Rank
70
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Traction
No public download signal
Freshness
Updated 2d ago
Crawler Summary
ACP Bridge for OpenClaw ACP Bridge for OpenClaw 通过 ACP 协议实现与 Gemini CLI 的多轮对话桥接。本 skill 提供一个 HTTP server, OpenClaw agent 可通过 HTTP 请求创建、使用和管理与 Gemini CLI 的多轮对话 session。 --- 前置条件 1. Go 环境 需要 Go 1.21+。验证: 2. Gemini CLI 需要安装 Gemini CLI 并确保在 PATH 中可用: 如果 Gemini CLI 安装在非标准路径,启动时通过 --gemini-bin 指定。 3. Gemini API Key Gemini CLI 需要配置 API Key,确保你已完成 gemini auth 或设置了对应的环境变量。 --- 部署与启动 一键部署 启动成功后你会看到: 后台运行(生产环境) 使用 systemd(Linux 服务器) --- CLI 参数 | Flag Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Freshness
Last checked 2/25/2026
Best For
dispatch-gemini-cli-skill is best for general automation workflows where OpenClaw compatibility matters.
Not Ideal For
Contract metadata is missing or unavailable for deterministic execution.
Evidence Sources Checked
editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack
ACP Bridge for OpenClaw ACP Bridge for OpenClaw 通过 ACP 协议实现与 Gemini CLI 的多轮对话桥接。本 skill 提供一个 HTTP server, OpenClaw agent 可通过 HTTP 请求创建、使用和管理与 Gemini CLI 的多轮对话 session。 --- 前置条件 1. Go 环境 需要 Go 1.21+。验证: 2. Gemini CLI 需要安装 Gemini CLI 并确保在 PATH 中可用: 如果 Gemini CLI 安装在非标准路径,启动时通过 --gemini-bin 指定。 3. Gemini API Key Gemini CLI 需要配置 API Key,确保你已完成 gemini auth 或设置了对应的环境变量。 --- 部署与启动 一键部署 启动成功后你会看到: 后台运行(生产环境) 使用 systemd(Linux 服务器) --- CLI 参数 | Flag
Public facts
4
Change events
1
Artifacts
0
Freshness
Feb 25, 2026
Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Trust score
Unknown
Compatibility
OpenClaw
Freshness
Feb 25, 2026
Vendor
Yuanshanxike
Artifacts
0
Benchmarks
0
Last release
Unpublished
Key links, install path, and a quick operational read before the deeper crawl record.
Summary
Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Setup snapshot
git clone https://github.com/yuanshanxike/dispatch-gemini-cli-skill.gitSetup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.
Vendor
Yuanshanxike
Protocol compatibility
OpenClaw
Handshake status
UNKNOWN
Crawlable docs
6 indexed pages on the official domain
Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.
Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.
Extracted files
0
Examples
6
Snippets
0
Languages
typescript
Parameters
bash
go version # 如未安装:https://go.dev/dl/
bash
# 安装 npm install -g @anthropic-ai/gemini-cli # 验证 gemini --version
bash
# 1. 进入项目目录 cd acp-bridge # 2. 编译 go build -o acp-bridge . # 3. 启动(默认端口 9090) ./acp-bridge --port 9090 --gemini-bin gemini
text
level=INFO msg="Gemini CLI found" path=/usr/local/bin/gemini level=INFO msg="ACP Bridge server starting" addr=:9090
bash
curl http://localhost:9090/health
bash
# 使用 nohup 后台运行
nohup ./acp-bridge --port 9090 --gemini-bin gemini > bridge.log 2>&1 &
# 检查是否运行正常
curl http://localhost:9090/health
# 预期输出:{"ok":true}Full documentation captured from public sources, including the complete README when available.
Docs source
GITHUB OPENCLEW
Editorial quality
ready
ACP Bridge for OpenClaw ACP Bridge for OpenClaw 通过 ACP 协议实现与 Gemini CLI 的多轮对话桥接。本 skill 提供一个 HTTP server, OpenClaw agent 可通过 HTTP 请求创建、使用和管理与 Gemini CLI 的多轮对话 session。 --- 前置条件 1. Go 环境 需要 Go 1.21+。验证: 2. Gemini CLI 需要安装 Gemini CLI 并确保在 PATH 中可用: 如果 Gemini CLI 安装在非标准路径,启动时通过 --gemini-bin 指定。 3. Gemini API Key Gemini CLI 需要配置 API Key,确保你已完成 gemini auth 或设置了对应的环境变量。 --- 部署与启动 一键部署 启动成功后你会看到: 后台运行(生产环境) 使用 systemd(Linux 服务器) --- CLI 参数 | Flag
通过 ACP 协议实现与 Gemini CLI 的多轮对话桥接。本 skill 提供一个 HTTP server, OpenClaw agent 可通过 HTTP 请求创建、使用和管理与 Gemini CLI 的多轮对话 session。
需要 Go 1.21+。验证:
go version
# 如未安装:https://go.dev/dl/
需要安装 Gemini CLI 并确保在 PATH 中可用:
# 安装
npm install -g @anthropic-ai/gemini-cli
# 验证
gemini --version
如果 Gemini CLI 安装在非标准路径,启动时通过
--gemini-bin指定。
Gemini CLI 需要配置 API Key,确保你已完成 gemini auth 或设置了对应的环境变量。
# 1. 进入项目目录
cd acp-bridge
# 2. 编译
go build -o acp-bridge .
# 3. 启动(默认端口 9090)
./acp-bridge --port 9090 --gemini-bin gemini
启动成功后你会看到:
level=INFO msg="Gemini CLI found" path=/usr/local/bin/gemini
level=INFO msg="ACP Bridge server starting" addr=:9090
# 使用 nohup 后台运行
nohup ./acp-bridge --port 9090 --gemini-bin gemini > bridge.log 2>&1 &
# 检查是否运行正常
curl http://localhost:9090/health
# 预期输出:{"ok":true}
# /etc/systemd/system/acp-bridge.service
[Unit]
Description=ACP Bridge for OpenClaw
After=network.target
[Service]
ExecStart=/path/to/acp-bridge --port 9090 --gemini-bin /usr/local/bin/gemini
Restart=on-failure
RestartSec=5
Environment=HOME=/root
[Install]
WantedBy=multi-user.target
sudo systemctl enable acp-bridge
sudo systemctl start acp-bridge
sudo systemctl status acp-bridge
| Flag | Default | 说明 |
| ---------------- | --------- | --------------------------------------- |
| --port | 9090 | HTTP server 端口 |
| --gemini-bin | gemini | Gemini CLI binary 路径 |
| --gemini-model | (empty) | 指定 Gemini 模型(如 gemini-2.5-pro) |
| --debug | false | 启用 debug 日志 |
创建一个 ACP session(启动 Gemini CLI 子进程)。
// Request
{
"cwd": "/path/to/workdir",
"permissionCallbackUrl": "http://127.0.0.1:8080/permission/callback"
}
// Response
{ "sessionId": "sess-12345" }
cwd(必填):Gemini agent 工作的目录permissionCallbackUrl(推荐):权限回调地址。未配置时,所有权限请求将被拒绝发送一条 prompt 到已有 session(支持多轮,同一 session 保持上下文)。
// Request
{ "sessionId": "sess-12345", "prompt": "分析这段代码的性能问题" }
// Response
{
"text": "agent 输出的完整文本",
"toolCalls": [
{ "toolCallId": "tc_1", "title": "ReadTextFile", "status": "completed" }
],
"stopReason": "end_turn"
}
关闭 session 并终止 Gemini CLI 子进程。用完务必关闭,否则子进程会残留。
// Request
{ "sessionId": "sess-12345" }
// Response
{ "ok": true }
健康检查。
{ "ok": true }
当 Gemini agent 需要执行敏感操作时,bridge 会 POST 到 permissionCallbackUrl。
此外,对敏感路径的文件写入(如 /etc、~/.ssh 等)也会触发额外的权限回调。
// Bridge -> OpenClaw (POST permissionCallbackUrl)
{
"sessionId": "sess-12345",
"toolCallTitle": "WriteTextFile: /tmp/output.txt",
"options": [
{ "optionId": "opt_1", "name": "Allow Once", "kind": "allow_once" },
{ "optionId": "opt_2", "name": "Deny", "kind": "deny" }
]
}
// 批准:
{ "selectedOptionId": "opt_1" }
// 拒绝:
{ "cancelled": true }
在 OpenClaw agent 的 tool 配置中,添加以下 HTTP 工具即可:
name: gemini_create_session
description: "创建一个 Gemini 多轮对话 session"
method: POST
url: "http://<bridge-host>:9090/session/create"
body:
cwd: string # 工作目录
permissionCallbackUrl: string # 权限回调 URL
returns: sessionId
name: gemini_prompt
description: "向 Gemini session 发送 prompt(多轮对话)"
method: POST
url: "http://<bridge-host>:9090/session/prompt"
body:
sessionId: string # 从 gemini_create_session 获取
prompt: string # 用户指令
returns: text, toolCalls, stopReason
name: gemini_close_session
description: "关闭 Gemini session,释放资源"
method: POST
url: "http://<bridge-host>:9090/session/close"
body:
sessionId: string
returns: ok
1. 调用 gemini_create_session,获取 sessionId
2. 调用 gemini_prompt(可多轮),每次传入同一个 sessionId
3. 任务完成后调用 gemini_close_session 释放资源
# 1. 创建 session
ID=$(curl -s -X POST http://localhost:9090/session/create \
-H 'Content-Type: application/json' \
-d '{"cwd": "/my/project"}' | jq -r '.sessionId')
# 2. 第一轮 prompt
curl -s -X POST http://localhost:9090/session/prompt \
-H 'Content-Type: application/json' \
-d "{\"sessionId\": \"$ID\", \"prompt\": \"分析 main.go 的代码结构\"}"
# 3. 第二轮 prompt(保持上下文)
curl -s -X POST http://localhost:9090/session/prompt \
-H 'Content-Type: application/json' \
-d "{\"sessionId\": \"$ID\", \"prompt\": \"针对你发现的问题给出优化建议\"}"
# 4. 关闭 session
curl -s -X POST http://localhost:9090/session/close \
-H 'Content-Type: application/json' \
-d "{\"sessionId\": \"$ID\"}"
| 症状 | 原因 | 解决方案 |
| ---------------------------------------------- | -------------------------------------- | --------------------------------------- |
| 启动时 ❌ Error: Gemini CLI binary not found | Gemini CLI 未安装或不在 PATH | 安装 CLI 或使用 --gemini-bin 指定路径 |
| ACP initialize failed | Gemini CLI 不支持 --experimental-acp | 升级到支持 ACP 的版本 |
| session not found | sessionId 错误或 session 已关闭 | 检查 sessionId 是否正确 |
| 权限请求被拒绝 | 未配置 permissionCallbackUrl | 创建 session 时传入回调 URL |
| prompt 请求超时 | Gemini agent 执行任务耗时较长 | 增大 HTTP client 超时时间 |
Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.
Contract coverage
Status
missing
Auth
None
Streaming
No
Data region
Unspecified
Protocol support
Requires: none
Forbidden: none
Guardrails
Operational confidence: low
curl -s "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/snapshot"
curl -s "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/contract"
curl -s "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/trust"
Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.
Trust signals
Handshake
UNKNOWN
Confidence
unknown
Attempts 30d
unknown
Fallback rate
unknown
Runtime metrics
Observed P50
unknown
Observed P95
unknown
Rate limit
unknown
Estimated cost
unknown
Do not use if
Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.
Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.
Rank
70
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Traction
No public download signal
Freshness
Updated 2d ago
Rank
70
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Traction
No public download signal
Freshness
Updated 6d ago
Rank
70
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
Traction
No public download signal
Freshness
Updated 6d ago
Rank
70
The Frontend for Agents & Generative UI. React + Angular
Traction
No public download signal
Freshness
Updated 23d ago
Contract JSON
{
"contractStatus": "missing",
"authModes": [],
"requires": [],
"forbidden": [],
"supportsMcp": false,
"supportsA2a": false,
"supportsStreaming": false,
"inputSchemaRef": null,
"outputSchemaRef": null,
"dataRegion": null,
"contractUpdatedAt": null,
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Invocation Guide
{
"preferredApi": {
"snapshotUrl": "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/snapshot",
"contractUrl": "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/contract",
"trustUrl": "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/trust"
},
"curlExamples": [
"curl -s \"https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/snapshot\"",
"curl -s \"https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/contract\"",
"curl -s \"https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/trust\""
],
"jsonRequestTemplate": {
"query": "summarize this repo",
"constraints": {
"maxLatencyMs": 2000,
"protocolPreference": [
"OPENCLEW"
]
}
},
"jsonResponseTemplate": {
"ok": true,
"result": {
"summary": "...",
"confidence": 0.9
},
"meta": {
"source": "GITHUB_OPENCLEW",
"generatedAt": "2026-04-17T03:12:44.565Z"
}
},
"retryPolicy": {
"maxAttempts": 3,
"backoffMs": [
500,
1500,
3500
],
"retryableConditions": [
"HTTP_429",
"HTTP_503",
"NETWORK_TIMEOUT"
]
}
}Trust JSON
{
"status": "unavailable",
"handshakeStatus": "UNKNOWN",
"verificationFreshnessHours": null,
"reputationScore": null,
"p95LatencyMs": null,
"successRate30d": null,
"fallbackRate": null,
"attempts30d": null,
"trustUpdatedAt": null,
"trustConfidence": "unknown",
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Capability Matrix
{
"rows": [
{
"key": "OPENCLEW",
"type": "protocol",
"support": "unknown",
"confidenceSource": "profile",
"notes": "Listed on profile"
}
],
"flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}Facts JSON
[
{
"factKey": "docs_crawl",
"category": "integration",
"label": "Crawlable docs",
"value": "6 indexed pages on the official domain",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
},
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Yuanshanxike",
"href": "https://github.com/yuanshanxike/dispatch-gemini-cli-skill",
"sourceUrl": "https://github.com/yuanshanxike/dispatch-gemini-cli-skill",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-02-25T01:46:34.478Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/contract",
"sourceUrl": "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-02-25T01:46:34.478Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/trust",
"sourceUrl": "https://xpersona.co/api/v1/agents/yuanshanxike-dispatch-gemini-cli-skill/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
]Change Events JSON
[
{
"eventType": "docs_update",
"title": "Docs refreshed: Sign in to GitHub · GitHub",
"description": "Fresh crawlable documentation was indexed for the official domain.",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
}
]Sponsored
Ads related to dispatch-gemini-cli-skill and adjacent AI workflows.