Skill

Sharpen plans through relentless interviews and docs

Run a relentless grilling interview that also captures ADRs and glossary terms via the domain-modeling skill as decisions are resolved.

Maintainer of this project? Claim this page to edit the listing.


75
Spark score
out of 100
Updated last month
Version 1.0.1

Add to Favorites

Why it matters

Run structured grilling sessions that challenge and refine technical plans or designs through adversarial questioning while automatically generating architectural decision records (ADRs) and glossary documentation as the conversation progresses.

Outcomes

What it gets done

01

Challenge design assumptions through systematic questioning

02

Generate architectural decision records during the interview

03

Build glossary documentation from domain modeling discussions

04

Validate technical plans against edge cases and constraints

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-grill-with-docs | bash

Overview

Grill With Docs

Runs a grilling interview using the domain-modeling skill so ADRs and glossary terms are captured automatically as design decisions are resolved. Use when a plan-sharpening interview should also produce a glossary and ADRs as it happens, not as a separate follow-up step.

What it does

Grill With Docs runs a /grilling session using the /domain-modeling skill, so the same relentless interview that sharpens a plan or design also produces documentation - Architecture Decision Records and a glossary - as decisions are resolved during the conversation, rather than requiring a separate documentation pass afterward.

When to use - and when NOT to

Use it when the request matches a relentless interview to sharpen a plan or design that should also create docs (ADRs and glossary) as it goes. If documentation output isn't needed, the plain Grilling/Grill Me variant covers the interview without the paired doc-writing.

Integrations

It combines two skills directly: the /grilling interview mechanism (one question at a time, with a recommended answer offered per question) drives the conversation, while /domain-modeling captures resolved terminology into CONTEXT.md and records architecture decisions as ADRs the moment each one crystallizes.

Who it's for

Teams sharpening a plan or design who want the resulting glossary and architectural decisions written down automatically as the interview happens, instead of interviewing first and documenting in a separate follow-up step.

Source README

When to Use

Use when this workflow matches the user request: A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

_Source: mattpocock/skills (MIT)._Run a /grilling session, using the /domain-modeling skill.

Limitations

  • Requires the upstream tool, account, API key, or local setup when the workflow names one.
  • Does not authorize destructive, production, paid, or external-message actions without explicit user approval.
  • Validate generated artifacts or recommendations against the user's real sources before treating them as final.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.