openclaw-worker
Skill0 starsChanged 3 months agoMITView on GitHub
通过 OpenClaw（Qwen3.7-plus）执行委派任务。Hermes 作为管家委派任务给 OpenClaw 工人。
In this repository219 other files it gives its agents.
- agent-doctrineSkill
- agent-evaluation-frameworkSkill
- agent-visualization-flintSkill
- hermes-agentSkill
- bailian-cliSkill
- edge-browser-automationSkill
- computer-useSkill
- jupyter-live-kernelSkill
- backup-strategiesSkill
- browser-automationSkill
- chinese-ai-free-apiSkill
- cicd-pipeline-templatesSkill
- copybaraSkill
- devops-toolkitSkill
- email-deliverabilitySkill
- monitoring-observabilitySkill
- obsidian-maintenanceSkill
- obsidian-troubleshootingSkill
- openclaw-windowsSkill
- webhook-subscriptionsSkill
- windows-dev-environmentSkill
- windows-masterSkill
- zero-downtime-deploySkill
- codebase-inspectionSkill
- github-workflowSkill
- adaptive-communicationSkill
- agent-cost-dashboardSkill
- agent-evolutionSkill
- agent-governanceSkill
- agent-osSkill
- context-efficient-toolsSkill
- context-loss-awarenessSkill
- creative-synthesisSkill
- hermes-desktop-pluginsSkill
- emotional-intelligenceSkill
- graph-engineering-workflowSkill
- hermes-maintenanceSkill
- hermes-voiceSkill
- hermes-hygieneSkill
- identity-coreSkill
- income-loopSkill
- master-synthesisSkill
- meta-cognitionSkill
- reasoning-engineSkill
- self-preservationSkill
- teaching-abilitySkill
- temporal-awarenessSkill
- hermes-themesSkill
- thinking-visualizationSkill
- user-modelingSkill
- voice-full-restoreSkill
- knowledge-graph-traversalSkill
- mcp-browser-canvasSkill
- free-api-gatewaySkill
- native-mcpSkill
- web-reverse-apiSkill
- ai-edaSkill
- huggingface-hubSkill
- industrial-ai-siemens-mcpSkill
- industrial-ai-unifiedSkill
- The first 60 shown.
The file
Files
OpenClaw Worker 委派
架构
- Hermes（管家）：DeepSeek V4 Pro，负责理解需求、拆解任务、委派给 OpenClaw
- OpenClaw（工人）：Qwen3.7-plus（阿里百炼），负责执行具体编码/文件/搜索任务
调用方式
通过 shell 调用 OpenClaw 单次执行任务：
# 环境变量（必须设置）
set OPENCLAW_STATE_DIR=D:\openclaw\state
# 调用命令（--json 输出结构化结果）
cd /d D:\openclaw && D:\sofeware\node\node.exe D:\openclaw\node_modules\openclaw\openclaw.mjs agent --local --agent main --message "任务描述" --json关键参数
--local：本地嵌入模式，不走 gateway--agent main：使用 main agent--message "..."：任务内容--json：输出 JSON（包含 payloads[].text 为回复文本）--message-file <path>：从文件读取多行任务
解析结果
JSON 输出中：
payloads[0].text：OpenClaw 的回复文本meta.durationMs：执行耗时meta.agentMeta.usage：token 用量
适用场景
- 需要 Qwen 模型视角的编码任务
- 文件读写操作（OpenClaw 有 read/write/edit/exec 工具）
- 需要 OpenClaw 工作区上下文的任务
- 双模型交叉验证（DeepSeek + Qwen）
注意事项
- OpenClaw 的 workspace 在 D:\openclaw\state\workspace\
- OpenClaw 会话是持久的（session c8674ede...），有上下文记忆
- 单次执行约 5-15 秒，复杂任务更长
- OpenClaw 有自己的工具集（read/write/exec/web_search/browser 等）
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.