agent-builder

v1.0.0

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 work...

⭐ 0· 84·0 current·0 all-time

by@marjoriebroad

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for marjoriebroad/agent-builder1.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "agent-builder" (marjoriebroad/agent-builder1) from ClawHub.
Skill page: https://clawhub.ai/marjoriebroad/agent-builder1
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install agent-builder1

ClawHub CLI

Package manager switcher

npx clawhub@latest install agent-builder1

Security Scan

VirusTotal

Benign

View report →

OpenClaw

Benign

high confidence

✓

Purpose & Capability

The name/description (agent-builder) match the SKILL.md: it guides an interview, produces workspace files (IDENTITY.md, SOUL.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md, memory/YYYY-MM-DD.md), and proposes tests and guardrails. No unrelated binaries, env vars, or external services are requested.

ℹ

Instruction Scope

Instructions are mostly scoped to building and iterating an OpenClaw agent workspace and listing local reference files to 'Read' (references/openclaw-workspace.md, references/templates.md, references/architecture.md). Because this is an instruction-only skill, it will direct the agent to create workspace files (including optional memory/seed entries). That is coherent with purpose, but be aware it expects to read/write workspace files and may create memory files where users might accidentally store secrets if not careful. The referenced 'references/' files are not included in the manifest, so the agent may ask the user for those or proceed without them.

✓

Install Mechanism

No install spec and no code files — lowest-risk deployment model. Nothing will be downloaded or written by an installer.

✓

Credentials

The skill declares no required environment variables, credentials, or config paths. It does not ask for unrelated secrets or cloud credentials, so requested access is proportionate.

✓

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent platform presence or modify other skills. Its expected behavior is to read/write workspace files it generates — normal for this purpose.

Assessment

This skill is coherent and low-risk in itself, but review generated files before using them. Practical precautions: do not put secrets or credentials into MEMORY.md or other generated files; verify any 'references/' files the skill reads are trustworthy; confirm the agent's autonomy level and outbound-message/ask-before-destructive guardrails before activating the agent in live channels; and run the first iteration in a sandboxed workspace to inspect outputs.

Like a lobster shell, security has layers — review code before you run it.

latestvk97f376ynp5b28252nfea3szt584scs1

84downloads

0stars

1versions

Updated 2w ago

v1.0.0

MIT-0

Agent Builder (OpenClaw)

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

Canonical references

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):

Job statement: What is the agent's primary mission in one sentence?
Surfaces: Which channels (Telegram/WhatsApp/Discord/iMessage)? DM only vs groups?
Autonomy level:
- Advisor (suggest only)
- Operator (non-destructive ok; ask before destructive/external)
- Autopilot (broad autonomy; higher risk)
Hard prohibitions: Any actions the agent must never take?
Memory: Should it keep curated MEMORY.md? What categories matter?
Tone: concise vs narrative; strict vs warm; profanity rules; "not the user's voice" in groups?
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:

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