mobile-architecture-director
Skill2 starsChanged 12 days agoMITView on GitHub
Choose a mobile architecture among Flutter, Expo/React Native, native, and other viable options. Use when platform choice or mobile architecture direction is unresolved. Not for building an app whose stack is already chosen.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- cmdr-chara/chara-toolkitword for word, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 1
- cmdr-chara/chara-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
- expo-react-native-builderSkill
- flutter-production-builderSkill
- go-engineeringSkill
- kotlin-engineeringSkill
- 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
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use this skill when platform choice, native/shared boundaries, or mobile architecture direction is unresolved.
- Distinctive: line 14
Do not trigger to implement an already selected Flutter or Expo/React Native application.
- Very specific: line 23
Treat current framework/store/platform claims as volatile and verify them from primary sources.
- Distinctive: line 24
Do not choose by popularity or one benchmark.
- Very specific: line 31
Compare viable options: Use references/platform-decision-matrix.md and verify its current-facts checklist.
- Very specific: line 36
Produce the decision record: Use references/mobile-nonfunctional-requirements.md for nonfunctional coverage and state when to reconsider …
- Distinctive: line 44
If evidence cannot distinguish viable options, do not fabricate a winner.
- Distinctive: line 48
Stop when the viable options, disqualifiers, weights, sensitivity, proof spikes, chosen boundaries, and reconsideration triggers are …
≈ “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
Mobile Architecture Director
Choose a mobile approach from product and operating constraints rather than framework preference.
Trigger boundary
Use this skill when platform choice, native/shared boundaries, or mobile architecture direction is unresolved.
Do not trigger to implement an already selected Flutter or Expo/React Native application.
Required inputs
Resolve product journeys, target platforms/devices, team skills, native/API requirements, offline/data model, security/privacy, accessibility, performance, distribution/update constraints, long-term ownership, working-tree state, and decision reversibility.
Safety baseline
- Preserve user work and existing repository evidence.
- Treat current framework/store/platform claims as volatile and verify them from primary sources.
- Do not choose by popularity or one benchmark.
- A must-have capability can disqualify an option regardless of weighted score.
Workflow
- Define must-have gates. Record platform/API/store/security/offline/accessibility constraints and explicit disqualifiers.
- Model the product architecture. Identify shared domain/data logic, native integrations, UI/platform-specific behavior, background work, and distribution boundaries.
- Compare viable options. Use
references/platform-decision-matrix.mdand verify its current-facts checklist; include Flutter, Expo/RN, separate native, and other relevant approaches rather than forcing all options. - Weight criteria. Score only criteria that matter to this product and show the weights so the result is inspectable.
- Prototype uncertainty. Define proof spikes for critical unknowns such as native SDKs, background work, performance, accessibility, build/signing, or offline durability.
- Test sensitivity. Re-run the decision when plausible weight changes or proof-spike results could flip it.
- Define boundaries. State what is shared versus native/platform-specific and who owns escape hatches.
- Produce the decision record. Use
references/mobile-nonfunctional-requirements.mdfor nonfunctional coverage and state when to reconsider the choice.
Handoffs and interaction boundaries
Hand selected Flutter work to flutter-production-builder, Expo/RN to expo-react-native-builder, native work to the appropriate native implementation workflow, security-first questions to security-review, and final release judgment to verification-and-release.
Failure handling
If evidence cannot distinguish viable options, do not fabricate a winner; define the smallest prototype or missing fact that would. If a must-have fails, remove the option before weighted comparison.
Stop conditions
Stop when the viable options, disqualifiers, weights, sensitivity, proof spikes, chosen boundaries, and reconsideration triggers are explicit enough to commit to a platform direction.
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.

