grilling
Interview the user until a plan, design, or decision is fully specified, by working a design tree in rounds rather than asking questions as they occur.
Skill by fblissjr
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/fblissjr-grilling
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, agent-building
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/grilling
What's inside
- Skill name
grilling- Description
- Interview the user until a plan, design, or decision is fully specified, by working a design tree in rounds rather than asking questions as they occur. Each round asks every question whose prerequisites are already settled, with a recommended answer attached, and the session ends when nothing is left unasked. Use when the user says "grill me", "stress-test this", "poke holes in this", "interview me", "what am I not thinking about", or when a plan is about to be built and its unknowns have not been enumerated. Finding facts is the agent's job; only decisions go to the user. Do NOT use to review work already done (use a postmortem or code review) or to answer a question the codebase can settle on its own.
- License
- Apache-2.0
- Instructions
- 71 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Grilling Interview relentlessly until you and the user share an understanding of the thing. Not a conversation that wanders toward clarity: a tree, worked systematically. ## The tree and the frontier Map the problem as a **design tree**. Every decision branches into the decisions that hang off it. The **frontier** is every decision whose prerequisites are already settled — the questions answerable *now*, without guessing at answers you have not heard yet. That word is doing the work: it is what separates this from asking questions in the order they occur to you. A question whose answer depends on another question still open belongs to a later round, not this one. Asking it now produces an answer the user will revise, and revised answers quietly invalidate everything built on them. ## Rounds Ask the whole frontier in one round. Then wait. Each answer reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. Every question carries your recommended answer. A bare question makes the user do the thinking twice. A recommendation they can accept, reject, or amend costs them one judgment instead. Ask in numbered plain text, one block per question, with the options inline where there are any. Use the `AskUserQuestion` picker only when the user asks for it by name: a picker hides the tradeoffs a recommendation needs. ```text Q1 — <question title> <the question, including the options if there are any> Recommended: <your answer, and the one-line reason> ``` ## Facts are yours, decisions are theirs Look up anything the environment can answer instead of asking. File contents, which version is installed, what the config already says, whether a thing already exists: go and look. A question the codebase settles is a question that wastes the user's turn and signals you did not check. When a frontier question needs a fact you do not have, dispatch the lookup and keep going. A running exploration is an unsettled prerequisite, so only the questions downstream of it wait. Ask the rest of the frontier now rather than blocking the round on one lookup. Delegate the lookup rather than doing it inline where the search is broad or the output is large — the point is to keep the interview in the main thread and the file-reading out of it. The decisions are the user's. Put each one to them and wait: a decision inferred from a previous answer, or taken from silence, is one the user never made. ## Done The session is done when the frontier is empty: every branch visited, nothing left silently assumed. Do not act on the design until the user confirms you have reached a shared understanding. Reaching the end of the questions is not the same as agreement.
From fblissjr/fb-claude-skills, Apache-2.0.
More from fblissjr/fb-claude-skills
- 0.603score
heylook-provider
fblissjr
Wire an application to heylook (heylookitsanllm), a local multimodal LLM server on Apple Silicon serving MLX and gguf models over one Anthropic…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
skill-dashboard
fblissjr
Show an interactive dashboard of all tracked skills, plugins, and repo hygiene in this project.
SkillAFreshness: A★ 2Claude Code +9 - 0.563score
design-scoreboard
fblissjr
Designs what an improvement or optimizer loop should climb for a given project and goal, and what must not get worse while it does: goal metrics measured on…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
mece-decomposer
fblissjr
MECE decomposition methodology, scoring rubrics, and Agent SDK mapping for process analysis.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
python-tooling
fblissjr
House Python conventions plus the type-checking failures that get misdiagnosed: the dependency pinning policy (applications exact, libraries floors), the rule…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
dimensional-modeling
fblissjr
Design and implement Kimball-style star schemas in DuckDB for LLM agent state persistence.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
improve
fblissjr
Runs one improvement pass over a project in the direction its north star points, without breaking what it does today: faster in real use, less code, a truer…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
optimize
fblissjr
Speeds up a codebase as far as it will go in one session, against a hard target (every primary benchmark at least 1.2x faster than the base commit by default)…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
trim-agents-md
fblissjr
Tightens a repository's always-loaded agent instructions (AGENTS.md, CLAUDE.md, unconditional rules): every line must prevent a mistake, and each one that…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
json-query
fblissjr
Guide JSON query tool selection and syntax.
SkillBFreshness: B★ 2Claude Code +9 - 0.558score
gemini-multimodal
fblissjr
Send a task to a Gemini model and get a structured answer back - perceptual work Claude cannot do directly, or any ad-hoc question worth a second model's take.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
doc-conventions
fblissjr
House documentation conventions that are not derivable from the repo: last-updated dates, where unshared notes and session logs live, how dependency changes…
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/fblissjr/fb-claude-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fblissjr
- 0.603score
heylook-provider
fblissjr
Wire an application to heylook (heylookitsanllm), a local multimodal LLM server on Apple Silicon serving MLX and gguf models over one Anthropic…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
skill-dashboard
fblissjr
Show an interactive dashboard of all tracked skills, plugins, and repo hygiene in this project.
SkillAFreshness: A★ 2Claude Code +9 - 0.563score
dimensional-modeling
fblissjr
Design and implement Kimball-style star schemas in DuckDB for LLM agent state persistence.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
mece-decomposer
fblissjr
MECE decomposition methodology, scoring rubrics, and Agent SDK mapping for process analysis.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
python-tooling
fblissjr
House Python conventions plus the type-checking failures that get misdiagnosed: the dependency pinning policy (applications exact, libraries floors), the rule…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
improve
fblissjr
Runs one improvement pass over a project in the direction its north star points, without breaking what it does today: faster in real use, less code, a truer…
SkillBFreshness: B★ 2Claude Code +9
Cite this page
grilling skill. Agent Mart. https://agentmart.dev/skills/fblissjr-grilling (last updated 2026-10-24)