ClawHub

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· 97·1 current·1 all-time
by@ryan-wuxl
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the artifacts and actions in SKILL.md: interview the user, generate OpenClaw workspace files, propose guardrails and tests. It does not request unrelated credentials, binaries, or config paths.
✓
Instruction Scope
Runtime instructions are limited to asking clarifying questions, producing workspace files (IDENTITY.md, SOUL.md, AGENTS.md, etc.), and proposing tests/guardrails. It references only workspace files and explicitly warns not to store secrets; it does not instruct reading system-wide secrets or unrelated paths.
✓
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing is written to disk by an installer. Risk from installation is minimal.
✓
Credentials
No required environment variables, credentials, or config paths are declared. The SKILL.md operates with workspace files only and explicitly cautions against committing credentials.
✓
Persistence & Privilege
always is false and autonomous invocation is allowed (platform default). The skill does not request persistent privileges or modify other skills' configs.
Assessment
This skill appears coherent and low-risk: it only guides creation of OpenClaw workspace files and asks clarifying questions. Before using it, review any generated files (SOUL.md, AGENTS.md, HEARTBEAT.md, MEMORY.md) to ensure they don't accidentally include secrets or overly permissive autonomy rules. Be cautious about enabling heartbeats or granting the resulting agent additional runtime permissions (network access, credentials, external tool access) without reviewing those changes. If you plan to connect generated agents to external services, supply only the minimal scoped credentials and audit those integrations separately.

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

latestvk97d5fpdhmzva8k3kq7fywzja183dw3y

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments