关于
The grill skill helps developers refine vague ideas by asking focused questions before writing a spec. It captures each answer as a clear goal (§G) or constraint (§C), parking unknowns as `?` items without guessing. Use it when you have a fuzzy concept to stress-test assumptions and prevent costly mistakes early in the planning process.
快速安装
Claude Code
推荐npx skills add JuliusBrussee/blueprint -a claude-code/plugin add https://github.com/JuliusBrussee/blueprintgit clone https://github.com/JuliusBrussee/blueprint.git ~/.claude/skills/grill在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
grill — sharpen idea before spec
One question at a time. Every answer lands in a § or gets parked ?. Never guess a constraint into existence.
Plan-then-execute guesses the fuzzy parts & builds the wrong thing. Grill drags the fuzz into §G/§C before a single §T row exists. A bad assumption caught here costs one question. Caught in §B it costs a bug.
WHEN TO GRILL
- Idea is one sentence & you can feel the holes.
- Multiple readings of the goal exist & you are about to pick one silently.
- Before
/spec newon anything non-trivial. - User asks to be challenged / stress-tested.
Skip for a typo or a one-line fix. Grill scales to uncertainty, ⊥ to ego.
CALIBRATE FIRST
One opening read, not a quiz:
- How well does user know this domain? (sets question depth)
- How locked is the idea? (exploring vs committed)
- Pressure wanted: light / normal / brutal.
Match it. Brutal grilling on a half-formed idea just demoralizes. Light grilling on a committed plan misses the load-bearing flaw.
QUESTION LADDER
Climb in order. Each rung, ask one question, recommend an answer, wait.
- Goal — what must the code do, in one line? (→ §G)
- Done — how do we know it works? name the observable. (→ §C / future §V)
- Boundary — what is explicitly out of scope? (→ §C)
- Lock — what tech/lib/pattern is non-negotiable? what is forbidden? (→ §C)
- Surface — what does the outside world touch — cmd, api, file, env? (→ §I)
- Edge — the one input that breaks the happy path? (→ future §V)
- Unknown — what do we not know yet? (→ park as
?§C bullet)
Stop climbing the moment the spec would be unambiguous. Do not ask all seven by reflex.
ANSWER FORMAT
Each question carries a recommended answer so the user can grunt "yes" & move:
Q: auth — session cookie or JWT? rec: JWT — stateless, you named horizontal scaling as a §C. (a) JWT (b) cookie (c) something else?
HANDOFF
When done, emit a compact block — goal line, constraint bullets, surfaced
unknowns as ? — and hand to the spec skill to write §G/§C. Grill proposes;
spec is the sole mutator. Never write SPEC.md directly.
WHEN TO STOP
Done when ALL hold:
- §G is one line, one reading, zero "or maybe".
- §C covers every non-negotiable the user stated or implied.
- Every blocking unknown is either answered or parked as an explicit
?.
Unresolved blocking unknown that needs the outside world → recommend /research, not a guess.
BOUNDARIES
- ⊥ make product decisions for the user. Recommend, never decide.
- ⊥ write SPEC.md. Hand structured answers to spec.
- ⊥ ask in bulk. One question, one recommendation, wait.
- ⊥ grill a trivial change. Right-size or skip.
GitHub 仓库
Frequently asked questions
What is the grill skill?
grill is a Claude Skill by JuliusBrussee. Skills package instructions and resources that Claude loads on demand, so Claude can perform grill-related tasks without extra prompting.
How do I install grill?
Use the install commands on this page: add grill to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does grill belong to?
grill is in the Meta category, tagged ai and testing.
Is grill free to use?
Yes. grill is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
