Skill 审计报告
llm-campaign-drift-gate 审计报告.
Gate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt-*-latest, gemini-*-preview, any provider alias without a pinned version). Use when: (1) resuming a paused or credit-exhausted scoring run days after its last chunk, (2) topping up credits to finish a campaign, (3) extending a cached scoring pipeline with new items. Prevents silently splicing two model versions or serving revisions into one measure. Verified 2026-07-16: for $0.30 caught a serving-revision drift WITHIN DeepSeek v4-flash (same alias, same family, litigation scores systematically shifted across a 2-day gap) before an $83 resume spend.
OpenAgentSkill 信任评分
OpenAgentSkill 信任评分
Trust Score 帮助 Agent 在安装前判断一个 Skill 是否足以进入候选清单。
GitHub 采用度
警告48
47 个 GitHub Stars
Star/Fork 活跃度
警告43
47 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过100
今天有推送
许可证清晰度
通过86
MIT
README/SKILL.md 完整度
通过86
元数据包含足够的用法与工作流上下文
依赖与运行时风险
通过90
公开元数据中未发现主要依赖风险提示
安装可用性
通过92
npx skills add kennethkhoocy/applied-micro-skills --skill llm-campaign-drift-gate
安装命令安全性
通过92
标准软件包或运行时安装路径
权限范围
通过100
公开元数据中未发现高风险权限范围
仓库证据
通过86
https://github.com/kennethkhoocy/applied-micro-skills/tree/main/plugins/applied-micro/skills/llm-campaign-drift-gate
审查状态
通过88
可用 AI 审查数据
Agent 验证结果
信息54
暂未有 Agent 结果数据
检查项
安装与采用审查
安装路径
92
npx skills add kennethkhoocy/applied-micro-skills --skill llm-campaign-drift-gate
仓库
88
https://github.com/kennethkhoocy/applied-micro-skills/tree/main/plugins/applied-micro/skills/llm-campaign-drift-gate
许可证
86
MIT
维护
100
今天有推送
AI 审查
88
Approved with no listed issues
README/SKILL.md 完整度
86
Usable description available
依赖风险
90
公开元数据中未发现主要依赖风险提示
安装命令安全性
92
标准软件包或运行时安装路径
权限范围
100
公开元数据中未发现高风险权限范围
Star/Fork 活跃度
43
47 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息
采用度
42
47 个 GitHub Stars
警告
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 47 GitHub stars
- Stars/forks activity: 47 stars, 0 forks; issue activity unavailable in current metadata
方法
本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛;它不是完整的源代码安全审计。
对比相近选项
下一步可审计的相关 Skill
Opencode
The open source coding agent.
201K Stars · 审计报告
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
169K Stars · 审计报告
Grill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
165K Stars · 审计报告