mobile-security

Guide for Android and iOS game security, reversing, and anti-cheat-adjacent platform research. Use this skill when working with APK or IPA analysis, IL2CPP mobile titles, Frida, Zygisk or Magisk, jailbreak or root detection bypass, Android kernel modules, emulator detection, or mobile anti-cheat systems.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/mobile-security/SKILL.md

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is an over-long reference catalog that leans on concepts Claude already knows and embeds detail that belongs in separate files, though it does supply some usable code snippets and source-fetching procedures. Its main weaknesses are verbosity and lack of validation/feedback loops in risky workflows.

Suggestions

Trim explanatory definitions of well-known tools (Frida, Magisk, KernelSU, IL2CPP) and keep only domain-specific operational guidance Claude would not already know.

Move the long tool/README coverage catalogs into a reference file and have SKILL.md summarize categories with one-level-deep links, improving conciseness and progressive disclosure.

Add explicit validation/checkpoint steps to the injection, patching, and root-bypass workflows (e.g. verify hook attached, confirm detection bypass succeeded) so risky operations include feedback loops.

Dimension	Reasoning	Score
Conciseness	The body is a long encyclopedic catalog (500+ lines) listing tools, comparisons, and concepts Claude largely already knows (e.g. what Frida, Magisk, KernelSU, IL2CPP are), padded with explanation that earns few tokens for the task.	1 / 3
Actionability	It includes some concrete snippets (Frida hook, /proc/pid/mem access, archive URL formats), but many sections are descriptive tool lists or numbered pseudo-workflows without executable specifics, leaving guidance incomplete.	2 / 3
Workflow Clarity	Several multi-step processes are listed (IL2CPP analysis, APK workflow) but as flat numbered lists without validation checkpoints or error-recovery feedback loops, despite operations like injection and patching where verification matters.	2 / 3
Progressive Disclosure	It points to external sources (raw README, archive, description URLs, wiki/overviews) at one level, which is good, but the bulk of inline catalog content that should live in reference files is monolithically embedded in SKILL.md rather than split out.	2 / 3
	Total	7 / 12 Passed

Description

100%

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 strong: it concretely lists capabilities, uses third person, provides an explicit 'Use this skill when' trigger clause, and occupies a distinctive niche. It is a model description with no significant weaknesses.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and domains: 'APK or IPA analysis, IL2CPP mobile titles, Frida, Zygisk or Magisk, jailbreak or root detection bypass, Android kernel modules, emulator detection, or mobile anti-cheat systems', listing several specific tasks rather than vague language.	3 / 3
Completeness	It states both what it does ('Guide for Android and iOS game security, reversing, and anti-cheat-adjacent platform research') and when to use it via an explicit 'Use this skill when...' clause enumerating trigger scenarios, satisfying both what and when.	3 / 3
Trigger Term Quality	Includes natural terms users would say such as 'APK or IPA analysis', 'Frida', 'Magisk', 'jailbreak or root detection bypass', and 'emulator detection', giving good coverage of the common phrasings in this domain.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly bounded to mobile game security/reversing with distinctive trigger terms (IL2CPP, Zygisk, Frida, jailbreak bypass), making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (532 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: gmh5225/awesome-game-security
Path: .claude/skills/mobile-security/SKILL.md
Commit: 838f1ed

Reviewed: 3 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.