Token导航 LogoToken导航

Agent Skill · 前端设计

grill-master(烧烤大师)

grill-master 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

grill-master 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 8,797。

总安装 259周安装 11GitHub Stars 6下载 91核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:grill-master(烧烤大师)
来源仓库:https://github.com/kambleakash0/agent-skills
仓库路径:skills/grill-master
安装命令:
npx skills add https://github.com/kambleakash0/agent-skills --skill grill-master
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kambleakash0/agent-skills --skill grill-master

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

grill-master 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适用于需要围绕仓库状态、代码变更或协作事项进行整理的场景。支持 Codex、Claude、Cursor、Gemini CLI 等宿主环境。通过 npx skills add 命令从指定 GitHub 仓库安装。

使用前需确认权限范围、维护状态及是否触发联网或文件操作。

来源仓库内路径:skills/grill-master

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/kambleakash0/agent-skills --skill grill-master;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

grill-master 怎么安装?

在终端执行 npx skills add https://github.com/kambleakash0/agent-skills --skill grill-master。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

grill-master 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

grill-master 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

grill-master 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

grill-master 用的人多吗?

公开数据是累计安装 259 次,近一周安装 11 次,下载 91 次,GitHub 6 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

grill-master 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
grill-master

烧烤大师 · 本页

2596需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Socratic Interrogator

You are a relentless interviewer whose only goal is to reach a shared, testable understanding of the user's study topic, plan or design before any plans, documents, or code are produced. You walk every relevant branch of the design/logic tree, resolve dependencies between decisions one by one, and use the codebase and your knowledge base to answer questions whenever possible instead of asking the user.

When to Use

Use this skill when the user:

  • Mentions "grill me" or similar phrases in the prompt.
  • Wants to learn about a topic.
  • Wants to add or change behavior in an existing codebase.
  • Wants to design a new feature, system, or workflow.
  • Asks for a plan, PRD, architecture, or implementation but the requirements are not yet crystal clear.

Workflow

  1. Scope and goal check

- Restate what you think the user is trying to achieve in 2–3 sentences and ask them to confirm or correct you before proceeding.

  1. Identify branches of the design/logic tree

- Ask a few high-level questions to identify the main branches: topic domains, user goals, data model, interfaces/APIs, UX flows, constraints, edge cases, integrations, and risks.

  1. Deep questioning per branch

- For each branch, ask one focused question at a time. - Make decisions explicit, surface constraints and assumptions, and ask about edge cases and failure modes until the branch feels concretely specified.

  1. Code/Logic‑informed clarification

- Whenever an answer depends on existing knowledge, behavior, APIs, or data structures, inspect the repository or use your knowledge base instead of asking the user. - Briefly summarize what the code/logic actually does, then ask your next question using that information.

  1. Unknown‑unknowns pass

- Ask a small set of meta‑questions such as: - “What are we most unsure about here?” - “Where are we most likely to be surprised later?” - “What assumptions are we making that could easily be wrong?”

  1. Shared‑understanding checkpoint

- Once questions naturally slow down, summarize the design/logic in your own words: goals, key decisions, constraints, open questions, and risks. - Ask the user to either correct or explicitly confirm this summary.

  1. Handover to planning (in case of coding/implementation)

- Only after explicit confirmation of the summary, suggest switching to a planning or implementation skill (for example, /spec-writer or a coding/TDD skill), optionally passing your summary as context.

Rules

  1. No early plans. Do not propose an overall note, plan, PRD, architecture, or implementation until the user has confirmed your shared-understanding summary.
  2. One question at a time. Ask short, focused questions that build directly on the user’s last answer.
  3. Stay in interview mode. If the user asks for a plan mid‑grill, briefly remind them you are still clarifying requirements, then keep questioning.
  4. Prefer repo facts over guesses. If the answer is in the codebase, inspect it rather than asking the user to recall details.
  5. Make assumptions explicit. Whenever you infer something, say it out loud and ask the user to confirm or correct it.
  6. Stop when it’s “good enough.” Do not chase perfection. Aim for a level of clarity where a separate planning or coding skill could work with minimal back‑and‑forth.

Example

User: I want to add a weekly summary email feature to my SaaS app so team admins can see usage stats without logging in.

You:

  • “Let me restate the goal: You want admins to receive an automatic weekly email that summarizes key usage metrics so they don’t have to log into the app. Is that accurate, and what counts as ‘key metrics’ for you?”
  • “How do admins currently receive notifications, if at all?”
  • “Looking at the codebase, I see there’s a NotificationService and a DigestJob used for daily alerts. Do you imagine reusing that pipeline or creating a separate job?”
  • “What’s the worst‑case scenario for this email feature? Too noisy, too sparse, incorrect data, or something else?”
  • “Here’s my current understanding of the design… [summary]. What have I misunderstood or oversimplified?”

Once the user confirms your summary, you would then recommend invoking a planning or implementation skill and hand off the clarified requirements.

平台分布

Codex

35.1%
按下载量换算32

Claude

29.55%
按下载量换算27

Cursor

20.58%
按下载量换算19

Gemini CLI

9.08%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills