Pedro Gonzalez

Agent Builder

AI 智慧體v1.0.0
作者:Pedro Gonzalez更新於 2026-05-11agent-builder@clawhub_plgonzalezrx8/agent-builder
Agent 框架工作流編排#Agent Persona

據 AlphaMoat 統計,截至 2026-10,Agent Builder 累計下載 20,203 次、獲 30 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 1,396 位,在「AI 智慧體」分類(1,632 個)中排名第 194 位。

列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。

累計下載
2萬
星標
30
全站下載量排名
#1,396
全站前 13% · 「AI 智慧體」前 12%
平台累計下載星標評論
ClawHub ↗8410282
SkillHub ↗2萬30—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

先定人格與執行規則,再按模板產出工作區檔案,佈局與心跳規則、模板片段、可選的架構說明都放在各自的參考文件裡。提問只問必要的,並會確認硬性禁止項與工具使用姿態。

資料釋出於 2026-10-27

可以用來做什麼

  • 從零設計一個新 agent 的人格與執行規則。
  • 按工作區佈局生成配套的說明檔案。

什麼時候用

  • 要新建一個 OpenClaw agent 時。
  • 已有 agent 但缺少工作區檔案或規則約束時。

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

幫我設計一個技術文件助手 agent,先問該問的問題再生成工作區檔案。
給這個 agent 補上禁止事項和工具使用規則。

月度資料趨勢

累計下載2萬
76361.4萬2.1萬2026-03 · 累計下載 85672026-05 · 累計下載 1萬2026-06 · 累計下載 1.1萬2026-07 · 累計下載 1.1萬2026-08 · 累計下載 1.1萬2026-09 · 累計下載 1.3萬2026-10 · 累計下載 2萬26-0326-0926-10
星標30
2628302026-03 · 星標 262026-05 · 星標 302026-06 · 星標 302026-07 · 星標 302026-08 · 星標 302026-09 · 星標 302026-10 · 星標 3026-0326-0926-10

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。 該技能有同名的其他版本,調整前的資料歸屬當前下載量最大的這一個。

月份累計下載環比星標
2026-102萬—30
2026-091.3萬—30
2026-081.1萬+2.3%30
2026-071.1萬+3.6%30
2026-061.1萬+3.5%30
2026-051萬—30
2026-038567—26

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 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
展開全部(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 智慧體」分類下的熱門技能

Pedro Gonzalez 的其他技能

資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。