grill-with-docs
Relentless interview that sharpens a plan or design while writing the domain docs — glossary and ADRs — as decisions land.
Skill by OpalBolt
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/opalbolt-grill-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, writing
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-with-docs
What's inside
- Skill name
grill-with-docs- Description
- Relentless interview that sharpens a plan or design while writing the domain docs — glossary and ADRs — as decisions land. Invoke with /grill-with-docs.
- License
- MIT
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (3)
- ADR-FORMAT.md
- CONTEXT-FORMAT.md
- SKILL.md
SKILL.md (first lines)
# Grill With Docs Run `grilling` for the interview mechanics — rounds, frontier, recommended answers. This skill adds the domain discipline: while you grill, build and sharpen the project's domain model and write it down the moment it crystallises. ## During the session - **Challenge against the glossary.** When a term conflicts with `CONTEXT.md`, call it out immediately: "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?" - **Sharpen fuzzy language.** When a term is vague or overloaded, propose a precise canonical one: "'account' — the Customer or the User? Those are different things." - **Discuss concrete scenarios.** When domain relationships come up, stress-test them with edge-case scenarios that force precision about the boundaries between concepts. - **Cross-reference with code.** When the user states how something works, check the code agrees; surface contradictions: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?" ## Capturing - **Update `CONTEXT.md` inline, as each term is resolved** — batching loses them. It is a glossary and nothing else: define what a term IS, keep implementation detail, specs, and scratch out. Format and multi-context layout: [CONTEXT-FORMAT.md](CONTEXT-FORMAT.md). - **Create files lazily** — only when you have something to write. First resolved term creates `CONTEXT.md`; first ADR creates `docs/adr/`. - **Offer an ADR when all three hold:** hard to reverse, surprising without context, a real trade-off. Format and what qualifies: [ADR-FORMAT.md](ADR-FORMAT.md). ## Persist when the session ends early If the frontier won't empty in one sitting, don't force it. Write the destination, the decisions so far, and the remaining open questions to `.scratch/<effort>/map.md` (or wherever the repo's AGENTS.md names as the artifact home). A later session resumes by loading that file and continuing the interview from its frontier. The map is scratch, not an artifact: crystallised terms go to `CONTEXT.md`, real trade-offs to ADRs, and once `to-spec` synthesizes the session the map file is disposable. When the frontier empties and the user confirms shared understanding, hand off to `to-spec` to synthesize the session into a spec.
From OpalBolt/Personal-AI-Marketplace, MIT.
More from OpalBolt/Personal-AI-Marketplace
- 0.598score
orchestrator
OpalBolt
Run a pre-sliced plan to completion, unattended.
SkillAFreshness: A★ 2Claude Code +9 - 0.557score
agent-writer
OpalBolt
Write or regenerate the root AGENTS.md context file for a project by introspecting the repo and interviewing the user for only what cannot be inferred.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
git-commit
OpalBolt
Write well-formed git commit messages following Conventional Commits, enforce issue references, and ensure commit bodies explain why — not what.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
issue
OpalBolt
Expand a rough idea into a well-structured, actionable issue — then create it in the right tracker (GitHub, Linear, Jira).
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
pr
OpalBolt
Create a well-structured GitHub pull request that gives the reviewer full context: what issue is being addressed, what problem it solves, what changed, why…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
markdown-writer
OpalBolt
Write markdown that reads human, not AI slop — READMEs, docs, guides, comments, PR text.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
jam-with-me
OpalBolt
Thinking-partner session that turns a rough idea into a concise idea bundle through open-ended conversation.
SkillBFreshness: B★ 2Claude Code +9 - 0.532score
prototype
OpalBolt
Build a throwaway prototype to answer a design question.
SkillBFreshness: B★ 2Claude Code +9 - 0.532score
grilling
OpalBolt
Grill the user relentlessly about a plan, decision, issue, or idea until nothing is silently assumed — rounds of frontier questions, each with a recommended…
SkillBFreshness: B★ 2Claude Code +9 - 0.532score
code-review
OpalBolt
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding…
SkillBFreshness: B★ 2Claude Code +9 - 0.531score
writing-for-agents
OpalBolt
Writing documents for agents.
SkillBFreshness: B★ 2Claude Code +9 - 0.529score
to-tickets
OpalBolt
Break a plan, spec, or the current conversation into tracer-bullet tickets with blocking edges, published to the repo's tracker.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Aug 24, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from OpalBolt
- 0.598score
orchestrator
OpalBolt
Run a pre-sliced plan to completion, unattended.
SkillAFreshness: A★ 2Claude Code +9 - 0.557score
git-commit
OpalBolt
Write well-formed git commit messages following Conventional Commits, enforce issue references, and ensure commit bodies explain why — not what.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
agent-writer
OpalBolt
Write or regenerate the root AGENTS.md context file for a project by introspecting the repo and interviewing the user for only what cannot be inferred.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
issue
OpalBolt
Expand a rough idea into a well-structured, actionable issue — then create it in the right tracker (GitHub, Linear, Jira).
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
pr
OpalBolt
Create a well-structured GitHub pull request that gives the reviewer full context: what issue is being addressed, what problem it solves, what changed, why…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
markdown-writer
OpalBolt
Write markdown that reads human, not AI slop — READMEs, docs, guides, comments, PR text.
SkillBFreshness: B★ 2Claude Code +9
Cite this page
grill-with-docs skill. Agent Mart. https://agentmart.dev/skills/opalbolt-grill-with-docs (last updated 2026-10-24)