money-verify
cheat-on-money skill 的反诈核心。对某个具体的兼职/副业/项目做反诈 rubric 打分,实时上网查证负面与真实收款证据,输出 高危/存疑/可行 判定 + 验证第一步 + 诚实收入预期。触发词:"XX靠谱吗"/"这个项目是不是骗局"/"帮我查下这个兼职"/"money verify"/"验证机会"/"这个能信吗"。
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
cheat-on-money skill 的反诈核心。对某个具体的兼职/副业/项目做反诈 rubric 打分,实时上网查证负面与真实收款证据,输出 高危/存疑/可行 判定 + 验证第一步 + 诚实收入预期。触发词:"XX靠谱吗"/"这个项目是不是骗局"/"帮我查下这个兼职"/"money verify"/"验证机会"/"这个能信吗"。
The ONLY sanctioned path to the Kronk MCP service (`web_search`, `fuzzy_edit`) in the rote-routed config. Every command is a `rote ...` invocation in Bash. Load whenever you need web research, or when a host edit fails on exact-string matching and you need the rote-routed `fuzzy_edit` fallback.
GitHub 源码解读助手。适用于用户提供 GitHub 仓库链接,并希望解读源码、理解原理、分析架构、生成学习报告或快速上手文档时使用。会在 working 目录下生成源码解读和快速上手两份文档。默认先交付初稿,不自动复查;如果用户明确同意,再安排后续复查。不适用于仅克隆仓库或只要一句简介的场景。
Qoder 官方文档知识库,包含产品介绍、用户指南、功能配置、扩展能力、账户定价和故障排查。当用户询问 Qoder 相关问题(如安装、使用、功能、定价、快捷键、MCP、Skills、Quest Mode、Repo Wiki 等)时使用此 skill。
Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence. Query and read the PR-driven history docs under model-pr-optimization-history before choosing source paths, fast paths, kernel/fusion ideas, regression risks, or validation lanes.
Look up and cite international protocol standards (RFC/IEEE) (TR-F021). Any change to RADIUS/EAP/accounting/CoA/IPv6 protocol behavior should first check docs/rfcs and cite the clause.
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of <url>". Proactively suggest when the user pastes a URL and asks what it contains. (munder-difflin)