expo-react-native-builder
Skill2 starsChanged 11 days agoMITView on GitHub
Build or audit production Expo/React Native applications. Use when Expo/React Native is already selected and implementation, native integration, updates, or release behavior is in scope. Not for choosing the mobile platform or an Expo SDK upgrade.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- cmdr-chara/codex-toolkitword for word, first seen Oct 31, 2026
Other versions1 project uses a version of this.
Word for word · 1
- cmdr-chara/codex-toolkit★ 2100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bin/AGENTS.mdAGENTS.md
- evaluations/AGENTS.mdAGENTS.md
- orchestration/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- skills/llms.txtllms.txt
- bug-finderSkill
- codebase-evolution-controllerSkill
- codebase-improvement-plannerSkill
- completion-proofSkill
- content-provenance-hygieneSkill
- cpp-engineeringSkill
- debugging-investigatorSkill
- delegate-with-mission-cardsSkill
- documentation-synchronizerSkill
- flutter-production-builderSkill
- go-engineeringSkill
- kotlin-engineeringSkill
- mobile-architecture-directorSkill
- multi-agent-work-coordinatorSkill
- optimize-codebase-performanceSkill
- product-design-directorSkill
- production-web-builderSkill
- python-engineeringSkill
- repository-intelligenceSkill
- review-and-refactor-codeSkill
- rust-engineeringSkill
- screenshot-to-interfaceSkill
- security-reviewSkill
- swift-engineeringSkill
- toolchain-preflightSkill
- typescript-quality-enforcerSkill
- verification-and-releaseSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 10 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use this skill for:
- Very specific: line 16
Do not trigger when the mobile platform is unresolved.
- Distinctive: line 28
Treat its output as signals to verify, not semantic truth.
- Distinctive: line 33
Prefer built-in Expo/RN capabilities or an existing repository package when sufficient.
- Distinctive: line 34
Do not silently add dependencies, regenerate native projects, change signing, publish updates, or submit stores.
- Distinctive: line 35
Keep secrets out of client bundles and logs.
- Distinctive: line 42
Choose dependencies conditionally: Do not start with a package list.
- Distinctive: line 43
Implement boundaries: Keep navigation, server state, durable local state, forms, device APIs, and native modules owned by the layer that …
- Very specific: line 44
Handle offline/update risk: Read references/offline-updates-and-security.md for durable queues, conflict/idempotency, storage, update …
- Distinctive: line 45
Verify the feature: Use focused unit/integration tests plus representative device/emulator checks for native, permission, background, …
- Very specific: line 46
Prepare release: Read references/release-checklist.md only for build/update/store work.
- Very specific: line 50
Use product-design-director or screenshot-to-interface for unresolved design intent.
- Distinctive: line 54
If package or platform evidence is stale, verify current primary sources before deciding.
- Distinctive: line 58
Stop when the requested Expo/RN behavior is integrated, focused checks and applicable device/build evidence are recorded, and remaining …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Expo React Native Builder
Build production Expo/React Native behavior from repository constraints rather than from a default package list.
Trigger boundary
Use this skill for:
- implementing or auditing an existing Expo/React Native app;
- Expo Router, development builds, native modules, offline/data behavior, EAS Build/Update, device integration, or store delivery.
Do not trigger when the mobile platform is unresolved; use mobile-architecture-director. A version/SDK migration whose central problem is compatibility belongs to codebase-evolution-controller.
Required inputs
Resolve repository state, Expo/RN/React/Node/package-manager constraints, app config and native/prebuild ownership, product flows, backend/device contracts, offline requirements, accessibility/localization, EAS profiles, release targets, and protected user work.
For a quick read-only inventory, run:
python skills/expo-react-native-builder/scripts/expo_project_inventory.py . --format markdownTreat its output as signals to verify, not semantic truth.
Safety baseline
- Preserve uncommitted work and repository conventions.
- Prefer built-in Expo/RN capabilities or an existing repository package when sufficient.
- Do not silently add dependencies, regenerate native projects, change signing, publish updates, or submit stores.
- Keep secrets out of client bundles and logs.
- Expo Go is not production release evidence when custom native behavior or production configuration matters.
Workflow
- Establish ownership. Map routing, app lifecycle, native directories/prebuild policy, development builds, backend/data boundaries, and release/update configuration.
- Model behavior. Define loading, empty, error, retry, offline/stale, auth, permission, background, interruption, and process-restart states before choosing libraries.
- Choose dependencies conditionally. Do not start with a package list. Check existing/built-in capability first; for new packages verify compatibility, maintenance, license, security/deprecation, runtime/build cost, and removal path. Use
references/package-selection.mdwhen package selection matters; verify current SDK compatibility with its checklist. - Implement boundaries. Keep navigation, server state, durable local state, forms, device APIs, and native modules owned by the layer that can enforce their lifecycle and trust requirements.
- Handle offline/update risk. Read
references/offline-updates-and-security.mdfor durable queues, conflict/idempotency, storage, update compatibility, and sensitive data. - Verify the feature. Use focused unit/integration tests plus representative device/emulator checks for native, permission, background, deep-link, accessibility, and performance behavior that cannot be proven in JS alone.
- Prepare release. Read
references/release-checklist.mdonly for build/update/store work. Native dependency, config, permission, or entitlement changes require a compatible binary rather than a JS-only update.
Handoffs and interaction boundaries
Use product-design-director or screenshot-to-interface for unresolved design intent. Use security-review when security is the primary decision. Hand migrations to codebase-evolution-controller, causal failures to debugging-investigator, documentation drift to documentation-synchronizer, and final ship judgment to verification-and-release.
Failure handling
If package or platform evidence is stale, verify current primary sources before deciding. If a native capability cannot be reproduced in the available environment, report the exact gap instead of treating a JS test as equivalent evidence.
Stop conditions
Stop when the requested Expo/RN behavior is integrated, focused checks and applicable device/build evidence are recorded, and remaining release or platform gaps have an explicit owner.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

