{"id":18652,"plugin_id":"plugins_6a8874a5fe5081919d0e22dacb040180","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:14:52.753Z","digest":"fa332fc4d0151e20ad627cd69e3cba58bbedad6c9f05c0764439908f09041d67","against":null,"payload":{"description":"Specify reliable autonomous or semi-autonomous AI agents with objectives, tools, permissions, state, memory, handoffs, approvals, retries, observability, evaluation, and safe failure. Use for agent architecture, multi-agent workflows, AI employees, tool-using assistants, or converting a process into an agent specification.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":220}],"name":"design-ai-agents","skill_md_contents":"---\nname: design-ai-agents\ndescription: Specify reliable autonomous or semi-autonomous AI agents with objectives, tools, permissions, state, memory, handoffs, approvals, retries, observability, evaluation, and safe failure. Use for agent architecture, multi-agent workflows, AI employees, tool-using assistants, or converting a process into an agent specification.\n---\n# Design AI Agents\n1. Define observable objective, environment, inputs, outputs, authority, risk, and definition of done.\n2. Separate reasoning/workflow from external capabilities; never assume unavailable tools or data.\n3. Route the smallest useful expert group with one lead, necessary support, and an independent reviewer using the shared [expert routing model](../../shared/expert-system/expert-routing-model.md). Multi-agent does not mean maximum agent count.\n4. Give every specialist an explicit role contract, decision classes, required evidence, handoff, evaluation, and stop conditions. Use the shared [decision-authority model](../../shared/expert-system/decision-authority-model.md); escalate controlled-source conflicts and Class-1 decisions.\n5. Specify state machine, source of truth, memory retention, tool contracts, permissions, approval gates, retries, timeouts, idempotency, and recovery.\n6. Define dynamic specialist activation, task-specific expert snapshots, independent reviewer agents, handoffs, logs, cost/latency limits, privacy, injection resistance, and human escalation.\n7. Build role-specific and system-level evaluation cases for normal, empty, conflicting, adversarial, stale, and tool-failure conditions.\n8. Return architecture, agent and role contracts, routing matrix, state diagram in text, tool matrix, policies, eval suite, rollout plan, and residual risks.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}