greenlight

Pre-submission compliance scanner for the Apple App Store and Google Play. Use this skill when reviewing iOS, macOS, tvOS, watchOS, visionOS, or Android app code (Swift, Objective-C, Kotlin, Java, React Native, Expo) to identify store rejection risks before submission, including Android manifest and Gradle policy checks and built APK/AAB inspection. Triggers on tasks involving app review preparation, compliance checking, App Store or Play submission readiness, target API level deadlines, restricted permissions, or when a user asks about App Store guidelines or Google Play Developer Program Policies.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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 skill body is highly actionable and well-sequenced with executable commands, a concrete fix table, and a strong validation feedback loop. It is slightly heavier than necessary due to inlined install fallbacks and a command catalog that pad the overview.

Suggestions

Trim or relocate the multi-method install fallback and the full 'Other CLI Commands' catalog — the core instruction only needs the canonical 'greenlight preflight .' run; install details could be a one-liner pointer.

Consider dropping the promotional 'About' section, as it adds tokens that do not advance the run-fix-rerun task.

Move the optional Step 4 runtime verification detail to a short summary with a pointer, keeping the primary loop front and center.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with executable commands and a tight fix-mapping table, but the install instructions, full command catalog, and promotional 'About' section add tokens that are not essential to the core run-fix-rerun loop.	4 / 5
Actionability	Provides copy-paste-ready commands for every step plus a concrete per-finding remediation table mapping each issue class to a specific fix (e.g. hardcoded secrets to process.env or Expo Constants), covering the common cases exhaustively.	5 / 5
Workflow Clarity	Clear numbered sequence (scan -> fix in severity order -> re-run) with an explicit validation feedback loop ('Keep looping until GREENLIT') and an optional runtime verification step, including error-recovery guidance for FAILED flows.	5 / 5
Progressive Disclosure	Content is well-organized into clear sections (Steps 1-4, severity table, command catalog) with no bundle files to offload to, but some material (install fallbacks, full CLI catalog, marketing) is inlined where it could be trimmed or referenced to tighten the overview.	4 / 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 a strong, third-person statement that concretely names capabilities, platforms, languages, and natural trigger phrases, cleanly answering both what the skill does and when to use it. It is distinct and unlikely to collide with unrelated skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'identify store rejection risks', 'Android manifest and Gradle policy checks', 'built APK/AAB inspection' — across named platforms and languages, giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (pre-submission compliance scanner identifying rejection risks) and 'when' via the 'Use this skill when reviewing...' trigger clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrases ('app review preparation', 'compliance checking', 'App Store or Play submission readiness') plus concrete trigger terms like 'target API level deadlines' and 'restricted permissions', with good synonym coverage.	5 / 5
Distinctiveness Conflict Risk	The narrow niche of store-submission compliance scanning with named platform/language triggers is clearly distinct from other skills; minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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: RevylAI/greenlight
Path: skills/greenlight/SKILL.md
Commit: fcb36e3

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.