anti-cheat-systems

Guide for modern game anti-cheat architecture, Windows kernel monitoring, and detection tradeoffs. Use this skill when analyzing EAC, BattlEye, Vanguard, FACEIT AC, kernel callbacks, handle protection, manual-map detection, boot-start drivers, BYOVD, DMA threats, or behavioral telemetry in game security research.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/anti-cheat/SKILL.md

Quality

Content

42%

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

The content is technically rich and well-sectioned but far too verbose and monolithic, with encyclopedic detail inlined into SKILL.md rather than offloaded to bundled reference files. It reads as a reference dump more than an actionable, progressively-disclosed skill overview.

Suggestions

Move the large encyclopedic blocks (kernel pool scanning, AI aimbot detection, DMA detection methodology, ML classifier) into separate reference files under references/ and keep SKILL.md as a concise overview that links to them one level deep.

Collapse the overlapping AI-aimbot sections (visual detection, server-side replay, ML classifier) into a single consolidated reference to remove redundancy and tighten token usage.

Add a concrete, sequenced analysis workflow with validation checkpoints (e.g., identify target system -> fetch description/archive via the documented URL priority -> map detection layers -> verify against README sections) instead of descriptive mechanism lists.

Dimension	Reasoning	Score
Conciseness	The body is a ~920-line encyclopedic dump with prose lists stuffed into code fences and overlapping sections (AI aimbot detection, server-side replay, and ML classifier repeat similar material); a meaningful core is specialized but it is heavily padded and could be tightened.	2 / 3
Actionability	There are concrete artifacts (archive/description URL formats, a fetch priority order, firmware tier mappings, an ML feature vector), but most of the body describes detection mechanisms conceptually rather than giving executable commands or a concrete analysis procedure.	2 / 3
Workflow Clarity	Sequences exist (Research Techniques steps, Data Source priority order 1->2->3) but there is no end-to-end analysis workflow with validation checkpoints or error-recovery feedback loops.	2 / 3
Progressive Disclosure	It is a monolithic wall of inline text; the referenced wiki/overviews/anti-cheat.md, wiki/index.md, and wiki/AGENTS.md paths are not present in the bundle (references/, scripts/, assets/, wiki/ do not exist), so detailed material that should be split into separate files is inlined instead.	1 / 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 specific, trigger-rich, and complete, clearly stating both what the skill covers and when to invoke it in third-person voice. It is a strong, low-conflict description for a specialized domain.

Dimension	Reasoning	Score
Specificity	Names concrete domain objects and actions ('analyzing EAC, BattlEye, Vanguard, FACEIT AC, kernel callbacks, handle protection, manual-map detection, boot-start drivers, BYOVD, DMA threats'), listing multiple specific items rather than vague language.	3 / 3
Completeness	It states what ('Guide for modern game anti-cheat architecture, Windows kernel monitoring, and detection tradeoffs') and an explicit when ('Use this skill when analyzing ...'), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	The trigger list ('EAC, BattlEye, Vanguard, FACEIT AC, kernel callbacks, handle protection, manual-map detection, BYOVD, DMA threats, behavioral telemetry, game security research') closely matches the natural terms a user researching anti-cheat would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow (game anti-cheat systems and Windows kernel detection) with distinctive system-specific triggers, making conflict with unrelated skills unlikely.	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 (927 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: gmh5225/awesome-game-security
Path: .claude/skills/anti-cheat/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.