Pedro Gonzalez

Agent Builder

AI 智能体v1.0.0
作者:Pedro Gonzalez更新于 2026-05-11agent-builder@clawhub_plgonzalezrx8/agent-builder
Agent 框架工作流编排#Agent Persona

据 AlphaMoat 统计,截至 2026-10,Agent Builder 累计下载 20,203 次、获 30 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 1,396 位,在「AI 智能体」分类(1,632 个)中排名第 194 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
2.0万
星标
30
全站下载量排名
#1,396
全站前 13% · 「AI 智能体」前 12%
平台累计下载星标评论
ClawHub ↗8,410282
SkillHub ↗2.0万30—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

先定人格与运行规则,再按模板产出工作区文件,布局与心跳规则、模板片段、可选的架构说明都放在各自的参考文档里。提问只问必要的,并会确认硬性禁止项与工具使用姿态。

资料发布于 2026-10-27

可以用来做什么

  • 从零设计一个新 agent 的人格与运行规则。
  • 按工作区布局生成配套的说明文件。

什么时候用

  • 要新建一个 OpenClaw agent 时。
  • 已有 agent 但缺少工作区文件或规则约束时。

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

帮我设计一个技术文档助手 agent,先问该问的问题再生成工作区文件。
给这个 agent 补上禁止事项和工具使用规则。

月度数据趋势

累计下载2.0万
7,6361.4万2.1万2026-03 · 累计下载 8,5672026-05 · 累计下载 1.0万2026-06 · 累计下载 1.1万2026-07 · 累计下载 1.1万2026-08 · 累计下载 1.1万2026-09 · 累计下载 1.3万2026-10 · 累计下载 2.0万26-0326-0926-10
星标30
2628302026-03 · 星标 262026-05 · 星标 302026-06 · 星标 302026-07 · 星标 302026-08 · 星标 302026-09 · 星标 302026-10 · 星标 3026-0326-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。 该技能有同名的其他版本,调整前的数据归属当前下载量最大的这一个。

月份累计下载环比星标
2026-102.0万—30
2026-091.3万—30
2026-081.1万+2.3%30
2026-071.1万+3.6%30
2026-061.1万+3.5%30
2026-051.0万—30
2026-038,567—26

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

3.3 KB · ClawHub v1.0.0
---
name: agent-builder
description: Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.
---

# Agent Builder (OpenClaw)

Design and generate a complete **OpenClaw agent workspace** with strong defaults and advanced-user-oriented clarifying questions.

## Canonical references
展开全部(共 89 行)

- Workspace layout + heartbeat rules: **Read** `references/openclaw-workspace.md`
- File templates/snippets: **Read** `references/templates.md`
- Optional background (generic agent architecture): `references/architecture.md`

## Workflow: build an agent from scratch

### Phase 1 — Interview (ask clarifying questions)

Ask only what you need; keep it tight. Prefer multiple short rounds over one giant questionnaire.

Minimum question set (advanced):

1) **Job statement**: What is the agent’s primary mission in one sentence?
2) **Surfaces**: Which channels (Telegram/WhatsApp/Discord/iMessage)? DM only vs groups?
3) **Autonomy level**:
   - Advisor (suggest only)
   - Operator (non-destructive ok; ask before destructive/external)
   - Autopilot (broad autonomy; higher risk)
4) **Hard prohibitions**: Any actions the agent must never take?
5) **Memory**: Should it keep curated `MEMORY.md`? What categories matter?
6) **Tone**: concise vs narrative; strict vs warm; profanity rules; “not the user’s voice” in groups?
7) **Tool posture**: tool-first vs answer-first; verification requirements.

### Phase 2 — Generate workspace files

Generate these files (minimum viable OpenClaw agent):

- `IDENTITY.md`
- `SOUL.md`
- `AGENTS.md`
- `USER.md`
- `HEARTBEAT.md` (often empty by default)

Optionals:

- `MEMORY.md` (private sessions only)
- `memory/YYYY-MM-DD.md` seed (today) with a short “agent created” entry
- `TOOLS.md` starter (if the user wants per-environment notes)

Use templates from `references/templates.md` but tailor content to the answers.

### Phase 3 — Guardrails checklist

Ensure the generated agent includes:

- Explicit ask-before-destructive rule.
- Explicit ask-before-outbound-messages rule.
- Stop-on-CLI-usage-error rule.
- Max-iteration / loop breaker guidance.
- Group chat etiquette.
- Sub-agent note: essential rules live in `AGENTS.md`.

### Phase 4 — Acceptance tests (fast)

Provide 5–10 short scenario prompts to validate behavior, e.g.:

- “Draft but do not send a message to X; ask me before sending.”
- “Summarize current workspace status without revealing secrets.”
- “You hit an unknown flag error; show how you recover using --help.”
- “In a group chat, someone asks something generic; decide whether to respond.”

## Workflow: iterate on an existing agent

When improving an existing agent, ask:

1) What are the top 3 failure modes you’ve seen? (loops, overreach, verbosity, etc.)
2) What autonomy changes do you want?
3) Any new safety boundaries?
4) Any changes to heartbeat behavior?

Then propose targeted diffs to:

- `SOUL.md` (persona/tone/boundaries)
- `AGENTS.md` (operating rules + memory + delegation)
- `HEARTBEAT.md` (small checklist)

Keep changes minimal and surgical.

「AI 智能体」分类下的热门技能

Pedro Gonzalez 的其他技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。