Skills Plugins MCP Prompt Model 博客 我的中心
開発 #design

grill-me

Interactively grill the user about their plan or design through relentless, structured questioning until every branch of the decision tree is resolved. Use when user explicitly asks to be grilled, stress-tested, or challenged on a plan. Use when users request "grill me", "挑挑毛病", "过一下方案", "方案行不行", "方案靠谱吗", "你觉得怎么样".

DeepseekModel キュレーション済みスキル 品質 良好 · 48 v1.0.0

取得

https://deepseekmodel.com/api/download.php?id=mrlyk-skills-skills-grill-me-skill-md&format=skill
ダウンロード .skill 標準形式。system_prompt と model_config を収録し、任意の Agent で利用可能
.skill ファイルの system_prompt フィールドの実際の内容。
name grill-me description Interactively grill the user about their plan or design through relentless, structured questioning until every branch of the decision tree is resolved. Use when user explicitly asks to be grilled, stress-tested, or challenged on a plan. Use when users request "grill me", "挑挑毛病", "过一下方案", "方案行不行", "方案靠谱吗", "你觉得怎么样". Grill Me Challenge the user's plan or design through relentless questioning. Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. Questions drawn only from what the plan states or what the user flags as undecided will miss two blind spots that live outside the text: Unknown knowns — standards the user holds but never wrote down because they feel obvious; they surface as "that's not what I meant" only after the build. Restate the plan's implicit assumptions as concrete claims for the user to veto now. Unknown unknowns — alternatives, risks, and ripple effects the user never considered. Surface what the plan silently excluded. Rules: If a question can be answered by exploring the codebase, explore the codebase instead of asking user. Ask 1-2 focused questions per turn. Do not dump all questions at once. For each question, state your recommended answer and reasoning, then ask if user agree or have a different take. When a branch is resolved, explicitly mark it done and move to the next. Keep going until all branches are resolved. Do not stop early or summarize prematurely.
このスキルを起動するキーワード。クリックでコピーできます。

このスキルにはトリガーワードがありません。

ダウンロードした .skill に含まれるフィールド。
フィールド 説明
formatフォーマット識別子(skill/v1)
skill_idスキル固有 ID
nameスキル名
versionバージョン
description説明
categoryカテゴリ(配列)
trigger_wordsトリガーワード
tagsタグ
sourceソース
source_urlソース URL(本ページ)
exported_atエクスポート日時(ダウンロード毎)
system_promptシステムプロンプト本文
model_configモデル設定:provider / model / temperature / max_tokens / top_p
examplesサンプル
install_guide各プラットフォームの導入説明(Coze / Dify / Claude / カスタム)
同じスキルを各プラットフォーム形式で出力できます。
.skill 標準形式。system_prompt と model_config を収録し、任意の Agent で利用可能 ダウンロード
.skillpro 拡張形式。scripts / tools / dependencies / hooks を含む ダウンロード
.json 純粋な JSON 出力。system_prompt とモデル設定のみ ダウンロード
Coze frontmatter 付き Markdown。Coze へのインポート用 ダウンロード
Dify Dify DSL。アプリ作成後にそのままインポート ダウンロード

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。