Agent building

Generate log2timeline and Plaso super-timelines and triage them in Timesketch.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard input/output scanners as runtime defenses.

Identify poisoned training data and backdoored models across the ML pipeline.

Build Anvia agents and tools — Agent options, tool definitions, approvals, memory, streaming, multi-agent teams, and provider wiring.

Connect Discord, Slack, and Telegram to Anvia agents — channel adapters, agent-backed bots, proactive delivery, sessions, streaming, and platform actions.

Build deterministic multi-step work with Anvia Pipelines — steps, composition, parallel branches, decision routing, batch runs, agent, extractor, and decision…

根据用户描述生成高质量绘图 prompt，并按通用、roadmap、schematic 模式通过 BenszAPI 直接完成 gpt-image-2.5-flare、gpt-image-2.5-sunburst、gpt-image-2 或 Nano Banana/Gemini…

当用户明确要求使用 awesome-code、进行多代理协作或需要复杂任务规划时使用。它负责拆解任务、选择专业角色、设置门禁并审查结果；所有 Agent 的创建、隔离、串行或并行执行都必须交给 `parallel-vibe`。⚠️ 不适用：用户只需单一角色完成简单修改或咨询，或未表达多代理协作意图。

当用户明确要求并行或串行启用多个 Agent，或上游 Skill 声明需要统一的多 Agent 执行底座时使用。负责 Agent 的创建、隔离、调度、回收和汇总。⚠️ 不适用：普通 shell 并发、单元测试并发、下载任务，或要求强隔离的敏感数据处理。

为任意 Agent Skill 设计、实现、接入或精简 Verifier 与 State；当用户希望给目标 skill 配置验证器/状态机、落实已有设计，或仅规划和审查架构时使用，尤其适合需要避免过度设计、硬编码并符合 Kernel 契约的任务。

Connect MCP servers to Anvia agents — clients, transports, tool discovery, URL safety, and lifecycle.

Audit any repository and set it up so coding agents ship changes safely with little human review.

Rename Herdr tabs, panes, and agents so each sidebar entry says in a few words what that session is doing.

Show what coding-agent sessions cost for every worktree of the current repo — Cursor, Claude Code, and Codex — as handoff-style cards with dollars and tokens.

List and continue coding-agent transcripts across Cursor, Claude Code, Codex, Gemini, and other local agents.

Operate the user's already-open, logged-in Chrome tabs through Chrome DevTools MCP.

Meta-skill que orquestra todos os agentes do ecossistema.

当 Bensz Agent Skill 或基础设施本身因设计缺陷出现问题，或用户明确要求记录/上报此类 bug 时使用。⚠️ 不适用：用户数据错误、第三方服务故障、用户主动改源码或模型偶发波动。

当用户明确要求压缩、瘦身或精简 Agent Skill 文档、降低上下文开销且不改变功能时使用。⚠️ 不适用：新增功能、修复脚本逻辑、批量改代码或压缩普通文档。

当用户明确要求搜索、寻找、查找或推荐某个领域的 Agent Skill 时使用。对候选 Skill 进行多来源检索与比较后给出推荐。⚠️ 不适用：只想查看已有技能列表，或没有明确搜索/推荐意图。

Madorin 插件开发入口技能。用于统一编排 Native、MCP、Process 三类通道，约束工程规范、插件元数据协议、宿主能力申请、设置界面 schema、外部包 AOT 校验、发布安装与运行时更新流程。触发关键词：插件开发、Native 插件、MCP 插件、Process 插件、进程插件、发布插件、安装插件。

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can…

Retrospective of one Claude Code session, built from its jsonl log and published as a single artifact page — where the time went (AI working vs.

Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims…