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
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.
About
Use cases: design, testing
Reviews
Write a reviewNo 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. Checked Oct 25, 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
- 0.565score
delta
MAHDTech
Operate and configure Delta and DeltaDB, the multiplayer agent coding environment and CRDT version control system from Zed Industries.
SkillAFreshness: AClaude Code +9 - 0.565score
tauri
MAHDTech
Reference and development guidelines for Tauri v2+ cross-platform desktop and mobile apps.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-archive
MAHDTech
Retire a skill cleanly - move its directory from skills/<category>/ into skills-archive/<category>/, mark it archived in frontmatter with what replaced it…
SkillAFreshness: AClaude Code +9 - 0.565score
refactor-codebase
MAHDTech
Remove engineering debt, untangle large modules, collapse duplicated logic, and modernize legacy patterns without changing behavior.
SkillAFreshness: AClaude Code +9 - 0.565score
tars-backlog-create-issue
MAHDTech
Use when creating a new backlog issue/ticket in the `.tars/issues/todo/` directory, defining its YAML frontmatter, headings, tasks, acceptance criteria…
SkillAFreshness: AClaude Code +9 - 0.565score
opencode
MAHDTech
Guidance for using OpenCode, the open-source AI coding agent.
SkillAFreshness: AClaude Code +9 - 0.565score
opencode-acp
Benjamin Jesuiter <bjesuiter@gmail.com>
Control OpenCode directly via the Agent Client Protocol (ACP).
SkillAFreshness: AClaude Code +9 - 0.565score
skill-audit
MAHDTech
Periodically audit the whole skill collection for health - validate each skill's frontmatter, clarity, and category, verify every cross-reference resolves…
SkillAFreshness: AClaude Code +9 - 0.565score
skill-creator
MAHDTech
Use when creating a new skill or editing an existing one in this repo - how to name it, place it in the right category, write its frontmatter and description…
SkillAFreshness: AClaude Code +9 - 0.561score
tars-backlog-loop
MAHDTech
Coordinate the full backlog lifecycle by sequentially executing tars-backlog-audit, tars-backlog-triage, and tars-backlog-implement to resolve all issues.
SkillAFreshness: AClaude Code +9 - 0.561score
tars-backlog-audit
MAHDTech
Audit the codebase for bugs, features, security issues, or technical debt, and generate structured issue files in `.tars/issues/todo/`.
SkillAFreshness: AClaude Code +9 - 0.561score
tars-backlog-triage
MAHDTech
Triage pending backlog issues in `.tars/issues/todo/` to verify their accuracy, check for hallucinations, and add review notes.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 30
- Last commit (this folder)
- Oct 10, 2026 (18 days ago)
- Last release
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/MAHDTech/agent-skills
- Website
- skills.mahdtech.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MAHDTech
- 0.565score
delta
MAHDTech
Operate and configure Delta and DeltaDB, the multiplayer agent coding environment and CRDT version control system from Zed Industries.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-archive
MAHDTech
Retire a skill cleanly - move its directory from skills/<category>/ into skills-archive/<category>/, mark it archived in frontmatter with what replaced it…
SkillAFreshness: AClaude Code +9 - 0.565score
refactor-codebase
MAHDTech
Remove engineering debt, untangle large modules, collapse duplicated logic, and modernize legacy patterns without changing behavior.
SkillAFreshness: AClaude Code +9 - 0.565score
tauri
MAHDTech
Reference and development guidelines for Tauri v2+ cross-platform desktop and mobile apps.
SkillAFreshness: AClaude Code +9 - 0.565score
tars-backlog-create-issue
MAHDTech
Use when creating a new backlog issue/ticket in the `.tars/issues/todo/` directory, defining its YAML frontmatter, headings, tasks, acceptance criteria…
SkillAFreshness: AClaude Code +9 - 0.565score
opencode
MAHDTech
Guidance for using OpenCode, the open-source AI coding agent.
SkillAFreshness: AClaude Code +9
Cite this page
grill-me-with-docs skill. Agent Mart. https://agentmart.dev/skills/mahdtech-grill-me-with-docs (last updated 2026-10-24)