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· 47·0 current·0 all-time
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
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.
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

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments