grill-with-docs
๐ฏSkillfrom mattpocock/skills
|A skill that runs a grilling session to challenge your plan against an existing domain model, sharpen terminology by building a shared language in CONTEXT.md, and document architectural decisions in ADRs before coding begins.
Overview
A skill from Matt Pocock's "Skills For Real Engineers" collection that runs a grilling session where the AI agent asks you detailed questions about what you are building before any coding starts. It goes beyond the basic /grill-me skill by challenging your plan against the existing domain model, building shared language in a CONTEXT.md file, and documenting architecture decisions in ADRs. The goal is to close the communication gap between developer and agent that is the most common source of misalignment.
Key Features
- Structured grilling session where the agent asks detailed questions to fully understand your requirements before writing code
- Builds and maintains a CONTEXT.md file that captures shared domain language and terminology
- Documents architecture decision records (ADRs) based on the grilling session outcome
- Works with any coding agent model and composes with other skills in the mattpocock/skills toolkit
Who is this for?
- Developers who have experienced the frustration of an AI agent building something that does not match their intent
- Engineers who want to establish clear domain language and architecture decisions before implementation begins
- Teams using AI coding agents on complex projects where misalignment leads to costly rework
Same repository
mattpocock/skills(35 items)
Installation
npx vibeindex add mattpocock/skills --skill grill-with-docsnpx skills add mattpocock/skills --skill grill-with-docs~/.claude/skills/grill-with-docs/SKILL.mdSKILL.md
More from this repository10
Interviews the user relentlessly about every aspect of a plan or design until reaching shared understanding, resolving each branch of the decision tree one by one. Provides recommended answers for each question and explores the codebase when answers can be found there.
An agent skill from Matt Pocock's engineering toolkit that helps improve your codebase architecture. Part of a composable skill set designed to fix common AI coding agent failure modes through structured, experience-based workflows.
Enforces test-driven development with a strict red-green-refactor loop using vertical slices (one test then one implementation at a time), emphasizing behavior verification through public interfaces rather than implementation-coupled testing.
A skill that turns the current conversation context and codebase understanding into a structured PRD (Product Requirements Document) and submits it as a GitHub issue, with modular architecture and user story generation.
A skill that guides AI agents through a disciplined diagnosis loop for hard bugs and performance regressions, following a structured sequence of reproduce, minimise, hypothesise, instrument, fix, and regression-test steps.
Breaks a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Each issue is a thin end-to-end path through every integration layer that can be demoed or verified on its own.
A meta-skill that guides the process of creating new agent skills with proper SKILL.md structure, progressive disclosure, and bundled resources. It helps gather requirements, draft skill files, and write effective descriptions.
Instructs the AI agent to step back from detailed code and provide a higher-level perspective, mapping all relevant modules and callers to help developers understand how a section of code fits into the broader architecture.
Initial setup skill for Matt Pocock's engineering skills collection that configures your backlog manager, triage labels, and documentation paths for AI coding agents.
Ultra-compressed communication mode that reduces token usage by approximately 75% by dropping filler words, articles, and pleasantries while preserving full technical accuracy in responses.