Token导航 LogoToken导航TokenDH.com
研究检索external-serviceclawhub未标认证来源可访问clear审计提醒

orgxorgx 搜索

Agent Skill

orgx 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,840

周安装

122

GitHub Stars

公开资料未说明

下载量

996
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:orgx(orgx 搜索)
来源仓库:https://github.com/hopeatina/orgx
安装命令:
openclaw skills install orgx
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install orgx

简介

orgx 集成 OrgX 管理系统用于进度汇报决策请求与工件注册流程。

  • 支持内存同步质量关卡检查等高级协作功能调用。orgx 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 要求使用者已加入对应 OrgX 实例并获得操作权限。
  • 部分命令可能触发审批流程需等待人工确认才能继续。
  • 错误操作可能导致任务状态异常请及时回滚恢复现场。

SKILL.md

name
orgx
description
Use when managing work with OrgX — reporting progress, requesting decisions, registering artifacts, syncing memory, checking quality gates, or viewing org status. Activates for phrases like "report progress", "request approval", "create initiative", "check orgx", "sync with orgx", "register artifact".
version
2.1.0
user-invocable
true
tags

OrgX Integration

Connect to OrgX for multi-agent orchestration, decision workflows, initiative tracking, model routing, quality gates, and structured work reporting.

Quick Start

# Install the plugin
openclaw plugins install @useorgx/openclaw-plugin

# Or via npx
npx @useorgx/openclaw-plugin

After installing, pair with OrgX via the live dashboard at http://127.0.0.1:18789/orgx/live or set ORGX_API_KEY in your environment.

MCP Tools Reference

Work Reporting (use these regularly)

orgx_report_progress — Report what you've accomplished.

orgx_report_progress({
  summary: "Fixed the authentication bug and added tests",
  phase: "testing",           // researching | implementing | testing | reviewing | blocked
  progress_pct: 75,           // 0-100 (optional)
  next_step: "Run full CI suite"  // (optional)
})

orgx_request_decision — Ask the user to decide something before continuing.

orgx_request_decision({
  question: "Deploy to production now or wait for load testing?",
  context: "All unit tests pass. Load testing would take ~2 hours.",
  options: ["Deploy now", "Wait for load testing", "Deploy to staging first"],
  urgency: "medium",          // low | medium | high | urgent
  blocking: true              // pause work until decided (default: true)
})

orgx_register_artifact — Register a deliverable (PR, document, config, etc.).

orgx_register_artifact({
  name: "PR #107: Fix Vercel build size",
  artifact_type: "pr",        // pr | commit | document | config | report | design | other
  description: "Reduced function size by pruning recursive assets",
  url: "https://github.com/org/repo/pull/107"  // (optional)
})

Org Status & Sync

orgx_status — View active initiatives, agent states, pending decisions, tasks.

orgx_sync — Push local memory/daily log to OrgX, receive org context back.

orgx_sync({
  memory: "Contents of MEMORY.md",
  dailyLog: "Today's session summary"
})

Quality & Spawning

orgx_spawn_check — Check quality gate + get model routing before spawning a sub-agent.

orgx_spawn_check({ domain: "engineering", taskId: "..." })
// Returns: { allowed: true, modelTier: "sonnet", checks: {...} }

orgx_quality_score — Record quality score (1-5) for completed work.

orgx_quality_score({
  taskId: "...",
  domain: "engineering",
  score: 4,
  notes: "Clean implementation, good test coverage"
})

Entity Management

orgx_create_entity — Create an initiative, workstream, task, decision, milestone, artifact, or blocker.

orgx_update_entity — Update status/fields on any entity.

orgx_list_entities — Query entities by type and status.

Run Control

orgx_delegation_preflight — Score scope quality and estimate ETA/cost before execution.

orgx_run_action — Pause, resume, cancel, or rollback a run.

orgx_checkpoints_list / orgx_checkpoint_restore — List and restore run checkpoints.

Reporting Protocol

When working on a task or initiative, report your progress to OrgX at key moments. This keeps the dashboard accurate and helps the team track your work.

On task start

Call orgx_report_progress with phase: "researching" or "implementing" and a brief summary of what you're about to do.

At meaningful progress points

Call orgx_report_progress at natural checkpoints: after finishing research, after a first implementation pass, after tests pass, etc. Include progress_pct when you can estimate it.

When you need a human decision

Call orgx_request_decision with a clear question, context, and options. Set blocking: true if you should wait for the answer before continuing. Set urgency appropriately:

  • low — Can wait hours/days
  • medium — Should be decided today
  • high — Blocking progress, needs attention soon
  • urgent — Critical path, needs immediate attention

When you produce a deliverable

Call orgx_register_artifact for anything the team should see: PRs, documents, config changes, reports, design files. Include a URL when available.

On task completion

  1. Call orgx_report_progress with phase: "reviewing" and progress_pct: 100
  2. Call orgx_quality_score to self-assess your work (1-5 scale)
  3. Call orgx_update_entity to mark the task as completed

On blockers

Call orgx_report_progress with phase: "blocked" and describe the blocker in the summary. If you need human help, also call orgx_request_decision.

Model Routing

OrgX classifies tasks for model selection:

Task TypeTierModel
Architecture, strategy, decisions, RFCsopusanthropic/claude-opus-4-6
Implementation, code, features, docssonnetanthropic/claude-sonnet-4
Status checks, formatting, templateslocalollama/qwen2.5-coder:32b

Always call orgx_spawn_check before spawning sub-agents to get the right model tier.

Live Dashboard

The plugin serves a live dashboard at http://127.0.0.1:18789/orgx/live showing:

  • Activity Timeline — Real-time feed of agent work with threaded session views
  • Agents/Chats — Active sessions grouped by agent
  • Decisions — Pending approvals with inline approve/reject
  • Initiatives — Active workstreams and progress

Entity API

For direct API access:

GET  /api/entities?type={type}&status={status}&limit={n}
POST /api/entities
PATCH /api/entities
POST /api/entities/{type}/{id}/{action}

Entity types: initiative, workstream, task, decision, milestone, artifact, agent, blocker

MCP Server (mcp.useorgx.com)

For environments that support MCP servers directly (Claude Desktop, Cursor, etc.), connect to mcp.useorgx.com for the full suite of 26+ OrgX tools including initiative management, decision workflows, and agent orchestration.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

94.77%
按下载量换算944

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills