game-hacking-techniques

Classify game-cheating threats across client memory, code injection, rendering, input, engines, kernels, DMA and remote transports. Use for repository-backed attack-surface maps, attacker prerequisites, state exposure, legitimate comparison baselines, and observable artifacts. Select engine source, capture or diagnostic resources that fit the evidence; separate source, transport, processing and server authority, and report benign counterexamples and limits without inferring a product or enforcement policy.

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/game-hacking/SKILL.md

Quality

Content

50%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 rich, highly actionable taxonomy with concrete code, commands, and protocol details, plus two well-signaled reference files. Its main weaknesses are token inefficiency from inlining reference-grade material and a lack of explicit validation checkpoints in its scattered workflows.

Suggestions

Move the full YOLO training pipeline, KMBox protocol details, and World-to-Screen code into separate reference files (e.g. references/ai-aimbot-pipeline.md, references/input-transport-protocols.md), leaving only a concise overview and a link in SKILL.md.

Add an explicit, numbered analysis workflow with validation checkpoints (e.g. identify capability -> check prerequisites -> record observable artifacts -> cross-check benign counterexample -> flag unresolved uncertainty) rather than scattering the method across prose and the attack-surface-map reference.

Trim the inline technique listings (hooking methods, injection methods, driver communication taxonomy) to the decision-relevant subset and point to the repository resource for the exhaustive list.

Dimension	Reasoning	Score
Conciseness	The body inlines hundreds of lines of reference-grade material (full YOLO training pipeline with commands, KMBox protocol hex codes and packet structure, World-to-Screen C++, exhaustive technique taxonomies) that read like separate reference files; it is dense domain knowledge rather than concepts Claude already knows, but it is noticeably verbose with several padded sections, fitting anchor 2 rather than 3.	2 / 5
Actionability	Highly concrete and largely executable: copy-paste YOLO commands ("yolo detect train data=... model=yolov8n.pt epochs=100 imgsz=640 batch=16 device=0", "trtexec --onnx=best.onnx --saveEngine=best.engine --fp16"), a World-to-Screen C++ function, specific API names (OpenProcess, ReadProcessMemory, NtReadVirtualMemory), and KMBox command codes with packet offsets; not a 5 because much of the taxonomy is listing rather than instructing.	4 / 5
Workflow Clarity	Primarily a taxonomy/classification skill rather than a single workflow; the YOLO pipeline includes a validation step (step 5) but the core analysis sequence is scattered and most listed sequences (External/Internal cheat, escalation model) lack validation checkpoints, matching anchor 3.	3 / 5
Progressive Disclosure	Two real, clearly-signaled one-level-deep references exist (references/attack-surface-map.md and references/repository-resources.md, both verified present) with well-organized sections, but the body itself inlines large reference-grade blocks (YOLO pipeline, KMBox protocol, W2S code) that should be split into separate files, fitting anchor 3 rather than 4.	3 / 5
	Total	12 / 20 Passed

Description

67%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 specific, third-person, and covers a comprehensive threat surface with an explicit Use-for clause, but its trigger terms lean technical and miss the natural vocabulary (aimbot, wallhack, ESP, anti-cheat) users would actually say. Boundaries against sibling skills are signaled, leaving only minor overlap risk.

Suggestions

Add concrete user-facing trigger phrases to the Use-for clause, e.g. "Use when the user mentions aimbots, wallhacks, ESP/overlays, DMA cheats, HWID spoofing, or game anti-cheat evasion."

Swap abstract phrases like "state exposure" and "observable artifacts" for more natural synonyms that a user requesting this skill would actually say.

Sharpen the closing clause ("without inferring a product or enforcement policy") into a concrete action so the final capability reads as a directive rather than a caveat.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ("Classify", "Select engine source, capture or diagnostic resources", "separate source, transport, processing and server authority", "report benign counterexamples and limits") with comprehensive domain coverage across memory, injection, rendering, input, engines, kernels, DMA and remote transports; not a 5 because a few actions stay abstract ("without inferring a product or enforcement policy").	4 / 5
Completeness	Clearly states what ("Classify game-cheating threats across...") and provides an explicit "Use for..." when-clause, but the when-scenarios are abstract attack-model situations rather than concrete user trigger phrases, matching anchor 4 instead of 5.	4 / 5
Trigger Term Quality	"game-cheating threats" is the one natural user phrase, while "state exposure", "observable artifacts", "attacker prerequisites" and "enforcement policy" are jargon; common variations users actually say (aimbot, wallhack, ESP, anti-cheat) are absent, so it sits at anchor 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (game-cheating threats) and explicitly defers to sibling skills (game-server-security, game-supply-chain-security), but several closely related sibling skills (anti-cheat, dma-attack, game-engine) create minor overlap risk, fitting anchor 4 rather than 5.	4 / 5
	Total	15 / 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 (755 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 15 suspicious	Warning

	Total	14 / 16 Passed

Repository: gmh5225/awesome-game-security
Path: .claude/skills/game-hacking/SKILL.md
Commit: c7e4d3f

Reviewed: 5 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.