game-hacking-techniques

Guide for game-hacking technique taxonomy and threat modeling relevant to game security. Use this skill when researching memory access, code injection, overlays, input simulation, engine-specific attack surfaces, or how modern anti-cheat systems constrain user-mode, kernel-mode, hypervisor, and DMA-based cheat implementations.

Quality

69%

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/game-hacking/SKILL.md

Quality

Content

46%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.

A rich, well-structured taxonomy with genuinely executable commands and protocol details, but it is far too long and inlines deep-dive material (YOLO pipeline, KMBox protocol) that should be split into referenced files. Several referenced wiki paths are dead, hurting navigation.

Suggestions

Move the YOLO training pipeline and KMBox protocol deep-dives into separate reference files under references/ and replace them with one-line pointers, cutting the body substantially.

Remove the redundant 'README Coverage' bullet list since every category is expanded in later sections, or collapse it to a single link to the data source.

Verify the referenced wiki/ paths exist in the bundle or remove those pointers; dead references undermine progressive disclosure.

Tighten the YOLO/TensorRT sections to commands and key parameters only, dropping general ML explanation Claude already knows.

Dimension	Reasoning	Score
Conciseness	The ~770-line body is noticeably verbose: the 'README Coverage' list duplicates the detailed sections that follow, and the YOLO training / TensorRT export pipeline over-explains ML concepts Claude already knows; it is padded but not at the level of explaining basic file formats, so above a 1.	2 / 5
Actionability	Provides concrete, executable commands ('yolo detect train ...', 'yolo export model=best.pt format=onnx', 'trtexec --onnx=...'), a working WorldToScreen C++ snippet, KMBox packet offsets, and exact data-source URL formats — mostly copy-paste ready with only minor gaps in surrounding context.	4 / 5
Workflow Clarity	Sequences are present (External/Internal Cheat 4-step lists, data-source priority order) but lack validation checkpoints or feedback loops; the development workflows are rough high-level steps without error-recovery guidance.	3 / 5
Progressive Disclosure	Content that clearly belongs in separate files — the ~130-line YOLO training pipeline and the ~70-line KMBox protocol spec — is inlined into a single monolithic file, and the referenced 'wiki/overviews/game-hacking.md', 'wiki/index.md', and 'wiki/AGENTS.md' paths do not exist in the bundle, leaving navigation buried.	2 / 5
	Total	11 / 20 Passed

Description

92%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.

A strong, third-person description that names concrete capabilities and gives explicit 'Use this skill when...' trigger guidance with specific keywords. It is held back only by omitting a few common cheat terms users would naturally say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'memory access, code injection, overlays, input simulation, engine-specific attack surfaces' plus anti-cheat layers across 'user-mode, kernel-mode, hypervisor, and DMA-based' — giving comprehensive coverage rather than the minor gaps of a 4.	5 / 5
Completeness	Explicitly answers both 'what' ('Guide for game-hacking technique taxonomy and threat modeling') and 'when' ('Use this skill when researching...') with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ('memory access', 'code injection', 'overlays', 'input simulation') with synonyms (user-mode/kernel-mode/hypervisor/DMA), but missing common cheat terms users would say (aimbot, ESP, wallhack) and any file extensions, so below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (game-hacking / anti-cheat threat modeling) with distinct, specialized triggers that would not fire for adjacent skills, yielding minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (774 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: gmh5225/awesome-game-security
Path: .claude/skills/game-hacking/SKILL.md
Commit: a73f4a5

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.