Meta-Skill Orchestration Surface

The meta-skill that knows its own activation surface. Use this skill whenever the user wants to "activate" a capability, asks "what can you do", wants to cha...

This skill appears to be what it says: a router/orchestrator that reads its included activation map and proposes/executes skill chains. Before installing or enabling it, consider: (1) confirm that the agent will always present proposed chains and request explicit user approval before executing steps that access external services; (2) review downstream skills (skill-creator, mcp-builder, connectors) for any credential or network requirements they will request if invoked; (3) be cautious about allowing automatic publication or deployment steps (Cloudflare, Vercel, marketplace bridges) — those require platform credentials and may publish content or code; and (4) periodically audit the activation-map contents so any referenced external endpoints or packaged tools are still trustworthy. If you want stronger guarantees, require that the activator never autonomously invokes build/deploy skills without an extra confirmation step.

Type: OpenClaw Skill Name: reson8-activator Version: 1.0.0 The bundle describes a high-privilege 'meta-orchestrator' designed to manage an extensive inventory of tools across Cloudflare, Google Workspace, and browser automation environments. Key indicators of risk include instructions for the agent to 'Extend' its own surface by generating new code/plugins via 'skill-creator' and 'mcp-builder', and the orchestration of high-risk tools like 'javascript_tool', 'computer' access, and 'read_network_requests' (found in activation-map.md). While the framework is presented as a 'Tapestry of Skills' for orchestration, the ability to bridge sensitive data across substrates (e.g., Cloudflare, Crypto Exchanges, and Google Drive) and 'teach' other agents how to invoke these tools creates a massive attack surface for lateral movement or data exfiltration if the agent is compromised via prompt injection.