CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

react-native-architecture

Production-ready patterns for React Native development with Expo, including navigation, state management, native modules, and offline-first architecture.

Quality

53%

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/react-native-architecture/SKILL.md

The canonical home for this skill is react-native-architecture in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

18%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.

The body is a well-organized shell with essentially no substance: generic boilerplate instructions, no concrete React Native guidance, no workflow, and a sole reference to a playbook file that is missing from the bundle. It reads as a template skeleton rather than a usable skill.

Suggestions

Ship `resources/implementation-playbook.md` (or fix the path) and either inline a concise quick-start pattern in SKILL.md or ensure the playbook genuinely contains the navigation/state/native-module/offline patterns promised.

Replace the generic instruction bullets with concrete, domain-specific guidance, e.g., named library choices (React Navigation, Zustand/Redux, expo-modules-core, WatermelonDB/SQLite sync patterns) and an explicit decision sequence.

Delete the tautological 'Do not use' bullets and the duplicated description line, and if a workflow exists (e.g., scaffolding → wiring navigation → state layer → offline sync → validation), lay it out as a numbered sequence with verification checkpoints.

DimensionReasoningScore

Conciseness

The body is short and does not explain concepts Claude already knows, but it contains clear trimmable filler: the description sentence repeated verbatim under the heading, the tautological "Do not use this skill when: The task is unrelated to react native architecture" / "You need a different domain or tool outside this scope", and generic instruction bullets ("Apply relevant best practices and validate outcomes") that convey no information. Not 4 because those wasted tokens are more than minor instances of over-explanation; not 2 because there is no actual over-explanation or padding by way of teaching known concepts.

3 / 5

Actionability

The Instructions are entirely abstract — "Clarify goals, constraints, and required inputs", "Apply relevant best practices and validate outcomes", "Provide actionable steps and verification" — with no concrete React Native guidance, commands, code, or examples anywhere in the body. The single concrete element, a pointer to `resources/implementation-playbook.md`, targets a file that does not exist in the bundle, so it delivers nothing. This matches the anchor 'entirely vague or abstract; only describes rather than instructs'; it does not reach 2 because there are no usable specific steps at all.

1 / 5

Workflow Clarity

No multi-step process is present: the four instruction bullets are unordered generic directives with no sequence and no validation checkpoints (nothing like "unpack → edit → validate → rebuild"). There is no rough sequence to evaluate, matching the 'steps missing or incoherent; no sequence; no validation' anchor. It cannot score 2 because even the loose 'open → change → save' style of rough sequence is absent.

1 / 5

Progressive Disclosure

The body has clean section structure and points one level deep to `resources/implementation-playbook.md` — but that file (and the `resources/` directory) does not exist in the bundle, so the skill's only substantive content pointer is broken and navigation leads nowhere. Per the judging guideline to score against the actual bundle structure, this is a minimal-structure / unusable-reference situation; not 1 because the body itself is well-sectioned and the reference is clearly signaled rather than deeply nested, and not 3 because a broken sole reference is worse than 'references present but not clearly signaled'.

2 / 5

Total

7

/

20

Passed

Description

66%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.

The description is reasonably strong: specific domain, good natural keywords, and a distinct niche. Its main defect is the complete absence of explicit 'when to use' trigger guidance, which caps completeness and limits its practical triggering quality.

Suggestions

Append an explicit trigger clause, e.g., "Use when starting or restructuring a React Native/Expo project, or when the user mentions Expo, React Native, mobile app architecture, or offline-first mobile design."

Convert the topic list into concrete actions (e.g., "Structures navigation with React Navigation, sets up state management, integrates native modules, and designs offline-first data layers") so the 'what' describes what the skill does, not just what it covers.

Add common synonyms and platform terms ("mobile app", "iOS", "Android") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain and four concrete coverage areas — "navigation, state management, native modules, and offline-first architecture" — which is several specific items with only minor gaps, though it describes topics rather than executable actions ("Production-ready patterns for..."). Not 5 because there are no action verbs describing what the skill actually does (e.g., 'structures', 'sets up', 'integrates'), unlike the comprehensive action-listing anchor; not 3 because the coverage goes well beyond 1-2 items and is specific to the domain.

4 / 5

Completeness

The 'what' is clear (production-ready patterns for React Native/Expo across four named areas), but there is no 'when' clause at all — no "Use when..." or equivalent trigger guidance anywhere in the description. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3; it cannot score 4 since the 'when' is not merely weak, it is absent.

3 / 5

Trigger Term Quality

Includes strong natural terms users would actually say: "React Native", "Expo", "navigation", "state management", "native modules", "offline-first". Not 5 because common variations like "mobile app", "iOS", "Android", and file/extension terms are missing; not 3 because keyword coverage is good and goes beyond a single generic phrase.

4 / 5

Distinctiveness Conflict Risk

"React Native development with Expo... native modules, and offline-first architecture" carves out a clear niche that is unlikely to trigger for unrelated skills. Not 5 because there is minor overlap risk with closely related skills (general React/React web skills, a hypothetical pure-Expo tooling or EAS build skill, or other mobile-development skills); not 3 because the combination of RN + Expo + offline-first is considerably more specific than the 'somewhat specific' anchor.

4 / 5

Total

15

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/react-native-architecture/SKILL.md

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.