Agent Skills › gmh5225/awesome-game-security › game-security-research-rigor

game-security-research-rigor

GitHub

用于验证游戏安全领域争议性或重大声明的严谨性，要求基于原始证据、可复现性及明确信任边界进行推理，区分观察与归因，校准不确定性。

.claude/skills/research-rigor/SKILL.md gmh5225/awesome-game-security

Trigger Scenarios

需要验证游戏安全相关结论处理存在争议的漏洞或攻击声称评估安全研究证据质量

Install

npx skills add gmh5225/awesome-game-security --skill game-security-research-rigor -g -y

More Options

Non-standard path

npx skills add https://github.com/gmh5225/awesome-game-security/tree/main/.claude/skills/research-rigor -g -y

Use without installing

npx skills use gmh5225/awesome-game-security@game-security-research-rigor

指定 Agent (Claude Code)

npx skills add gmh5225/awesome-game-security --skill game-security-research-rigor -a claude-code -g -y

安装 repo 全部 skill

npx skills add gmh5225/awesome-game-security --all -g -y

预览 repo 内 skill

npx skills add gmh5225/awesome-game-security --list

SKILL.md

Frontmatter

{
    "name": "game-security-research-rigor",
    "description": "Verify consequential or disputed game-security claims with primary sources, reproducible evidence, explicit trust boundaries, and calibrated uncertainty. Use alongside a domain skill when evidence quality affects the conclusion."
}

Game security research rigor

Keep conclusions no stronger than the evidence. Separate observation, finding, attribution, and action, and record temporal and environmental limits.

Topic routing

Claims and workflow for reasoning layers, research steps, and versioned claim records.
Evaluation and governance for detector metrics, invariants, decision policy, quality gates, and test limits.
Sources and repository evidence for source roles and collection-specific evidence.
Robustness and triage for confounders, adversarial inputs, and disagreement.
Skill evaluation for catalog routing tests.

State what would falsify the conclusion and what evidence remains unavailable. Do not convert a repository summary, community report, or absence of evidence into a verified product claim.