Professional Agent Forge
v1.0.0Build a complete OpenClaw agent package for a real profession or job role. Use when the user asks for things like "create a product manager agent", "make me...
⭐ 0· 69·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description align with requested artifacts (soul.md, identity.md, memory.md, agents.md, tools.md). The included reference files correspond to the professions named. No unrelated binaries, env vars, or external credentials are requested.
Instruction Scope
SKILL.md instructs the agent to read internal reference files when available and to use a generic framework otherwise. It does not direct reading system files, environment variables, or sending data to external endpoints beyond recommending tool integrations. The instructions are focused and bounded to creating agent packages.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written by an installer, so there is minimal disk execution risk from the skill itself.
Credentials
Requires no environment variables, credentials, or config paths. The skill suggests MCP/tool integrations in its outputs (e.g., notion-mcp, docusign-mcp) but does not request those credentials itself; those would be configured separately if a user adopts the recommended toolchain.
Persistence & Privilege
Flags show default autonomy (disable-model-invocation=false) and always=false. The skill does not request forced always-on presence or attempt to modify other skills or system-wide settings.
Assessment
This skill appears internally consistent and low-risk from a configuration/installation standpoint: it only uses bundled reference files and produces text artifacts. Before using it in production, keep two practical safety steps in mind: (1) For regulated domains (legal, medical, financial), have a qualified human review any outputs and include explicit disclaimers — the skill's lawyer reference itself recommends not replacing a licensed practitioner. (2) When you wire up the recommended MCPs or external tools (Notion, DocuSign, analytics, etc.), grant only the minimum credentials needed and review those integrations separately — the skill does not request credentials itself. If you want to limit risk further, avoid enabling autonomous invocation for this skill in sensitive environments or require human approval before agent package deployment.Like a lobster shell, security has layers — review code before you run it.
latestvk97a38gjjwrmktc7f22mb1v3d183hpnz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.