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

58%

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

25%

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 a comprehensive but bloated monolith: it inlines large amounts of domain knowledge that could be deferred to the referenced archive/wiki, lacks validation checkpoints in its workflows, and provides no progressive file structure despite being far over a reasonable overview length.

Suggestions

Collapse the SKILL.md body into a concise overview and move the detailed pipelines (YOLO training, KMBox protocol, AI visual aimbot architecture) into dedicated reference files under references/, keeping only navigation pointers inline.

Add explicit validation checkpoints to multi-step workflows (e.g., verify an archive fetch succeeded before parsing it, validate a trained model's mAP before exporting to TensorRT).

Trim redundant explanatory prose and concept restatements (memory access methods, injection taxonomies) to assume Claude's competence and respect the context budget.

Dimension	Reasoning	Score
Conciseness	The body is extremely long and padded with extensive explanatory prose—e.g., the AI Visual Cheats block, the full YOLO training pipeline, and KMBox protocol byte maps restate substantial domain knowledge Claude already has rather than pointing to it, fitting the verbose anchor.	1 / 3
Actionability	There are some concrete, executable elements (the WorldToScreen C++ function, training/export CLI commands, URL formats), but large sections are descriptive taxonomies and prose lists rather than copy-paste-ready instructions, so it is only partly actionable.	2 / 3
Workflow Clarity	Sequences like the Development Workflow and YOLO pipeline are numbered, and the Data Source section gives a clear priority order, but there are no validation checkpoints or feedback loops for operations (e.g., verifying archive fetches, validating a built model), capping it at 2.	2 / 3
Progressive Disclosure	No bundle files exist and nearly all detail is inlined as a monolithic wall of text; external material is referenced only via raw GitHub URLs and a wiki path, with no one-level-deep structured reference files, matching the monolithic anchor.	1 / 3
	Total	6 / 12 Passed

Description

92%

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 is specific, trigger-rich, and explicitly pairs what the skill does with when to use it. Its only weakness is mild generic overlap with general security-research skills, which slightly lowers distinctiveness.

Suggestions

Sharpen distinctiveness by scoping triggers to games specifically (e.g., 'Use when researching cheats or anti-cheat for PC/console games') to reduce overlap with general security-research skills.

Consider leading with the offensive-vs-defensive framing more tightly so it is clearly the game-hacking taxonomy rather than a broad security skill.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete capabilities—'researching memory access, code injection, overlays, input simulation, engine-specific attack surfaces'—plus concrete modes like 'user-mode, kernel-mode, hypervisor, and DMA-based cheat implementations', matching the multi-action anchor.	3 / 3
Completeness	It explicitly answers what (a guide for technique taxonomy and threat modeling) and when via 'Use this skill when researching memory access, code injection, overlays...', satisfying both the what and the explicit-when anchors.	3 / 3
Trigger Term Quality	It surfaces natural research terms users would say—'memory access', 'code injection', 'overlays', 'input simulation', 'anti-cheat systems'—with good coverage of common phrasings across the threat-modeling domain.	3 / 3
Distinctiveness Conflict Risk	The game-security/threat-modeling niche is fairly distinct, but the broad phrasing 'relevant to game security' and overlapping terms (memory access, code injection) could overlap with general security-research skills, so it stops just short of the clear-niche anchor.	2 / 3
	Total	11 / 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 (756 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: gmh5225/awesome-game-security
Path: .claude/skills/game-hacking/SKILL.md
Commit: 9efdfd0

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.