🧐
QualityPython

Grill Me

by feiskyer

Grill Me is a Quality skill for Claude Code, published by feiskyer in codex-settings.

237 stars33 forkson feiskyer/codex-settingsAdded 2026/09/03Repository updated 2026/08/13
agent-skillsagentic-aiagentsaiai-codingcodexcodex-clicodex-profilescodex-skillscopilotlitellmmcpopenaivibe-coding
Install in seconds
Install Grill Me
Copy Grill Me into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/feiskyer/codex-settings/tree/main/skills/grill-me ~/.claude/skills/grill-me

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/feiskyer/codex-settings.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/grill-me/SKILL.md in feiskyer/codex-settings
Installs to
~/.claude/skills/grill-me
Collection
One of 11 skills cataloged from this repository
Category
Quality1478 skills

What Grill Me does

Grill Me runs one-question-at-a-time challenge sessions to pressure-test a proposal or design. It also maintains the domain glossary, context notes, and ADRs when decisions are settled.

Grill Me is cataloged under Quality on DirSkills. Grill Me comes from a repository tagged agent-skills, agentic-ai, agents, ai and ai-coding.

Documentation

README

追问会话

启动步骤

触发后,先执行以下检查:

  1. 检查项目根目录是否已有 CONTEXT.mdCONTEXT-MAP.md,有则读取
  2. 检查 docs/adr/ 是否已有 ADR 记录,有则了解已有决策
  3. 然后开始追问

核心规则

针对方案的每一个方面进行不留死角的追问,直到我们达成共识。沿着设计决策树逐一走下去,逐条解决决策之间的依赖关系。每个问题给出你的推荐答案。

一次只问一个问题,等我回复后再继续下一个。一次抛出多个问题会让人无所适从。

如果某个事实可以通过探索代码库获得,就直接查找,不要问我。但决策权在我——每个决策都提给我,等我回答。

在我明确确认达成共识之前,不要开始执行方案。


领域建模(内置流程)

追问过程中,一旦有决策结晶,就立即建立和完善项目的领域模型——挑战术语、构造边界场景、在第一时间写下术语表和决策记录。

文件结构

大多数仓库只有单一上下文:

/
├── CONTEXT.md
├── docs/
│   └── adr/
│       ├── 0001-event-sourced-orders.md
│       └── 0002-postgres-for-write-model.md
└── src/

如果根目录存在 CONTEXT-MAP.md,则表示仓库有多个上下文,地图指向各自位置:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Grill Me

  • What else does feiskyer publish alongside Grill Me?

    Grill Me is one of 11 skills that DirSkills catalogs from feiskyer/codex-settings, the repository it ships in. Its siblings there include Brainstorming, Claude Code Headless Mode and Deep Research. Each one is a separate skill with its own page in this directory, installs the same way Grill Me does, and is maintained by feiskyer in that same repository. The rest of the collection is listed on the feiskyer/codex-settings page.

  • How does Grill Me compare to other Quality skills?

    Grill Me ranks #1353 by stars among the 1478 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Grill Me against them. Open each page to compare what they document and how they install.

More from feiskyer/codex-settings

Grill Me is one of 11 skills cataloged on DirSkills from feiskyer/codex-settings.

See all 11 skills
🧠
7h ago

Brainstorming

Brainstorming helps turn a user’s idea into a design and spec before implementation. It is used for new features, components, or systems when choices, constraints, and success criteria need to be clarified first.
AI Engineering
23733
🤖
7h ago

Claude Code Headless Mode

Claude Code Headless Mode delegates work to the Claude Code CLI for non-interactive runs, automation scripts, CI jobs, and resumable sessions. Use it when you want Claude to execute a task through `claude -p` instead of solving it inline.
Automation
23733
🔎
7h ago

Deep Research

Deep Research orchestrates a multi-agent workflow that splits a research goal into parallel sub-tasks, gathers evidence with Codex CLI subprocesses, and merges the results into a verified report. Use it for systematic web or document research, competitor analysis, and long-form evidence synthesis.
AI Engineering
23733
🖼️
7h ago

GPT Image

GPT Image generates or edits images with OpenAI GPT Image models from prompts and input images. Use it when you want to create artwork, logos, or modified images with gpt-image-2 or related models.
AI Engineering
23733
🐛
7h ago

GitHub Issue Fix

GitHub Issue Fix analyzes a reported issue in the current repository, implements the smallest appropriate change, and verifies it with targeted tests. Use it when you need help investigating or fixing an issue by number or URL.
Quality
23733
🧐
7h ago

GitHub Pull Request Review

GitHub Pull Request Review analyzes a GitHub pull request with evidence-backed checks, multiple review angles, and false-positive filtering. Use it when reviewing a PR by number or URL and you want a local findings report or an explicitly authorized published review.
Quality
23733