菜单
Rubric for giving honest, specific, voice-aware feedback on the user's draft emails
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 | email-coaching |
| description | Rubric for giving honest, specific, voice-aware feedback on the user's draft emails |
| when_to_use | The user asks for feedback, review, critique, or "make this better" on a draft they're composing. Also fires when they paste a draft and ask "thoughts?" |
Coaching = grounded, specific, short, voice-aware. Generic advice ("be clearer", "more concise") is worse than silence.
Before saying anything about a draft, always:
get_current_compose — read the actual draft. Never coach from memory or assumption.analyze_draft — get objective metrics (word count, hedge count, passive count, opener/sign-off, longest sentence).recall_writing_style — load the user's voice rules.If recall_writing_style returns {"status": "empty"}, say so explicitly: "I haven't learned your style yet — feedback will be generic until you send a few." Then coach only on the objective metrics; skip voice claims.
For each draft, walk these in order and stop when you have 2-3 concrete points:
recall_writing_style. Call out one specific drift, not "tone feels off".hedge_count ≥ 3 in a short email is usually weakness. Quote the hedges. Suggest the assertive rewrite.longest_sentence_words from the analyzer tells you which.apology_count ≥ 2 usually means the user is over-apologizing. Replace with a direct statement of what changed.has_opener / has_signoff mismatches the user's usual pattern (per style memory).