Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

agent-builder

bởi plgonzalezrx8

Clawdbot Tools
4.9kLượt tải do clawskills.sh công bố
22Sao
1Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Build high-performing OpenClaw agents end-to-end.

Mô tả

Kỹ năng này làm gì

Guides you through designing an OpenClaw agent from scratch or refining an existing one. Runs a structured interview, then generates the full set of workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, and optionally MEMORY.md). Also covers guardrails, autonomy model, and acceptance tests.

Covers the full agent design lifecycle in one place, so you don't have to manually track which workspace files are required or remember what guardrails to include.

Khi nào nên dùng

  • Setting up a new personal assistant agent with custom tone and memory
  • Adding hard safety limits to an agent that keeps overreaching
  • Defining group chat etiquette rules for a shared bot
  • Iterating on an agent's autonomy level after observing failure modes
  • Generating acceptance test prompts before deploying an agent

Quy trình ví dụ

ĐẦU VÀO

User asks: Build me a Telegram assistant agent that summarizes daily news and asks before sending anything

AGENT
  1. 1

    Ask clarifying questions: job statement, channels, autonomy level, hard prohibitions, memory needs, and tone

  2. 2

    Generate IDENTITY.md, SOUL.md, AGENTS.md, USER.md, and HEARTBEAT.md from templates tailored to the answers

  3. 3

    Apply guardrails checklist: ask-before-send rule, loop breaker, stop-on-error rule

  4. 4

    Provide 5-10 acceptance test prompts to validate agent behavior

ĐẦU RA

Complete OpenClaw workspace with all required files and a test suite ready for deployment

Cài đặt

clawhub install plgonzalezrx8/agent-builder

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết