mia-trustMIA-Trust Pipeline - Memory-Intelligent Assistant 信任守门+记忆进化 pipeline
Install via ClawdBot CLI:
clawdbot install sii-yucheng2002/mia-trustGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://your-api-endpoint/v1/chat/completionsAudited Apr 16, 2026 · audit v1.0
Generated Sep 29, 2026
在金融、医疗等强监管行业中,AI Agent 在生成执行计划前需要经过多重安全校验。MIA-Trust 的 guard_blocked 模块能够对用户问题进行 6 维度安全预检,evaluate_plan 则对生成计划进行 3 轮审查,确保 Agent 行为符合合规要求,避免敏感操作或违规输出。
企业客服或内部知识助手需要记住历史交互经验,避免重复询问。MIA-Trust 的双记忆存储(memory + trust_experience)可将每次问答与执行结果持久化,后续通过 search 快速召回相似问题处理方案,持续提升回答准确率和用户满意度。
在 DevOps 场景中,AI 助手需根据告警生成修复计划并自动执行。MIA-Trust 的 Planner 生成计划、Trust 审查安全性,执行后记录到双记忆,形成可追溯的运维知识库,减少人为误操作并加速故障恢复。
在线教育平台利用 MIA-Trust 分析学生问题,生成个性化学习计划并评估其合理性与安全性,防止不当内容。系统还会存储每次辅导反馈到记忆库,不断优化后续推荐策略,提供更贴合学生需求的学习路径。
电商客服机器人可借助 MIA-Trust 对用户咨询进行安全预检,生成退换货或推荐方案并审查,执行后存储成功案例与反馈。通过记忆进化,机器人能快速复用高转化话术与处理流程,提升售后效率和客户复购率。
基础 Pipeline 以 ISC 协议开源,吸引开发者社区。企业版提供高级安全策略模板、审计日志、团队协作与私有化部署支持,按年订阅收费。
将 guard_blocked、evaluate_plan、memory 等核心能力封装为云端 API,客户按调用次数或 Token 用量付费,适合中小型团队快速集成。
针对金融、医疗、教育等垂直行业提供定制化 Pipeline 集成、安全合规调优及私有化部署服务,收取项目制实施费用与年度维护费。
💬 Integration Tip
先配置环境变量 MIA_PLANNER_MODE、API_KEY、URL 和 MODEL,再通过 run.mjs 一键运行完整 Pipeline;分步调用时注意各模块参数格式(JSON 字符串),并确保 node 依赖已通过 npm install 安装。
Scored May 25, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.