grill-me
Interview the user relentlessly about a plan or design, presenting choices one at a time until shared understanding is reached. Resolves every branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Best use case
grill-me is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Interview the user relentlessly about a plan or design, presenting choices one at a time until shared understanding is reached. Resolves every branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Teams using grill-me should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/grill-me/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How grill-me Compares
| Feature / Agent | grill-me | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Interview the user relentlessly about a plan or design, presenting choices one at a time until shared understanding is reached. Resolves every branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Grill Me Stress-test plans and designs through relentless, structured questioning before implementation begins. ## When to activate Activate when: - User says "grill me", "challenge my plan", "stress-test this", "interrogate my design", or any close variant - A new plan is being created and design decisions remain open - A design review is requested before committing to implementation ## Process Interview the user about every aspect of the plan until shared understanding is reached. Walk down each branch of the decision tree, resolving dependencies one-by-one. This skill is the canonical implementation of the [Grilling-With-Options Convention](../../../repo-governance/development/workflow/grilling-with-options.md) — that convention is the normative source for the format, mechanism, and scope below. Keep them in sync. **Rules (HARD — no exceptions):** 1. **Explore the codebase first** — if a question can be answered by reading existing files, read them instead of asking. Never ask what a file read can answer. 2. Present **2-4 concrete, mutually-exclusive options** per question, each with a one-sentence trade-off specific to this decision (no generic "this is simpler" filler) — open-ended questions without options are FORBIDDEN. If you cannot enumerate options, read the codebase first (Rule 1) and synthesize them before asking. 3. **Mark exactly one option Recommended** with a one-line rationale grounded in the repo state and the user's stated constraints. More than one Recommended is forbidden. 4. **One decision per question.** Tightly-coupled decisions (where one answer constrains the other) MAY be batched in a single multi-question prompt; unrelated decisions MUST NOT be bundled. 5. The user can always supply an **unlisted write-in answer** — options are a starting point, not a cage. Treat a write-in with the same weight as a listed option; if it opens a new branch, grill on that branch. 6. Continue until all branches are resolved — do not stop early. **Violation of Rule 2 (asking without options) is the most common failure mode.** If you catch yourself writing a question without listing concrete options, rewrite it with options before sending. ## Mechanism — use the AskUserQuestion tool Grilling MUST use the **`AskUserQuestion` tool** (the harness's native interactive multiple-choice mechanism), not free-text prose questions. It renders options as selectable choices and returns a structured answer — eliminating parse ambiguity — and always offers a free-form "Other" path. - One `AskUserQuestion` call carries 1–4 questions; use multiple questions only for tightly-coupled decision clusters (Rule 4). - Each question carries 2–4 options (Rule 2); put the Recommended one first and append `(Recommended)` to its label with the rationale in its description (Rule 3). **Fallback only when `AskUserQuestion` is unavailable** (non-interactive harness): use inline markdown options instead, still satisfying Rules 2–5: > **[Question]** > > - **Option A**: [description] — [trade-off] **(Recommended — [rationale])** > - **Option B**: [description] — [trade-off] > - **Option C**: [description] — [trade-off] > - **Other**: write in your own approach. No bare "What do you think about X?" questions. No yes/no questions without an options list. Present the choices; let the user pick or override. ## After the grilling When all decision tree branches are resolved: 1. Summarize every decision made and its rationale 2. Confirm shared understanding explicitly 3. Signal readiness to proceed to plan writing or implementation
Related Skills
nx-workspace
Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.
nx-run-tasks
Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.
nx-plugins
Find and add Nx plugins. USE WHEN user wants to discover available plugins, install a new plugin, or add support for a specific framework or technology to the workspace.
nx-import
Import, merge, or combine repositories into an Nx workspace using nx import. USE WHEN the user asks to adopt Nx across repos, move projects into a monorepo, or bring code/history from another repository.
nx-generate
Generate code using nx generators. INVOKE IMMEDIATELY when user mentions scaffolding, setup, structure, creating apps/libs, or setting up project structure. Trigger words - scaffold, setup, create a ... app, create a ... lib, project structure, generate, add a new project. ALWAYS use this BEFORE calling nx_docs or exploring - this skill handles discovery internally.
monitor-ci
Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. Prefer this skill over native CI provider tools (gh, glab, etc.) for CI monitoring — it integrates with Nx Cloud self-healing which those tools cannot access.
link-workspace-packages
Link workspace packages in monorepos (npm, yarn, pnpm, bun). USE WHEN: (1) you just created or generated new packages and need to wire up their dependencies, (2) user imports from a sibling package and needs to add it as a dependency, (3) you get resolution errors for workspace packages (@org/*) like "cannot find module", "failed to resolve import", "TS2307", or "cannot resolve". DO NOT patch around with tsconfig paths or manual package.json edits - use the package manager's workspace commands to fix actual linking.
swe-programming-typescript
TypeScript coding standards from authoritative docs/explanation/software-engineering/programming-languages/typescript/ documentation
swe-programming-rust
Rust coding standards from authoritative docs/explanation/software-engineering/programming-languages/rust/ documentation
swe-programming-golang
Go coding standards from authoritative docs/explanation/software-engineering/programming-languages/golang/ documentation
swe-programming-fsharp
F# coding standards from authoritative docs/explanation/software-engineering/programming-languages/f-sharp/ documentation
swe-programming-csharp
C# coding standards from authoritative docs/explanation/software-engineering/programming-languages/c-sharp/ documentation