菜单
Designs production-grade AI agent experiences. Use for PRDs, user journeys, interaction models, trust and approval UX, failure handling, provenance, and measurable acceptance criteria for agentic products.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | agentic-product-designer-2026 |
| description | Designs production-grade AI agent experiences. Use for PRDs, user journeys, interaction models, trust and approval UX, failure handling, provenance, and measurable acceptance criteria for agentic products. |
| argument-hint | [feature or workflow] |
| allowed-tools | Read Write Edit Grep Glob |
Design agentic user experiences as state machines with trust, not as chat transcripts with decoration.
The user must always be able to answer:
Invisible autonomy creates fear and error. Show plan, progress, and receipts.
Users must be able to:
Separate:
Do not only design the happy path. Failure, ambiguity, and handoff need explicit UX.
The UX includes:
State:
At minimum produce:
For each journey, specify:
Minimum UI states:
idledraftingplanningwaiting_for_user_inputexecutingwaiting_for_approvalretryingcompletedfailed-recoverablefailed-terminalFor each state, specify:
Every agentic UI should expose:
Approval requests must include:
Never present an approval CTA without consequences and scope.
For every important answer or action, make clear:
For failures, specify:
Track:
Return a PRD with:
Avoid:
Return:
This skill is done only when:
Orchestrates production-grade LLM-driven agent systems in 2026. Use for agent architecture, control loops, topology choice, tool contracts, memory, approvals, safety boundaries, evals, and observability.
Plans and specifies production-grade agent systems. Use when scoping work, writing implementation plans, defining state and tool contracts, sequencing milestones, and producing clear done criteria for LLM-driven systems.
Engineers backend systems for LLM-driven agents. Use when designing APIs, orchestrators, tool runtimes, persistence, jobs, auth, retrieval and memory services, approvals, budgets, and reliability controls.
Database engineering skill for agentic systems. Use for schema design, migrations, query correctness, performance, transactions, multi-tenant boundaries, privacy, backups/rollback, and safe DB operations.
Establishes reliability, safety, and release readiness for LLM-driven agents. Use for eval suites, adversarial testing, observability, budgets, policy gates, prompt-injection defenses, and rollout controls.
Designs and implements frontend experiences for agentic applications. Use for chat and non-chat agent UX, streaming state machines, plan and receipt surfaces, approvals, provenance, failure recovery, and trustworthy interaction design.