Skip to content
Agentmart
Submit a tool

grill-me-with-docs

Relentlessly interview the user to stress-test a problem, architecture, or design from scratch, while actively maintaining a domain glossary (CONTEXT.md) and…

Skill by MAHDTech

IndexedMIT
Write a review

Chalk Labs

Need help deploying grill-me-with-docs?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mahdtech-grill-me-with-docs

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Relentlessly interview the user to stress-test a problem, architecture, or design from scratch, while actively maintaining a domain glossary (CONTEXT.md) and recording major architectural decisions as ADRs. Use when starting a new initiative, tackling ambiguous domain problems, or when the user asks to grill with docs or ADRs.

Use cases: design, testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/grill-me-with-docs

What's inside

Skill name
grill-me-with-docs
Description
Relentlessly interview the user to stress-test a problem, architecture, or design from scratch, while actively maintaining a domain glossary (CONTEXT.md) and recording major architectural decisions as ADRs. Use when starting a new initiative, tackling ambiguous domain problems, or when the user asks to grill with docs or ADRs.
License
MIT
Metadata
source: mattpocock/skills · license: MIT · archived: 2026-10-10 · replaced-by: grilling
Instructions
63 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Grill Me with Docs

The comprehensive entry point into an ambiguous problem or architectural initiative. This skill combines the relentless 1-at-a-time decision interview of `/grilling` with active domain modeling and decision capture.

## The Workflow

```text
Problem / Idea
  │
  ├── 1. Relentless Interview Loop (1 decision at a time with recommendations)
  │     ├── Automated fact-finding via codebase / documentation
  │     └── User-confirmed decisions across the design tree
  │
  ├── 2. Live Domain Modeling
  │     └── Update CONTEXT.md whenever vocabulary or boundaries crystallize
  │
  ├── 3. Architectural Decision Records (ADRs)
  │     └── Create docs/adr/000X-*.md when hard-to-reverse trade-offs are settled
  │
  └── 4. Shared Understanding Confirmed → Handoff to /to-spec or /to-tickets
```

## 1. The Interview Loop

- **One decision at a time.** Walk the branches of the design tree sequentially.
- **Provide clear recommendations.** State options with pros/cons, flagging the recommended path.
- **Find facts autonomously.** Inspect the filesystem, code, and configs before asking.
- **Use interactive tooling.** Use `ask_question` or structured selection prompts where available.

## 2. Real-time Glossary (`CONTEXT.md`)

As terms, boundaries, and concepts are clarified during the interview, record them immediately in `CONTEXT.md`. Do not wait until the end of the session.

- **Check against existing terms:** Call out conflicting or overloaded words ("You said 'account' - do you mean Customer or User?").
- **Keep it free of implementation details:** `CONTEXT.md` is a ubiquitous language glossary, not a technical spec.
- Follow standard ubiquitous language glossary conventions: definitions, boundary rules, and rejected terms.

## 3. Recording Architectural Decision Records (ADRs)

Only create an ADR when a settled decision meets all three criteria:

1. **Hard to reverse** - High cost to change later (e.g. database choice, communication protocol, core boundary).
2. **Surprising without context** - Future engineers would ask "why did they build it this way?".
3. **Real trade-off** - Chosen among genuine alternatives with distinct advantages and disadvantages.

When all three are met, create `docs/adr/000X-slug.md` documenting context, decision, and consequences.

## 4. Closing the Session

The session finishes when:

1. All open branches of the design tree are explored and settled.
2. The `CONTEXT.md` glossary reflects all defined domain terms.
3. Key hard-to-reverse choices are recorded in `docs/adr/`.
4. The user explicitly confirms shared understanding.

## Handoffs

- **To Technical Spec:** Run `/to-spec` to synthesize the settled architecture into an issue or PRD.
- **To Backlog Decomposition:** Run `/to-tickets` to break the decisions down into atomic, dependency-mapped tickets.
- **Pure Interview:** If no glossary or ADR documentation is needed, reach for `/grilling`.

From MAHDTech/agent-skills, MIT.

More from MAHDTech/agent-skills

Signals

Stars
0
Forks
0
Open issues
30
Last commit (this folder)
Oct 10, 2026 (22 days ago)
Last release
Oct 23, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from MAHDTech

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get grill-me-with-docs running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying grill-me-with-docs?

CallGet help
Cite this page

grill-me-with-docs skill. Agent Mart. https://agentmart.dev/skills/mahdtech-grill-me-with-docs (last updated 2026-10-24)