maj-labs/app-store-review
Full-lifecycle Apple App Store review for iOS and iPadOS apps. Use for pre-submission audits, rejection diagnosis and Resolution Center replies, Guideline 4.3 spam or similarity recovery, human-craft and low-effort audits, App Review Notes, privacy manifests, Info.plist permission strings, subscriptions, Sign in with Apple, account deletion, UGC, third-party AI consent, TestFlight or App Store readiness, and vague requests such as "review my app" or "will Apple approve this" when an Xcode, Expo, React Native, or Flutter project is present. Produces evidence-tagged Markdown, JSON, and a self-contained visual HTML report, runs a read-only deterministic scan first, and only offers grouped fixes after the report.
97
97%
Does it follow best practices?
Impact
98%
2.08xAverage score across 4 eval scenarios
Low
Low-risk findings worth noting
Evaluation results
100%
100%Guideline 2.3.7 rejection recovery
Anonymized Guideline 2.3.7 rejection recovery for a proven subtitle price claim requiring localized metadata correction and a factual Resolution Center reply
Verbatim opening and one classification
0%
100%
Proven FIX under 2.3.7
0%
100%
Every live subtitle localization
0%
100%
Fallback metadata and assets
0%
100%
Description remains contextual
0%
100%
Conditional same-build guidance
0%
100%
Factual verified reply
0%
100%
No appeal or invented work
0%
100%
100%
Help Petra Respond to the Nimbus Weather Rejection
4.3(b) rejection recovery for weather app
4.3(b) vs 4.3(a) distinction
100%
100%
Response classification
100%
100%
Exact rejection message preserved
100%
100%
Resolution Center reply present
100%
100%
Build number placeholder or reference
100%
100%
Attachments listed
100%
100%
No code obfuscation recommendation
100%
100%
No unsupported provenance claim
100%
100%
Fast review timeline not mischaracterized
100%
100%
Evidence confidence labels
100%
100%
No invented evidence
100%
100%
No AI-detection claim
100%
100%
100%
55%Is ShareFlow Ready to Submit?
Expo app full pre-launch review with extension targets
Mode A declared first
0%
100%
Mode C declared
0%
100%
Expo config cited as evidence
87%
100%
Fix targets app.json or plugin
87%
100%
Share extension reviewed separately
87%
100%
MANUAL CHECK for absent ios/ directory
25%
100%
Missing camera purpose string identified
0%
100%
Policy verification date recorded
57%
100%
ITMS-91053 absent
100%
100%
Five Mode C interventions
0%
100%
All five Mode C dimensions graded
0%
100%
No files modified
100%
100%
Fix plan section present
44%
100%
92%
47%Should FocusNest Be Submitted?
Guideline 4.3(b) human-craft audit for a template-derived focus timer
Exact Mode C contract
0%
60%
All dimensions use allowed grades
0%
100%
Grades match supplied evidence
30%
100%
Current 4.3(b) position
87%
100%
4.3(a) kept distinct
100%
100%
Template provenance handled accurately
85%
100%
Product change leads
90%
100%
Exactly five interventions
50%
100%
Interventions are verifiable
42%
100%
Unverified surfaces preserved
50%
100%
No evasion or fake probability
100%
100%
No supplied files modified
100%
100%
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6