Dsh Ops Agent

Community

01men

dsh-ops-agent

管理数字员工的登记、授权、上下线和运行指标。

Overview

Publisher	01men
Repository	`ybkkasi`
Skill name	`dsh-ops-agent`
Stars	62
Forks	0
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by 01men on GitHub. Read the source before you install it.

Installation

Install the Dsh Ops Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/01men/ybkkasi/tree/main/skills/dsh-ops-agent
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/01men/ybkkasi.git /tmp/ybkkasi
mkdir -p .claude/skills
cp -r /tmp/ybkkasi/skills/dsh-ops-agent .claude/skills/dsh-ops-agent

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dsh Ops Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dsh Ops Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dsh Ops Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill: dsh-ops-agent

何时使用

Agent 注册与属性登记、用户绑定、试运行/上线/下线生命周期（L4 审批）、运行监测与异常排查。

调用方式（工具优先）

平台已把运维能力注册为 dsh 工具，回答现状问题（查询/盘点/排障）必须直接调用工具获取真实数据，禁止凭记忆回答：

agent_list / agent_get / agent_metrics / agent_metrics_report / agent_offline / agent_bind_user （工具参数见各工具 schema；下文手册中的 dshctl ... 为「平台独立部署 + HTTP API 运维」场景的 CLI 备选，需 DSHCTL_TOKEN/DSHCTL_USER，在 dsh 会话内一般用不到。）

前置条件

agent.write / agent.approve 权限；上线审批需第二管理员配合。

操作手册

场景 1：下线异常 Agent（标准闭环）

dshctl agent metrics <id> → 确认异常（成功率骤降/调用突增）
dshctl audit logs --resourceId=<id> → 回溯最近变更
影响面预览：GET /api/agents/ 的 impact 字段
dshctl agent offline <id> --reason="<原因>" --requesterId=<发起人> --requesterName=<姓名> → 生成 L4 审批单
第二管理员：dshctl approval decide <审批id> --decision=approve --opinion=<意见>
验证：dshctl agent get <id>（状态 offline、机器凭证禁用、绑定用户已通知）

场景 2：注册新 Agent

dshctl agent create --name=<名称> --model=deepseek-chat --riskLevel=low → 返回机器凭证（仅一次；scopes 含 mcp.invoke/skill.read/agent.read/agent.write/usage.write，Agent 可自推直连消耗的计量）。补全 dataClass 后方可上线。运营数据提报是接入义务（与 AI 应用同级）：Agent 必须每日 POST /api/agents//metrics-report （dau/sessions/uniqueUsers，明细可传 userIds 平台侧哈希脱敏），并 PATCH attrs.entryUrl 提报交互界面地址。凭证 secret 丢失/泄露：找管理员执行 dshctl credential rotate <principalId> 轮换（clientId 不变、旧值立即失效），无需重新注册。

场景 3：上线流程

确认治理属性齐备（否则接口会给出具体缺失项）
试运行：dshctl agent ... transition submit_trial（限定用户组）
上线：POST /api/agents//transition {action:"online"} → 审批单 → 单人审批通过

护栏

offline 必须给 reason；上线/下线均为 L4 审批
下线联动：吊销机器凭证 + 通知绑定用户 + 保留审计数据
调用频次突增（10 分钟 >120 次）会自动触发行为告警

Frequently asked questions

What does the Dsh Ops Agent AI skill do?

管理数字员工的登记、授权、上下线和运行指标。

Why use Dsh Ops Agent on TypingMind?

Because you install it once and use it with any model. Dsh Ops Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dsh Ops Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/01men/ybkkasi/tree/main/skills/dsh-ops-agent. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dsh Ops Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dsh Ops Agent?

As many as you like. As long as a model supports skills, you can use Dsh Ops Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dsh Ops Agent AI skill free?

Yes. It is published on GitHub by 01men under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Ci Metrics

pytorch

OrganizationPopular

Query PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics. Use when users ask about CI duration, job failures, queue times, workflow trends, runner health, dashboard data, or PyTorch…

Notcrawl

Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.

Openclaw Test Heap Leaks

openclaw

OrganizationPopular

Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

Prototype Openclaw Tui

openclaw

OrganizationPopular

Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Skill: dsh-ops-agent

何时使用

调用方式（工具优先）

前置条件

操作手册

场景 1：下线异常 Agent（标准闭环）

场景 2：注册新 Agent

场景 3：上线流程

护栏

Frequently asked questions

Related AI Skills

Set up your own AI workspace now