselves are reasonably tight and the decision tree is efficient.

3 / 5

Actionability

Every section provides fully executable, copy-paste ready TypeScript/TSX code examples covering GET, POST, React Query setup, mutations, error handling, auth token management, offline support, env vars, and request cancellation. The examples are complete and cover common cases thoroughly.

5 / 5

Workflow Clarity

The skill is organized as a reference catalog of patterns rather than a workflow. There are no explicit validation checkpoints or feedback loops for debugging network issues. The decision tree helps with routing to the right section, but for a skill that covers 'debugging network failures' and destructive operations like token management, there are no verification steps (e.g., 'verify the token refresh succeeded before retrying the original request').

3 / 5

Progressive Disclosure

The skill references one external file (expo-router-loaders.md) which is appropriate, but the bulk of the content (~300 lines of code examples) is inlined in the main SKILL.md. Topics like React Query setup, authentication/token refresh, and offline support could each be separate reference files, with the main skill providing a concise overview and decision tree. The structure is flat rather than layered.

3 / 5

Total

14

/

20

Passed

Description

91%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.

This is a strong skill description that clearly communicates both what it does and when to use it. The 'Use when' clause at the beginning with explicit trigger scenarios is effective, and the enumeration of specific technologies provides good coverage. The main weakness is that actions are described as coverage areas rather than concrete verbs, slightly reducing specificity.

DimensionReasoningScore

Specificity

Lists several specific technologies and concepts (fetch API, React Query, SWR, error handling, caching, offline support, Expo Router data loaders, useLoaderData), but the actions are described more as coverage areas ('Covers') rather than concrete actions like 'implements', 'configures', or 'debugs'.

4 / 5

Completeness

Explicitly answers both 'what' (implementing/debugging network requests, covering specific technologies) and 'when' ('Use when implementing or debugging ANY network request, API call, or data fetching') with concrete trigger phrases right at the start.

5 / 5

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'network request', 'API call', 'data fetching', 'fetch API', 'React Query', 'SWR', 'error handling', 'caching', 'offline support', 'useLoaderData'. These are terms developers naturally use when seeking help with networking.

5 / 5

Distinctiveness Conflict Risk

Fairly distinct with its focus on network requests and data fetching in a React Native/Expo context. Minor overlap risk with general React skills or API-related skills, but the specific mention of Expo Router, SWR, and React Query helps narrow the niche.

4 / 5

Total

18

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (509 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.