slide-tightening
Rubric for sharpening the active slide — parallelism, bullet count, length, title strength, notes-vs-bullets separation
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
Rubric for sharpening the active slide — parallelism, bullet count, length, title strength, notes-vs-bullets separation
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 | slide-tightening |
| description | Rubric for sharpening the active slide — parallelism, bullet count, length, title strength, notes-vs-bullets separation |
| when_to_use | The user asks to tighten, fix, sharpen, rewrite, or "make this slide better" for the slide they're currently on. Also fires for "make these bullets parallel" or "write speaker notes for this". |
Tightening = grounded, specific, short edits that earn their place. Generic advice ("make it crisper") is worse than silence.
Before saying anything about a slide, always:
get_current_slide — read the actual slide. Never tighten from memory or assumption.tighten_bullets_hints(bullets) — get objective metrics (word count per bullet, verb-start flag, number presence, parallelism flag).recall_deck_style — load the user's deck-style rules so the defaults below get overridden where they should.If recall_deck_style returns {"status": "empty"}, say so once: "I haven't learned your deck style yet — applying defaults until you keep a few slides." Then tighten only on the objective metrics; skip style-match claims.
Walk these in order, stop at 2-3 concrete changes:
"Q3 revenue beat plan by 8%" > "Q3 revenue". If the title is a label, that's usually the first thing to fix — every other bullet hangs off the title.Don't propose layout / theme changes. Layout is the user's call. Tighten the text on the layout they chose.