Skill shell that installs, runs and troubleshoots React-Monitor-Agent, a human-agent operation board built on review replay and checkpoints: the agent writes its work as a structured replay timeline of screen-recording, screenshot, diff and text nodes, and the human decides at plan, progress, risk and delivery checkpoints, with verdicts branching the timeline and rejected branches kept greyed-out for audit. The skill guides cloning the source repo and starting a zero-dependency Node event service on 127.0.0.1:8790 plus a React board on localhost:5173 that ships an offline FIXTURE demo mode. The bundle embeds the skill only; product source stays in the repo.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:Lumos-789/react-monitor-agent
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
人机协作的正确单位不是「对话」,是审查回放 + 检查点。
回应 DeepSeek《Exploring Super-agent Design》(2026-10-31,dsh-superagent-prototype)之问:基于 session 聊天窗口的设计,是路径依赖。
演示视频: B 站《DeepSeek 问:agent 为什么只有聊天窗?我做了个操作板》
三个概念
- 操作板 Operation Board — 只承载两类一等目标:
- Context Track 上下文建设(非业务产出:知识、规则、流程定义)
- Work Track 业务执行(coding 及一切真业务)
- 审查回放 Review Replay — agent 工作过程的结构化时间线叙事(录屏/截图/diff/文本混合节点),随时回放,不再实时盯滚动流。
- 检查点 Checkpoint — 回放中等人决策的关键帧,类型决定按钮子集:
| 检查点 | 触发 | 动作 |
|---|---|---|
| 方案 Plan | 方案/选型待拍板 | 批准 / 否定 / 改向 / 补充 |
| 阶段 Progress | 里程碑成果 | 批准 / 改向 / 补充 |
| 风险 Risk | agent 自报拿不准 | 批准 / 否定 / 补充 |
| 完工 Delivery | 交付物最终审查 | 完工 / 否定 / 补充 |
检查点模板保底 + agent 可加;否定/改向后旧分支灰掉保留(审计完整)。
与 dsh-superagent 的关系
dsh 管 agent 侧的自律(准入/授权/自治边界,panel 是工单列表);rma 管人侧的审查带宽(叙事回放,交互富而深)。互补不互斥——dsh 让 agent 少打扰人,rma 让人被打扰时看得快、答得快。
快速开始
# rma-core:零依赖 Node 服务(端口 8790,事件存 ~/.rma/)
cd core && npm install && npm run dev
# rma-board:Web 操作板(端口 5173)
cd app && npm install && npm run dev
# 验证(改动后自检):core 测试全绿,app 类型检查+构建通过
cd core && npm test
cd app && npm run build
打开 http://localhost:5173 即见操作板。前端默认 FIXTURE 演示模式(离线可跑,内置三工程:二维码名片生成器/竞品调研报告/superagent docs 蒸馏),回放中的检查点决策可真实点击——你的选择会改变时间线走向;要连真 core 时 VITE_RMA_MODE=live npm run dev。
插件安装
本仓同时是 skill 壳型插件仓(不内嵌产品源码,引导 agent 克隆本仓并按「快速开始」跑起服务):
- DSH: 仓根即 bundle——
package.json声明dsh.bundle(patch 指向cordis.patch.yml),index.js以 bundledSkillDir 挂载skills/react-monitor-agent/。 - ZCode:
.zcode-plugin/plugin.json(目前仅挂本地 dev marketplace 验证,未对外发布)。 - 两条渠道都只是安装/配置/排障入口;产品本体始终是
core/+app/,直接克隆即可用。
结构
core/ rma-core — 事件库(JSONL append-only)+ 检查点引擎 + localhost API
app/ rma-board — React 操作板 + 审查回放 + 完工态三屏
demo-projects/ 演示工程事件流
状态
- 2026-10-31 立项;11-01 全链可用:core 测试全绿,三屏 UI + 决策回注全链路(curl 实证)。
- 2026-11-03 插件化:DSH bundle(仓根三件套+skill 壳)+ ZCode 插件形态,本地 dev marketplace 装用验证通过。
- 路线图:DSH bundle 原生适配器(agent 进程内插件,自动事件采集)。
License
MIT
Links
More in this category
zhu1090093659/dsh-web#packages/dsh-skill-explorer★ 9959
Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.
iflytek/skillhub#dsh★ 5358
Browse and search a SkillHub registry and manage local skill installation, updates, and removal inside DeepSeek Harness. Targets DSH 0.2.0-rc.2 and 0.2.1-rc.2; not yet compatible with 0.2.1-rc.3.
QingYunA/answer-me-with-html★ 5085
Answers a question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled `am` CLI builds the page, with flow, sequence, tree, timeline and ER diagrams, tables and callouts.
hyhmrright/brooks-lint★ 1556
Provides six code quality skills for code review, architecture audits, technical debt, test quality, health dashboards, and remediation.
GanyuanRan/Aegis★ 1411
Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.
superdesigndev/superdesign-skill★ 935
Design skill for UI and marketing graphics on the Superdesign canvas: reads the repo for context, extracts its design system, then generates and iterates branchable design drafts, flow pages, and reusable components through the Superdesign CLI.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.