Skip to content
Development
Skill

/grill-po

Requirements grilling session with a Product Owner (or anyone in that role). Challenges plans against the existing domain model, sharpens terminology, and updates documentation (bounded-context files, Gherkin features, DMDs (Domain Model Decisions)) inline as decisions

From plugin
tdder
1414 skills7 agents2 commands1 hook
Install
$ npx -y skills add t1/tdder --skill grill-po --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/grill-po

Context preview

The summary Claude sees to decide when to auto-load this skill.

Requirements grilling session with a Product Owner (or anyone in that role). Challenges plans against the existing domain model, sharpens terminology, and updates documentation (bounded-context files, Gherkin features, DMDs (Domain Model Decisions)) inline as decisions

SKILL.md

grill-po.SKILL.md
name: grill-po
description: >
  Requirements grilling session with a Product Owner (or anyone in that role). Challenges plans against
  the existing domain model, sharpens terminology, and updates documentation (bounded-context files,
  Gherkin features, DMDs (Domain Model Decisions)) inline as decisions crystallise. Use when the user wants to discuss and
  capture requirements, stress-test a plan against the project's language, or refine feature scope.
version: 0.1.0

Grill PO

Interview the user relentlessly about every aspect of their plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.

Ask questions one at a time, waiting for feedback on each before continuing.

If a question can be answered by exploring the codebase, explore the codebase instead.

Domain Awareness

During codebase exploration, also look for existing documentation.

File Structure

**Single-context repo:**

/
├── bounded-context.md
├── docs/
│   └── features/
│       ├── place-order.feature
│       └── cancel-order.feature
└── src/

**Multi-context mono-repo:**

/
├── README.md                          ← contains "Bounded Contexts" section (context map)
├── AGENTS.md                          ← contains "Bounded Contexts" section (context map)
├── docs/
├── src/
│   ├── ordering/
│   │   ├── ordering-bounded-context.md
│   │   └── docs/features/             ← context-specific features
│   └── billing/
│       └── billing-bounded-context.md

Create files lazily — only when you have something to write.

**Detecting the structure:**

  • If a `bounded-context.md` exists at root → single context
  • If `*-bounded-context.md` files exist elsewhere → multi-context; read the "Bounded Contexts" section of

`README.md` or `AGENTS.md` for the context map

  • If neither exists → create `bounded-context.md` lazily when the first term is resolved

When multiple contexts exist, infer which one the current topic relates to. If unclear, ask.

During the Session

Challenge against the glossary

When the user uses a term that conflicts with the existing language in the bounded-context file, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"

Also scan existing `.feature` files for terminology drift: if a scenario uses a term differently from the bounded-context file, surface it. "Your feature file says 'purchase' but the glossary defines that concept as 'order' — which should it be?"

Sharpen fuzzy language

When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things."

Discuss concrete scenarios

When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.

Update the bounded-context file inline

When a term is resolved, update the bounded-context file right there. Don't batch these up — capture them as they happen. Use the format in [bounded-context-format.md](bounded-context-format.md).

The bounded-context file must be totally devoid of implementation details. Do not treat it as a spec, a scratch pad, or a repository for implementation decisions. It is a **glossary and nothing else**.

Document features as Gherkin

When a feature is agreed on, write or update a `.feature` file in `docs/features/` (or the context-specific equivalent). Use standard Gherkin (`Feature`, `Scenario`, `Given`/`When`/`Then`). Rules:

  • One `.feature` file per feature area, named after it (e.g. `place-order.feature`)
  • Scenarios use domain language from the bounded-context file — no technical terms
  • Scenarios are business-readable: a domain expert should be able to read and validate them
  • Do not add scenarios for implementation details (e.g. HTTP status codes, database columns)
  • Update existing scenarios when behavior changes — don't accumulate stale scenarios

Offer DMDs sparingly

Only offer to create a DMD when all three are true:

1. **Hard to reverse** — the cost of changing your mind later is meaningful 2. **Surprising without context** — a future reader will wonder "why did they model it that way?" 3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons

If any of the three is missing, skip the DMD. Use the format in [dmd-format.md](dmd-format.md).

Read more
Ships withtdder

A plugin for pi, Claude Code, and OpenCode that guides AI agents through disciplined Test-Driven Development and Clean Code practices. Note that currently this is WORK IN PROGRESS! I'm not even trying to keep it stable or tested.

Get the whole plugin

Other skills on tdder.

app
Skill

app

This skill should be used when the user asks to "calculate code mass", "measure code complexity with APP", "compare implementations using APP", "apply Absolute…

@t1@t1View Skill
clean-code
Skill

clean-code

This skill should be used when the user asks to "refactor code", "review code quality", "apply clean code principles", "check for code smells", "improve code…

@t1@t1View Skill
java
Skill

java

Always load this skill when writing, modifying, creating, or moving Java or Kotlin source code, or when project setup has already chosen Java/Kotlin as the…

@t1@t1View Skill
maven
Skill

maven

Always load this skill when a pom.xml file exists in the project, when creating or editing a pom.xml, or when setting up Maven project structure in a new…

@t1@t1View Skill