MateClaw is a pluggable agent runtime that coordinates AI agents, tools, conversations, memory, and workflows. It is designed for personal and multi-user AI assistants, including agents used through chat platforms. Catalogue add-ons provide skills for extending its agent workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mateaix/mateclaw --skill digital_employeegit clone --depth 1 https://github.com/mateaix/mateclawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mateaix/mateclaw/digital_employee)<a href="https://agentmods.dev/skills/mateaix/mateclaw/digital_employee"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/digital_employee.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 6 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01369 |
| Opus 5 | $0.00020 | $0.00685 |
| Sonnet 5 | $0.00008 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
digital_employee scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数字员工组建
把一句业务需求,变成「一支分工明确的数字员工团队 + 一条把他们串起来的工作流」。用户不必逐个设计、逐个手工创建 Agent。
何时使用
- 用户描述了一个需要多个角色协作的目标("帮我搭一个做竞品分析的团队"、"我要一套从线索到成交的销售流程")。
- 用户说"建几个 Agent / 数字员工帮我做 X"、"把 X 这件事自动化成一支团队"。
- 现有 Agent 不足以覆盖需求,需要新建专才角色。
不应使用
- 一个 Agent 就能完成 → 直接用
chat_with_agent或现有 Agent。 - 只是想编排已存在的 Agent 协作 → 用
multi_agent_collaboration。 - 只是想把流程做成工作流,且员工都已存在 → 直接用
workflow_draft_generate。
工作流程
第一步:理解需求,盘点现状
- 读懂用户的业务目标、产出物、是否有触发条件(定时 / 来消息时)、要不要审批、结果发到哪个渠道。
- 调用
listAvailableAgents()看现有员工——能复用就复用,不要重复造同名角色。 - 调用
list_capability_catalog()拿到可分配的技能名和工具名清单。后续create_employee只能用清单里的真实名字,不要臆造。
如果需求关键信息缺失(产出物、角色边界),先向用户澄清一句再继续,不要凭空假设。
第二步:设计团队(2–6 个角色)
把目标拆成互补的角色,每个角色给出:
name:工作区内唯一,用英文 kebab-case(如market-research-analyst)。description:一句话职责,工作流编排器会据此分配任务。systemPrompt:定义这个员工的专长、视角、工作方式——要具体,别写空话。skillNames/toolNames:从list_capability_catalog()里挑这个角色真正需要的;留空则继承全局默认能力(通才)。专才角色建议显式收窄。agentType:默认react;只有当角色需要"先规划再分步执行"时才用plan_execute。
设计原则:
- 角色数量 2–6 个,宁少勿滥;每个角色职责单一、边界清晰。
- 避免两个角色职责重叠。
- 一般不指定
modelName,留空用工作区默认模型;用户明确要求某模型时才填。
第三步:逐个创建员工
对每个设计好的角色调用一次 create_employee(...):
create_employee(
name="market-research-analyst",
description="负责竞品功能、定价、市场动态的检索与结构化整理",
systemPrompt="你是资深市场研究分析师……(写清专长与产出格式)",
skillNames=["news", "web_search"], // 来自 list_capability_catalog,可留空
toolNames=["web_search"] // 来自 list_capability_catalog,可留空
)
- 工具会返回
agentId和实际绑定的技能/工具;记下每个员工的 name,下一步要用。 - 若返回
[error](如重名),换个名字重试,不要中断整个流程。 - 创建即启用——员工立刻可被工作流引用。
第四步:编排工作流
所有员工创建完成后,调用一次 workflow_draft_generate(description=...)。在 description 里:
- 点名第三步创建的真实员工(用它们的 name),说明执行顺序、依赖关系、并行还是串行。
- 写清触发条件、是否需要审批、产出发往哪个渠道。
由于员工已经落库,workflow_draft_generate 会读到它们作为可用数字员工,直接引用真实 agent,而不是填 TODO_*_AGENT 占位。
工作流只会保存为草稿,不会自动发布、不会自动启用触发器。这是安全约定——让用户在工作流编辑器里 review 后再 publish。
第五步:汇报
给用户一份清晰小结:
- 创建了哪些员工(name + 职责 + 绑定的关键能力)。
- 生成的工作流草稿名称、id、各步骤如何串联。
- 草稿编译预校验是否通过、有无缺失字段需要补。
- 明确告知:工作流是草稿,请到工作流编辑器确认后再发布。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 104 lines · 41 tokens per session scan A d2859b75dd4b
digital_employee is a skill published in the GitHub repository mateaix/mateclaw (1,083 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,369 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
app
A skill-management module for storing, organising, sharing, and managing reusable skills, including their descriptions, content, tags, and files.
openclaw-security-checker
A security checker for OpenClaw installations, including their configuration, permissions, containers, network access, and logs.
pentest-whitebox-code-review
Source code security audit using backward taint analysis, slot type classification, render context verification, and 3-phase parallel review producing an exploitation queue.
pentest-api-deep
Deep OWASP API Security Top 10 testing for REST, GraphQL, gRPC, and WebSocket APIs — BFLA, mass assignment, rate limiting, and unsafe consumption.
pentest-business-logic
Business logic vulnerability testing — workflow bypass, payment manipulation, state machine abuse, and function limit circumvention per WSTG-BUSL.
seclens-enterprise-web
Professional web application and API security testing workflows using OWASP Top 10 methodologies.