菜单
Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing. Applies to any request where the agent lacks a dedicated tool.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
Use when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md). Establishes schema-first conventions and prefers graph queries over broad search.
Manage your SwarmClaw agent fleet — agents, tasks, chats, chatrooms, goals, schedules, memory, wallets, connectors, autonomy, and 40+ more command groups. Use when asked to dispatch work, check agent status, coordinate multi-agent work, run diagnostics, manage schedules, set goals, or orchestrate across a SwarmClaw dashboard instance.
Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit directly), reading code (use read/file tools), or work inside the SwarmClaw workspace itself.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: local git operations (use git directly), non-GitHub repos, or cloning (use git clone).
Use Google Workspace CLI (`gws`) for Drive, Docs, Sheets, Gmail, Calendar, Chat, and related Workspace API tasks.
| name | resourceful-problem-solving |
| description | Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing. Applies to any request where the agent lacks a dedicated tool. |
| always | true |
When asked to do something and no dedicated tool exists, follow this escalation pattern:
Use use_skill to search for a matching skill. Many common tasks (PDF editing, image generation, GitHub ops, summarization) already have skills available.
If no skill matches, check whether a CLI tool exists:
which <tool> # already installed?
brew search <tool> # macOS
pip search <tool> # Python ecosystem
npm search <tool> # Node ecosystem
If a suitable tool exists, install it and use it.
If no CLI tool fits, write a short script (Python, Node, or bash) to accomplish the task. Common patterns:
reportlab or fpdf2Pillowopenpyxl or csvjq, csvkit, or a short Python scriptcurl + parsing or Python requests + beautifulsoup4Install dependencies as needed: pip install <package> or npm install <package>.
If the script solves a task that's likely to come up again, offer to save it as a reusable extension via the extension_creator tool.