CtrlK
BlogDocsLog inGet started
Tessl Logo

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, Apple design and Human Interface Guidelines audits of native interaction, motion, gestures, materials, haptics, accessibility, and iPad adaptation, 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.

96

2.10x
Quality

94%

Does it follow best practices?

Impact

99%

2.10x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is maj-labs/app-store-review

SKILL.md
Quality
Evals
Security

Quality

Content

85%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-structured, executable multi-mode workflow with strong progressive disclosure and explicit validation gates. Its main weakness is repetition of the mode-start contract lines across the 'Output gates' and mode sections, which slightly inflates token use.

Suggestions

Consolidate the exact required mode-start contract lines so each appears once (e.g., define them in 'Output gates' and have the Mode A/B/C sections reference rather than re-state them), reducing duplication.

Trim overlap between the 11 'Non-negotiable rules' and the later workflow sections — several rules (read-only first pass, approval before editing, evidence labeling) are restated in the mode workflows.

Consider tightening the 'Choose the mode' routing prose, which repeats the load-list and run-order guidance already implied by the mode table.

DimensionReasoningScore

Conciseness

Mostly efficient with tables and code blocks, but it repeats content: the required mode-start contract lines appear both in 'Output gates' and again in the Mode A/B/C sections, and the 11 'Non-negotiable rules' overlap somewhat with later workflow guidance. It is tighter than verbose padding but still could be trimmed.

3 / 5

Actionability

Fully executable guidance throughout — concrete scanner invocations with real flags ('--compare-root', '--archive', '--metadata subtitle:en-US=...', '--metadata-root', '--format all --output-dir'), the renderer command, and exact required output lines/contracts that are copy-paste ready and cover the common cases.

5 / 5

Workflow Clarity

Clear sequenced workflow (Discover → Establish scope → Mode A/B/C) with explicit validation checkpoints, a read-only-first pass, an approval-before-editing gate for destructive edits, and literal 'Output gates' the deliverable must satisfy, plus a feedback step to remove scanner false positives.

5 / 5

Progressive Disclosure

Verified bundle structure: 9 reference files and 2 scripts all exist, are referenced one level deep with no nested 2+ level chains, and are surfaced through a clear 'Packaged resources' index plus per-mode 'Read and follow ... completely' pointers, making navigation easy.

5 / 5

Total

18

/

20

Passed

Description

100%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 comprehensive, concrete, and in correct third-person voice, explicitly covering both what the skill does and when to invoke it with natural trigger phrasings. It establishes a distinct niche with minimal overlap risk.

DimensionReasoningScore

Specificity

Lists many concrete actions and deliverables — 'pre-submission audits, rejection diagnosis and Resolution Center replies, Guideline 4.3 spam or similarity recovery, human-craft and low-effort audits, Apple design and Human Interface Guidelines audits' plus 'evidence-tagged Markdown, JSON, and a self-contained visual HTML report, runs a read-only deterministic scan first'. Comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (full-lifecycle review producing Markdown/JSON/HTML with a read-only scan and grouped fixes) and 'when' ('Use for pre-submission audits, rejection diagnosis...') with concrete trigger phrases, so neither what nor when is missing or merely implied.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrasings users would actually say — 'review my app', 'will Apple approve this', 'Guideline 4.3', 'Resolution Center', 'Sign in with Apple', 'TestFlight', plus framework names Xcode, Expo, React Native, and Flutter.

5 / 5

Distinctiveness Conflict Risk

A clear, narrow niche (Apple App Store review for iOS/iPadOS) with distinct triggers and framework scoping; the body even carves out a boundary ('Do not route a standalone SwiftUI implementation... to this skill'), keeping conflict risk minimal.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ElxMaj/app-store-review-skill
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.