Mobile project audit
Skill ahtishamshahzad/agent_dev_flow/.ai/skills/mobile/mobile-project-audit
Use when a mobile app already exists, before changing it — inventory the runtime (Expo vs CLI), navigation, state, native modules, build config, and iOS/Android readiness. Read-only; grounds mobile planning in reality. Delegates deep security/performance to their skills.From its SKILL.md
npx -y skills add ahtishamshahzad/agent_dev_flow --skill mobile-project-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.8 KB, 752 tokens by cl100k_base, as published. Nobody here has run it
Mobile Project Audit
Purpose
Understand an existing mobile app before changing it: its runtime, structure, navigation, state approach, native modules, build/release setup, and platform readiness — so mobile planning is grounded, not assumed. The mobile counterpart to ../../existing-project-audit.
When to Use
- Any request against an existing mobile codebase.
- Before recommending a runtime change or mobile migration.
- Not for greenfield mobile work (record "greenfield").
Inputs
- Read access to the mobile project.
- The classified request (to scope the audit).
Discovery Questions
- Expo or React Native CLI? Which SDK/RN version?
- What navigation, state, and data-fetching approaches are in use?
- Which native modules/SDKs and permissions are present?
- What is the current build/release setup (EAS? Fastlane? manual)?
Responsibilities
- Detect runtime (Expo managed / dev builds / bare CLI) and versions.
- Map navigation, state ownership, and data-fetching patterns.
- Inventory native modules, permissions, and config plugins.
- Assess build/release setup and iOS/Android readiness signals.
- Flag security/performance signals; hand depth to
../../security-review/mobile-performance. - Record findings; do not edit code.
Required Workflow
- Scope the audit to the request.
- Detect runtime + versions from config (
app.json/app.config,Podfile, Gradle). - Map navigation/state/data patterns from representative screens.
- Inventory native modules, permissions, plugins.
- Survey build/release and readiness.
- Record findings + risks.
Decision Rules
- Report what the project proves vs what you infer.
- Scope to the affected area for small requests; don't audit everything.
- Deep security/performance analysis is delegated, not done here.
Rules
- Read-only; no edits during the audit.
- Do not print secret values (redact) (
../../security-review). - Ground later mobile stages in findings, not guesses.
Anti-Patterns
- Proposing changes before understanding the runtime/patterns.
- Auditing the whole app for a one-screen change.
- Treating inferences as confirmed.
Validation Checklist
- Runtime + versions detected.
- Navigation/state/data patterns mapped.
- Native modules/permissions/plugins inventoried.
- Build/release + readiness surveyed.
- Security/performance signals flagged.
- No code edited.
Definition of Done
A scoped, read-only audit of the mobile app covering runtime, patterns, native modules, build/release, and readiness — confirmed vs inferred separated — ready to inform mobile planning.
Related Skills
../../existing-project-audit, mobile-stack-selection, mobile-navigation, mobile-state-management, mobile-native-modules, mobile-builds, ios-readiness, android-readiness, ../../security-review, mobile-performance.
Related Knowledge
../../../knowledge/ (existing mobile architecture).
Related References
../../../references/mobile/ topic folders when populated.
Context Loading Guidance
- Requires: mobile project read access, the classified request.
- Does not require: the whole app source, unrelated references, every mobile skill.
- May load:
mobile-native-modules,mobile-builds, readiness skills for depth. - Stop when: the scoped audit is recorded.
Token Efficiency Guidance
Read config and representative screens first; sample, don't read everything. Summarize into findings; don't paste large files.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.