Deep Dive
byungjunjang/jangpm-meta-skills
Socratic interview skill to deepen a spec or refine an existing agent blueprint.
针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。
Install Grill Me
$ npx skills add feiskyer/claude-code-settings --skill grill-me -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install feiskyer/claude-code-settings grill-me --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/grill-me .claude/skills/grill-me && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "grill-me" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/grill-me into .claude/skills/grill-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill-me", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/feiskyer/claude-code-settings/tree/main/skills/grill-meType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add feiskyer/claude-code-settings --skill grill-me -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install feiskyer/claude-code-settings grill-me --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/grill-me .agents/skills/grill-me && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "grill-me" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/grill-me into .agents/skills/grill-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill-me", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feiskyer/claude-code-settings --skill grill-me -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install feiskyer/claude-code-settings grill-me --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/grill-me .cursor/skills/grill-me && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "grill-me" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/grill-me into .cursor/skills/grill-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill-me", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/feiskyer/claude-code-settings.git --path skills/grill-me--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add feiskyer/claude-code-settings --skill grill-me -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install feiskyer/claude-code-settings grill-me --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/grill-me .gemini/skills/grill-me && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "grill-me" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/grill-me into .gemini/skills/grill-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill-me", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install feiskyer/claude-code-settings grill-meInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add feiskyer/claude-code-settings --skill grill-me -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/grill-me .github/skills/grill-me && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "grill-me" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/grill-me into .github/skills/grill-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill-me", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feiskyer/claude-code-settings --skill grill-me -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install feiskyer/claude-code-settings grill-me --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/grill-me .opencode/skills/grill-me && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "grill-me" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/grill-me into .opencode/skills/grill-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill-me", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
grill-me- GitHub stars
- 1.7k
- Token cost
- ~913 tokens
- SKILL.md length
- 166 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。
- Works in 3 steps: 检查项目根目录是否已有 CONTEXT.md 或… → 检查 docs/adr/ 是否已有 ADR 记录，有则了解已有决策 → 然后开始追问
- Tasks that involve Requirements gathering
- SKILL.md covers 启动步骤, 核心规则, 文件结构 and 追问过程中的行为, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Grill Me is an agent skill from feiskyer/claude-code-settings. 针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。
Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Requirements gathering, Architecture decision records and Design review and critique. The repository describes itself as: Curated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more. The licence is MIT.
When your agent uses it
- Tasks that involve Requirements gathering
- Tasks that involve Architecture decision records
- Tasks that involve Design review and critique
Example prompts
- “/grill-me”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 检查项目根目录是否已有 CONTEXT.md 或 CONTEXT-MAP.md，有则读取
- 检查 docs/adr/ 是否已有 ADR 记录，有则了解已有决策
- 然后开始追问
What it can do on your machine
Read from SKILL.md and the folder at commit 95dab59. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Grill Me loads about 913 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 166 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from feiskyer/claude-code-settings at commit 95dab59, republished under its MIT licence (© feiskyer). 166 words, ~913 tokens.
Download SKILL.mdSave it as
.claude/skills/grill-me/SKILL.md (or your agent's skills folder).- name
- grill-me
- description
- 针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。
- argument-hint
- 你要追问的方案/设计是什么？
- disable-model-invocation
- true
追问会话
启动步骤
触发后，先执行以下检查：
- 检查项目根目录是否已有
CONTEXT.md或CONTEXT-MAP.md，有则读取 - 检查
docs/adr/是否已有 ADR 记录，有则了解已有决策 - 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：
/
├── CONTEXT-MAP.md
├── docs/
│ └── adr/ ← 系统级决策
├── src/
│ ├── ordering/
│ │ ├── CONTEXT.md
│ │ └── docs/adr/ ← 上下文专属决策
│ └── billing/
│ ├── CONTEXT.md
│ └── docs/adr/懒创建——只在有内容可写时才创建文件。如果 CONTEXT.md 不存在，在第一个术语确定时创建它。如果 docs/adr/ 不存在，在第一个 ADR 需要时创建它。
追问过程中的行为
对照术语表质疑
当用户使用的术语与 CONTEXT.md 中已有定义冲突时，立即指出："你的术语表把'取消'定义为 X，但你现在似乎是指 Y——到底是哪个？"
磨尖模糊表达
当用户使用含糊或多义的词汇时，提出精确的规范术语："你说的'账户'——是指 Customer 还是 User？这是两个不同概念。"
讨论具体场景
讨论领域关系时，用具体场景压力测试。构造探索边界条件的场景，迫使用户精确界定概念之间的边界。
与代码交叉验证
当用户陈述某物如何运作时，检查代码是否一致。如果发现矛盾，立即暴露："你的代码取消的是整个 Order，但你刚说可以部分取消——哪个是对的？"
即时更新 CONTEXT.md
术语一旦敲定，立即更新 CONTEXT.md，不要攒着批量处理。格式参见下方「CONTEXT.md 格式」章节。
CONTEXT.md 必须完全不含实现细节。不要把它当规格文档、草稿本或实现决策仓库。它只是术语表。
审慎提供 ADR
仅当以下三条全部成立时才创建 ADR：
- 难以逆转 — 将来改变主意的代价可观
- 缺乏上下文则令人费解 — 未来读者会困惑"为什么这样做？"
- 确实是权衡的结果 — 存在真正的替代方案，且你基于具体理由选了其一
参考：CONTEXT.md 格式
结构
# {上下文名称}
{一两句话描述这个上下文是什么、为什么存在。}
## 语言
**订单（Order）**:
{一两句话定义该术语}
_避免使用_: Purchase, transaction
**发票（Invoice）**:
向客户发送的交付后付款请求。
_避免使用_: Bill, payment request
**客户（Customer）**:
下订单的个人或组织。
_避免使用_: Client, buyer, account注：示例语言应跟随项目主语言。中文项目用中文术语，英文项目用英文术语。
规则
- 有主张。 当多个词指代同一概念时，选最好的那个，其余列入
_避免使用_。 - 定义简洁。 最多两句话。定义它是什么，而非它做什么。
- 只收录项目上下文专属术语。 通用编程概念不属于这里。
- 出现自然聚类时分组。 若所有术语属于同一领域，平铺即可。
单上下文 vs 多上下文
单上下文（多数仓库）： 根目录一个 CONTEXT.md。
多上下文： 根目录 CONTEXT-MAP.md 列出所有上下文及其关系：
# 上下文地图
## 上下文
- [Ordering](./src/ordering/CONTEXT.md) — 接收和追踪客户订单
- [Billing](./src/billing/CONTEXT.md) — 生成发票和处理付款
- [Fulfillment](./src/fulfillment/CONTEXT.md) — 管理仓库拣货和发运
## 关系
- **Ordering → Fulfillment**: Ordering 发出 `OrderPlaced` 事件；Fulfillment 消费它以启动拣货
- **Fulfillment → Billing**: Fulfillment 发出 `ShipmentDispatched` 事件；Billing 消费它以生成发票
- **Ordering ↔ Billing**: 共享 `CustomerId` 和 `Money` 类型推断当前结构：
- 若
CONTEXT-MAP.md存在，读取它来定位上下文 - 若只有根目录
CONTEXT.md，则为单上下文 - 若都不存在，在第一个术语确定时懒创建根目录
CONTEXT.md
多上下文时，推断当前话题关联哪个上下文。不确定时，问。
参考：ADR 格式
ADR 存放在 docs/adr/，使用顺序编号：0001-slug.md、0002-slug.md……
懒创建 docs/adr/ 目录——只在第一个 ADR 需要时创建。
模板
# {决策的简短标题}
{1-3 句话：背景是什么，我们决定了什么，为什么。}一个 ADR 可以只有一段话。价值在于记录做了什么决策以及为什么——而非填满各个章节。
可选章节
仅在确有价值时才加。大多数 ADR 不需要。
- Status（
proposed | accepted | deprecated | superseded by ADR-NNNN）— 决策被重新审视时有用 - 备选方案 — 仅当被否决的替代方案值得记住时
- 后果 — 仅当存在不显而易见的下游影响时
编号
扫描 docs/adr/ 找到当前最大编号，加一。
什么适合做 ADR
- 架构形态。 "我们使用 monorepo。" "写模型使用事件溯源。"
- 上下文间的集成模式。 "Ordering 和 Billing 通过领域事件通信。"
- 有锁定效应的技术选型。 数据库、消息总线、认证提供商、部署目标。
- 边界与范围决策。 "Customer 数据由 Customer 上下文拥有；其他上下文只通过 ID 引用。"
- 对显而易见路径的刻意偏离。 让未来读者不会误以为是 bug 而"修复"它。
- 代码中不可见的约束。 "因合规要求不能使用 AWS。"
- 被否决方案的理由不明显时。 防止六个月后有人重新提出同样建议。
© feiskyer, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/grill-me of feiskyer/claude-code-settings.
Open the folder on GitHubat commit 95dab59
Compare with similar skills
Grill Me next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Grill Me this skillfeiskyer/claude-code-settings | 1.7k | — | ~913 | Automated safety check: Pass | MIT | |
| Deep Divebyungjunjang/jangpm-meta-skills | 120 | — | ~2.5k | Automated safety check: Pass | None | |
| Grill Menrwl/nx | 29k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Grill Memacalbert/envilder | 138 | — | ~1k | Automated safety check: Pass | MIT | |
| Grill Mefeiskyer/codex-settings | 244 | — | ~284 | Automated safety check: Pass | MIT | |
| Grill With Docsmeain/dotfiles | 285 | 20 repos | ~875 | Automated safety check: Pass | MIT |
Similar skills
Grill Me
nrwl/nx
Grill the user relentlessly about a plan, design, decision, or set of review findings — working the decision tree in rounds until nothing is left silently assumed.
Grill Me
macalbert/envilder
Grilling session that challenges a plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.
Grill Me
feiskyer/codex-settings
仅当用户显式调用 $grill-me，或明确要求"追问我""挑战这个方案""拷打这个设计"时使用。通过高强度逐问逐答检验方案，并同步沉淀术语表和 ADR。不要因普通设计讨论自动触发。
Grill With Docs
meain/dotfiles
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.
Foreman Grill Docs
VisionForge-OU/foreman
Headless grilling pass that challenges an approved implementation plan against the existing codebase and domain model, then writes an ADR draft and a PRD draft into the Foreman feature directory.
More from feiskyer/claude-code-settings
All 12 skills in this repoSkill Creator
feiskyer/claude-code-settings
Create, refine, and benchmark agent skills. An agent skill from feiskyer/claude-code-settings.
Brainstorming
feiskyer/claude-code-settings
Explore user intent, requirements, and design options through collaborative dialogue before implementation.
Deep Research
feiskyer/claude-code-settings
Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file.
Codex Skill
feiskyer/claude-code-settings
Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review.
GitHub Fix Issue
feiskyer/claude-code-settings
Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission.
GitHub Review PR
feiskyer/claude-code-settings
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents.
Related
Categories
Questions about Grill Me
What does Grill Me do?
针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。. Grill Me is an agent skill from feiskyer/claude-code-settings.
When should I use Grill Me?
Grill Me fits situations like: tasks that involve Requirements gathering; tasks that involve Architecture decision records; tasks that involve Design review and critique.
How do I install Grill Me in Claude Code?
Run `npx skills add feiskyer/claude-code-settings --skill grill-me -a claude-code`. Or copy the skill folder (skills/grill-me in feiskyer/claude-code-settings) into .claude/skills/grill-me in your project. Claude Code loads it when a task matches its description.
How do I install Grill Me in Codex?
Run `npx skills add feiskyer/claude-code-settings --skill grill-me -a codex`. Or copy the skill folder (skills/grill-me in feiskyer/claude-code-settings) into .agents/skills/grill-me in your project. Codex loads it when a task matches its description.
Can I use Grill Me in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add feiskyer/claude-code-settings --skill grill-me -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grill-me, .gemini/skills/grill-me, .github/skills/grill-me and .opencode/skills/grill-me in your project.
What does Grill Me need to run?
SKILL.md names no scripts, command-line tools or credentials: Grill Me is instructions for the agent only.
Does Grill Me access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Grill Me safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Grill Me use?
Grill Me is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Grill Me use?
About 913 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Grill Me?
Skills that share tags, products or a category with Grill Me: Deep Dive (byungjunjang/jangpm-meta-skills, 120 stars), Grill Me (nrwl/nx, 29k stars), Grill Me (macalbert/envilder, 138 stars) and Grill Me (feiskyer/codex-settings, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Grill Me?
feiskyer (a GitHub user) maintains it in feiskyer/claude-code-settings, which has 1,658 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 27, 2026.
Source: feiskyer/claude-code-settings on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.