Agent Skillspingdotgg/t3code › grill-me

grill-me

GitHub

通过交互式问答对计划或设计进行压力测试,逐步厘清决策树中的假设、风险和依赖,最终达成共识并总结设计方案。

.repos/effect-smol/.agents/skills/grill-me/SKILL.md pingdotgg/t3code

Trigger Scenarios

用户希望压力测试计划 用户希望接受设计审查 用户提及 'grill me'

Install

npx skills add pingdotgg/t3code --skill grill-me -g -y
More Options

Non-standard path

npx skills add https://github.com/pingdotgg/t3code/tree/main/.repos/effect-smol/.agents/skills/grill-me -g -y

Use without installing

npx skills use pingdotgg/t3code@grill-me

指定 Agent (Claude Code)

npx skills add pingdotgg/t3code --skill grill-me -a claude-code -g -y

安装 repo 全部 skill

npx skills add pingdotgg/t3code --all -g -y

预览 repo 内 skill

npx skills add pingdotgg/t3code --list

SKILL.md

Frontmatter
{
    "name": "grill-me",
    "description": "Interview the user about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions \"grill me\"."
}

Interview me about every aspect of this plan until we reach a shared understanding and a defensible design.

Ask exactly one question at a time, then wait for my answer before asking the next question.

Use each answer to choose the next highest-leverage unresolved question. Maintain an implicit decision tree of resolved decisions, open questions, assumptions, dependencies, risks, and rejected alternatives.

For each question, include:

  • clear answer options when appropriate
  • your recommended answer, marked as recommended
  • a brief reason for the recommendation

Use open-ended questions when fixed options would prematurely constrain the design space.

Challenge vague, inconsistent, risky, or unsupported assumptions. If an answer creates a contradiction or unresolved dependency, ask a follow-up before moving on.

Cover, as relevant:

  • goals and non-goals
  • users and stakeholders
  • constraints
  • alternatives
  • APIs and interfaces
  • data model
  • error handling
  • security
  • observability
  • testing
  • migration and rollout
  • failure modes
  • operational ownership
  • success criteria

If repository facts are needed, inspect the codebase instead of asking the user. Do not ask me to provide information that can be determined locally.

When an available user-input tool such as request_user_input fits the question, use it to ask one short question with a small set of mutually exclusive options. Otherwise, ask in plain text and present clear possible answers as a numbered list when that helps me answer quickly. Include your recommended option and mark it as recommended.

Stop when the major branches of the design tree have been resolved. Then summarize the agreed design, remaining risks, assumptions, rejected alternatives, and next steps.

Version History

  • ece0508 Current 2026-07-24 22:03

Same Skill Collection

.agents/skills/ios-debugger-agent/SKILL.md
.agents/skills/ios-simulator-browser/SKILL.md
.agents/skills/test-t3-app/SKILL.md
.agents/skills/test-t3-mobile/SKILL.md
.repos/effect-smol/.agents/skills/jsdocs/SKILL.md
.repos/effect-smol/.agents/skills/scratchpad/SKILL.md

Metadata

Files
0
Version
f2d5fc9
Hash
c5db9c53
Indexed
2026-07-24 22:03

Главная - Вики-сайт
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-20 11:54
浙ICP备14020137号-1 $Гость$