CtrlK
BlogDocsLog inGet started
Tessl Logo

react-native-architecture

Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns. Use when developing mobile apps, implementing native integrations, or architecting React Native projects.

57

Quality

66%

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 ./tests/ext_conformance/artifacts/agents-wshobson/frontend-mobile-development/skills/react-native-architecture/SKILL.md

The canonical home for this skill is react-native-architecture in wshobson/agents

SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

A code-rich, actionable reference with genuine commands and working patterns, but it functions as a monolithic catalog rather than a skill overview. The main quality levers are splitting patterns into one-level-deep reference files, trimming repetitive code blocks, and adding validation checkpoints around risky operations like store submission.

Suggestions

Split the six patterns into one-level-deep reference files (e.g., references/navigation.md, references/auth.md, references/offline-sync.md, references/native-modules.md, references/eas.md) and keep SKILL.md as a concise overview with clearly signaled links, per the progressive_disclosure rationale.

Trim repetitive code: collapse the five Platform.OS-guarded haptics wrappers into a single parameterized helper, reduce the four near-identical Tabs.Screen blocks to one plus a comment, and cut the full Button StyleSheet to the styles needed to convey the pattern.

Add a validation checkpoint workflow for releases — e.g., test the development/preview build on a real device, verify the production build, and only then run 'eas submit' — so the EAS section has explicit feedback loops for outward-facing operations.

Tighten the trigger phrasing in the description by scoping 'developing mobile apps' to React Native/Expo (e.g., 'Use when building React Native or Expo apps...') to reduce overlap risk with other mobile-development skills.

DimensionReasoningScore

Conciseness

The body is mostly executable code rather than prose explanation (efficient), but contains substantial trimmable repetition: the haptics service repeats the same 'Platform.OS !== "web"' guard across five near-identical functions, the tab layout has four nearly identical Tabs.Screen blocks, and a full 45-line StyleSheet is inlined. This matches 'mostly efficient but could be tightened' rather than the minor-trim anchor 4.

3 / 5

Actionability

Provides real commands ('npx create-expo-app@latest', 'eas build --platform ios --profile development') and substantial concrete code for every pattern. It falls short of fully copy-paste ready because several blocks reference undefined identifiers (FastImage, api, SplashScreen, onRefresh/isRefreshing in ProductList), leaving minor gaps.

4 / 5

Workflow Clarity

A 'When to Use' list and Quick Start give a rough sequence, but the body is a parallel pattern catalog with no ordered end-to-end process and no validation checkpoints — notably nothing about verifying a build before 'eas submit' to stores. This matches 'sequence present but checkpoints missing' rather than anchor 4, which requires most checkpoints present.

3 / 5

Progressive Disclosure

Sections are well-headed (above the unstructured anchor 2), but the ~670-line body inlines six complete patterns — the auth flow, offline sync setup, native module services, and EAS build config each clearly belong in separate reference files. With no bundle files present and no references in the body, all detail is forced into SKILL.md, matching 'content that should be separate is inline'.

3 / 5

Total

13

/

20

Passed

Description

75%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 that clearly states capabilities and includes an explicit 'Use when...' clause with concrete trigger phrases. Its main weakness is that the primary trigger ('developing mobile apps') is broader than the skill's actual React Native/Expo scope, slightly diluting both completeness and distinctiveness.

DimensionReasoningScore

Specificity

Names the domain and several concrete capability areas — 'navigation, native modules, offline sync, and cross-platform patterns' — with only minor gaps. It stays at 4 rather than 5 because a single verb ('Build') heads a list of feature areas rather than enumerating multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both what ('Build production React Native apps with Expo, navigation, native modules, offline sync...') and when ('Use when developing mobile apps, implementing native integrations, or architecting React Native projects'). The 'when' could be more tightly scoped — 'developing mobile apps' is not specific to React Native — so it does not reach the fully concrete anchor 5.

4 / 5

Trigger Term Quality

Includes natural terms users would say — 'React Native', 'Expo', 'mobile apps', 'native integrations', 'architecting React Native projects'. A few natural variations are missing (e.g., 'iOS app', 'Android app', 'cross-platform app'), keeping it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

'React Native' and 'Expo' carve out a clear niche with distinct triggers, giving minimal conflict risk with unrelated skills. The broad 'developing mobile apps' trigger could overlap with other mobile-development skills (e.g., Flutter or native iOS/Android), which prevents a 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (674 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
Dicklesworthstone/pi_agent_rust
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.