Coding
遇到事实、对比、支持情况类问题，或用户追问没懂/你搜过吗/不确定不要瞎说时，先搜索或查文档核实再回答。Use for factual, comparison, or support/capability questions, or when the user challenges accuracy ('did you actually search?'): verify via search/docs before answering.
遇到事实、对比、支持情况类问题，或用户追问没懂/你搜过吗/不确定不要瞎说时，先搜索或查文档核实再回答。Use for factual, comparison, or support/capability questions, or when the user challenges accuracy ('did you actually search?'): verify via search/docs before answering.
回答前先核实，不凭印象直接下判断。
以下问题默认进入核实流程：
以下情况通常不需要触发：
web_searchopenclaw status、gh、git、进程/服务状态四种结论，严格区分，不要混用：
错误：凭印象说"XX 支持 / 不支持"
正确：
错误："本质上是一样的 / 不是一回事"
正确：
错误：说"现在应该还是支持的"
正确：
发送回答前过一遍：
用户： OpenClaw 原生支持多 session 吗？
错误：
是原生支持的，这是核心设计。
正确：
我先查一下官方说明和当前状态。
然后：
根据官方文档和 `openclaw status` 输出，OpenClaw 当前版本支持多 session，显示为 `sessions 3`。具体能力是……
用户： 这个搜索 provider 是基于 MCP 吗？
错误：
不是，它们不是一回事。
正确：
我查一下 OpenClaw 官方文档和插件说明。
然后：
根据官方文档，OpenClaw 的 plugin 机制和 MCP 是并列能力，但部分 plugin 会桥接到 MCP。更准确地说……
Backend, API, infrastructure, cloud, integration, networking, DevOps, deployment, and Terraform engineering. Use when the user asks to build, design, debug, deploy, integrate, or optimize backend systems, APIs, microservices, cloud infrastructure, CI/CD pipelines, databases, or networks. Covers REST
Check whether this agent is talking to a NEAR AI Cloud TEE endpoint or to an ordinary one, and cryptographically attest that endpoint. Reports which models the chain uses, which ones actually served recent turns, warns when a fallback sends prompts outside the enclave, verifies the Intel TDX quote, and uses the nearai-verify OpenClaw plugin for message-level proof. Trigger when asked "am I private", "is this a TEE", "prove it", "verify your latest response", "which model answered that", or before handling sensitive data.
VerifiedEmail (verified.email). Use this skill for ANY VerifiedEmail request — searching and reading data. Whenever a task involves VerifiedEmail, use this s...
Legacy verification-guided task discipline. Helps structure task claims so they can be checked against evidence, receipts, or review criteria. Does not itsel...
Legacy verification-guided rewriting skill. Makes AI-generated text more natural while encouraging claims to stay grounded and attributable. Does not perform...
可靠推理与自验证：对推理结果做命题抽取、矛盾检测、覆盖度评估与事实锚定校验，输出可验证的结论，纯Python零依赖。当需要"验证推理是否正确""自查答案""检测逻辑矛盾""reason-verify"时使用。