deck-structure
When and how to suggest reordering, splitting, or trimming a deck — agenda placement, CTA placement, problem-solution arc, methodology-results arc
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。
菜单
When and how to suggest reordering, splitting, or trimming a deck — agenda placement, CTA placement, problem-solution arc, methodology-results arc
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。
Use when the user wants to build a Google ADK agent — scaffolding a new agent, adding tools/skills/prompts to one, or asking how to structure an ADK project. Triggers on phrases like "create an ADK agent", "build a Google agent", "scaffold an agent", "make an agent that does X", "I need an ADK skeleton", or any task involving generated-agents/, LlmAgent, SkillToolset, or the ADK framework. Also use whenever the user mentions `nuvel`, the `nuvel` CLI, or asks about agent architecture patterns / callbacks / HITL / streaming / ADK prompt engineering — nuvel ships the canonical knowledge skills for those topics. Lean toward triggering — if the task touches Google ADK at all, this skill is in scope.
Delegate work to sub-agents with the ADK 2.0 Task API — `mode='task'`, `mode='single_turn'`, `mode='chat'` on `LlmAgent`, the auto-attached `finish_task` tool, and typed contracts via `input_schema` / `output_schema`. Load this skill when one agent needs to hand a bounded unit of work to another and get a validated result back, or when migrating off SequentialAgent / ParallelAgent / LoopAgent.
Creating valid SKILL.md files following the agentskills.io specification — frontmatter, instructions, references directory, progressive disclosure (L1/L2/L3), and SkillToolset wiring in agent.py. Load this skill when generating domain skills for an agent.
Build graph-based agents with ADK 2.0 `Workflow` — declare nodes and edges, route conditionally, fan-out/fan-in in parallel, run dynamic nodes at runtime, and add human-in-the-loop revision cycles. Load this skill whenever the agent needs anything beyond a strictly linear or trivially parallel pipeline.
Agent architecture patterns for Google ADK 2.0 — when to reach for a single LlmAgent, a Workflow graph (new default for multi-step orchestration), or the shortcut classes SequentialAgent / LoopAgent / ParallelAgent. Load this skill when deciding the agent's top-level shape.
Pattern for turning a brief into a coherent deck outline — intent detection, section ratios, draft headings, expansion
| name | deck-structure |
| description | When and how to suggest reordering, splitting, or trimming a deck — agenda placement, CTA placement, problem-solution arc, methodology-results arc |
| when_to_use | The user asks to restructure, reorder, "fix the flow", "what's missing", or to review the whole deck rather than a single slide. Also fires for "should I split this into two decks?" and "is the order right?". |
Structural suggestions are expensive — every move ripples through the deck, every cut burns work. So the bar is high: a change earns its place only when the deck is meaningfully better afterwards.
get_deck_outline — read the live outline (titles, bullet counts, has-notes per slide).analyze_deck_flow(outline_json) — get evidence of structural problems: repeated titles, missing agenda, missing CTA, bullet overload, section imbalance.suggest_reordering(outline_json) — get a concrete list of move suggestions with reasons.If both analyze_deck_flow and suggest_reordering come back with no findings, say "the flow holds — no moves I'd defend" and stop. Don't invent problems.
Pick the arc that matches what the deck is actually doing:
For a 10-slide pitch, that's typically 1 title + 1 agenda + 2 problem + 2 solution + 2 evidence + 1 ask + 1 thanks (optional). Map the user's outline to that template; the gaps are your structural observations.
Only when one of:
Skip aesthetic preferences. "I'd rather have the team slide earlier" is not a structural problem.
For each suggested move, return:
Move slide N ("<title>") → position M
Why: <one-sentence reason>
Cap at 3 moves in one pass. If there are more, name the top 3 and say "more once we settle these."
When the user asks "what's missing?", answer with at most 2 missing slides, each with the title you'd give it and where it'd go.