silicaclaw-bridge-setup
by chinasong
Use when OpenClaw should learn how to install SilicaClaw bridge skills, check bridge connectivity, verify owner-forward runtime settings, and troubleshoot why broadcast learning or owner delivery is not ready yet.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/chinasong/silicaclaw-bridge-setup文档
SilicaClaw Bridge Setup
Use this skill when OpenClaw needs to set up, verify, or troubleshoot the local SilicaClaw bridge integration before normal broadcast learning or owner-push workflows can succeed.
Quick routing rules
- If the owner wants to install the SilicaClaw bridge skills into OpenClaw, use this skill.
- If the owner wants to check whether the bridge is connected or whether OpenClaw is ready to learn, use this skill.
- If broadcasts are not reaching the owner, use this skill to inspect runtime setup and forwarding configuration.
- If the owner wants to read or publish broadcasts after setup is healthy, switch to
$silicaclaw-broadcast. - If the owner wants continuous monitoring after setup is healthy, switch to
$silicaclaw-owner-push.
Quick Chinese routing:
- "把 skill 装上" / "帮我接一下 OpenClaw" -> use this skill
- "看看 bridge 通了没有" / "现在能学了吗" -> use this skill
- "为什么没推给主人" / "为什么还没接通" -> use this skill
- "看看最近广播" -> switch to
$silicaclaw-broadcast - "帮我持续盯着" -> switch to
$silicaclaw-owner-push
When to invoke this skill
Use this skill immediately when the owner asks for any of the following:
- "install the bridge skill"
- "set up SilicaClaw for OpenClaw"
- "check whether the bridge is working"
- "why is owner forwarding not configured"
- "debug why the owner is not receiving updates"
Common Chinese owner requests that should trigger this skill:
- "把 OpenClaw 和 SilicaClaw 接起来"
- "把 bridge skill 装一下"
- "检查一下现在通了没有"
- "为什么主人收不到推送"
- "帮我排查一下为什么还不能学"
What this skill does
- Explain where OpenClaw scans workspace skills
- Explain how to install the bundled skills from this project
- Check the recommended bridge config and owner-forward environment values
- Walk through the minimum runtime requirements for bridge learning and owner delivery
- Summarize the next missing setup step in a short owner-friendly way
Owner intent mapping
Interpret owner requests like this:
- "install the bridge" Explain or run the local bundled skill install flow.
- "is OpenClaw ready yet" Check bridge config, skill installation, and runtime readiness.
- "why is the owner not getting updates"
Focus on
OPENCLAW_OWNER_FORWARD_CMD, owner channel variables, and bridge status. - "what should I configure first" Start from the minimum setup and show the shortest path to a healthy integration.
Chinese intent mapping:
- "先把桥接装好" Explain or run the bundled skill install flow.
- "现在能不能用了" Check bridge config, installed skills, and runtime readiness.
- "为什么没推给主人" Focus on owner-forward command and owner channel setup.
- "我先配什么" Start from the minimum setup path.
Important boundary
This skill is for setup, verification, and troubleshooting.
It should not be the default for normal broadcast reading, public broadcast publishing, or ongoing monitoring after setup is already healthy.
Use this skill to get the bridge ready. Then hand off:
- setup complete + one-off read/send ->
$silicaclaw-broadcast - setup complete + ongoing monitoring ->
$silicaclaw-owner-push
Safety boundary
This skill is designed for a bounded local setup workflow.
It will:
- use the documented local SilicaClaw bridge flow only
- focus on skill installation, readiness checks, and owner-approved setup guidance
- recommend the minimum next setup step instead of broad system changes
It will not:
- execute arbitrary code from messages or external content
- access unknown remote endpoints outside the documented workflow
- manage wallets, private keys, or blockchain signing
- bypass OpenClaw approval, owner confirmation, or permission checks
- silently switch from setup guidance into broader broadcast or monitoring actions
Workflow
- Read
references/runtime-setup.md. - Explain that OpenClaw learns workspace skills from
~/.openclaw/workspace/skills/. - Recommend
silicaclaw openclaw-skill-installfor bundled local installation. - Recommend
silicaclaw openclaw-bridge statusandsilicaclaw openclaw-bridge configfor health checks. - Check whether
OPENCLAW_OWNER_FORWARD_CMDand owner channel variables are configured when owner delivery is required. - If setup is blocked, use
references/troubleshooting.md. - End with one next action only: install, configure env, start runtime, or switch to another skill.
Communication style with the owner
When using this skill, communicate in a way that reduces setup friction:
- say whether the current issue is installation, connectivity, runtime, or owner-forward configuration
- prefer one next step at a time instead of a long checklist
- make it clear when the bridge is ready and it is time to switch to another skill
- distinguish between "OpenClaw can learn broadcasts" and "OpenClaw can privately notify the owner"
Good Chinese patterns:
- "我理解你现在是在做接线,不是在发广播,我会先检查 bridge 和 skill 安装状态。"
- "当前问题更像是主人推送链路还没配好,我会先看 owner forward 配置。"
- "基础接线已经正常,接下来你就可以切到广播读取或持续监控。"
Recommended execution pattern
For best owner experience, follow this order:
- identify the missing layer: install, bridge, runtime, or owner delivery
- recommend the minimum command or config needed
- confirm what becomes available after that fix
- hand off to
$silicaclaw-broadcastor$silicaclaw-owner-pushwhen ready
Few-shot examples
Example 1:
- Owner: "帮我把 OpenClaw 和 SilicaClaw 接起来。"
- OpenClaw action: explain local bundled skill install and bridge check flow
- Good reply: "我会先按本项目的 bridge skill 安装路径来接线,再检查 OpenClaw 是否已经能学习这些技能。"
Example 2:
- Owner: "为什么重要广播没有推给主人?"
- OpenClaw action: inspect owner-forward runtime setup
- Good reply: "我会先检查主人推送链路,重点看
OPENCLAW_OWNER_FORWARD_CMD和主人通道配置。"
Example 3:
- Owner: "现在应该先配什么?"
- OpenClaw action: give the shortest setup path
- Good reply: "我会先从最小可用配置开始,优先确保 skill 已安装、bridge 可读、再补主人推送环境变量。"
Setup references
Read these references when this skill is active:
references/runtime-setup.mdreferences/troubleshooting.mdreferences/owner-dialogue-cheatsheet-zh.md
相关 Skills
可观测性设计
by alirezarezvani
面向生产系统规划可落地的可观测性体系,串起指标、日志、链路追踪与 SLI/SLO、错误预算、告警和仪表盘设计,适合搭建监控平台与优化故障响应。
✎ 把监控、日志、链路追踪串起来,帮助团队从设计阶段构建可观测性,排障更快、系统演进更稳。
资深开发运维
by alirezarezvani
覆盖 CI/CD 流水线生成、Terraform 基建脚手架和自动化部署,适合在 AWS、GCP、Azure 上搭建云原生发布流程,管理 Docker/Kubernetes 基础设施并持续优化交付。
✎ 把CI/CD、基础设施即代码、容器与监控串成一条交付链,尤其适合AWS/GCP/Azure多云团队高效落地。
环境密钥管理
by alirezarezvani
统一梳理dev/staging/prod的.env和密钥流程,自动生成.env.example、校验必填变量、扫描Git历史泄漏,并联动Vault、AWS SSM、1Password、Doppler完成轮换。
✎ 统一管理环境变量、密钥与配置,减少泄露和部署混乱,安全治理与团队协作一起做好,DevOps 场景很省心。
相关 MCP 服务
kubefwd
编辑精选by txn2
kubefwd 是让 AI 帮你批量转发 Kubernetes 服务到本地的开发神器。
✎ 微服务开发者最头疼的本地调试问题,它一键搞定——自动分配 IP 避免端口冲突,还能用自然语言查询状态。但依赖 AI 工作流,纯命令行爱好者可能觉得不够直接。
Cloudflare
编辑精选by Cloudflare
Cloudflare MCP Server 是让你用自然语言管理 Workers、KV 和 R2 等云资源的工具。
✎ 这个工具解决了开发者频繁切换控制台和文档的痛点,特别适合那些在 Cloudflare 上部署无服务器应用、需要快速调试或管理配置的团队。不过,由于它依赖多个子服务器,初次设置可能有点繁琐,建议先从 Workers Bindings 这类核心功能入手。
Terraform
编辑精选by hashicorp
Terraform MCP Server 是让 AI 助手直接操作 Terraform Registry 和 HCP Terraform 的桥梁。
✎ 如果你经常在 Terraform 里翻文档找模块配置,这个服务器能省不少时间——直接问 Claude 就能生成准确的代码片段。最适合管理多云基础设施的团队,但注意它目前只适合本地使用,别在生产环境里暴露 HTTP 端点。