Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Maintain and extend the open-websearch MCP server. Trigger when changing search engines, proxy or TLS behavior, tool registration, live parsing behavior, or compatibility and regression behavior inside this repository.
Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO. Use when Codex needs to turn an editable Goal template and user config into a safe local or SSH RL training plan without overstating dry-run results or relabeling SFT, GRPO, GSPO, or other algorithms.
Guide the user through running iFixAi's operational-misalignment diagnostic on their own agent. Prefer pointing it at the user's REAL deployed agent over its HTTP endpoint (its actual tools, retrieval, and governance) with `--provider http --endpoint <url>`; only when no endpoint is reachable, fall back to replicating the model beneath as a bare stand-in (Anthropic, OpenAI, Gemini, Azure, Bedrock, etc.). Graded by the judge(s) of their choice (the same model, one independent judge, or a cross-vendor panel). You are the operator who walks them through it and explains the scorecard, running the SAME `ifixai run` engine as the guided CLI. Use when the user asks to run iFixAi or to detect operational misalignment in an agent.
Run the Lathe worker loop so the web UI's Ask / Verify / Add-a-part buttons drive work directly in this session instead of handing back a command to paste. Use when the user invokes /lathe-work (start it once per session while `lathe serve` is running). Works in any coding agent.
Create or modify a custom ORGII agent definition (and the org it belongs to). Use when the user wants to create, configure, retune, rename, or delete an agent, define an agent's soul / capabilities / tools, organise agents into an org, or asks about agent-definitions.json.
Create, update, or delete custom ORGII agent definitions and agent organizations. Use when the user wants to create an agent, update an agent's soul or tools, rename or remove an agent, manage org membership, list agents or orgs, or asks about agent-definitions.json. Triggers include "创建 agent", "更新 agent 配置", "管理 org", "add agent to org", "delete agent".
Create, read, update, enable, disable, or delete ORGII skills. Use when the user wants to create a new skill, edit an existing skill, list available skills, enable or disable a skill, rename a skill, or delete a skill. Triggers include "创建 skill", "更新 skill", "删除 xxx skill", "list skills", "disable skill".
Add a redacted agent session transcript to a GitHub PR or issue body as local-only provenance for OpenClaw workflows.
MCP (Model Context Protocol) 协议安全测试方法论。当目标环境使用 MCP Server 集成外部工具、 需要评估 MCP 工具描述安全性、或测试 Agent 通过 MCP 调用工具时的安全边界时触发。 覆盖: 工具描述投毒、地毯式骗局(动态篡改)、指令覆盖(Shadow Tool)、隐藏指令(ANSI/Unicode)、 跨 Server 攻击、Token 窃取、Schema 操纵、上下文溢出。
Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.