Automated summary
Interviews the user one question at a time, each with a recommended answer, to stress-test a plan or design until decisions and remaining unknowns are explicit.
Strengths
- Asks a single question at a time with a recommended answer, so the user reacts to a concrete position instead of a blank page
- Walks the design tree branch by branch, resolving dependencies between decisions
- Inspects the codebase rather than asking whenever a question can be answered from the code
- Stops once major branches are resolved, remaining unknowns are explicit, and a clear next action exists
Limitations
- Produces no written artifact: it does not generate a spec or decision record
- Assumes the user is willing to sit through a long sequence of questions
- Focuses on design decisions, not implementation or verification of the outcome
Use it before committing to a plan or design that still has unresolved tradeoffs and hidden assumptions.
Avoid it when the plan is already fully specified or when you want code produced rather than questions asked.
Security analysis
SafeThe skill contains only interviewing and planning guidance. It declares no tools, runs no commands, makes no network calls, and handles no secrets or destructive actions. The only potentially tool-adjacent instruction is to inspect the codebase when a question can be answered there, which is a normal read-oriented code activity and not a meaningful execution risk.
No concerns found
How this analysis is madeExamples
Grill me on my plan to split our Rails monolith into three services — one question at a time, with your recommendation for each.I'm designing an offline-first sync layer. Grill me until the tradeoffs, failure modes, and open questions are clear.Before I write the RFC for our new auth system, grill me on the decisions I haven't made yet.name: grill-me description: Stress-test a user's plan or design by interviewing them through the decision tree until shared understanding is reached. Use when the user wants to be grilled, stress-test a plan, sharpen a design, or mentions "grill me". license: MIT version: 0.1.0 homepage: https://github.com/mattpocock/skills/tree/main/skills/productivity/grill-me compatibility: claude-code: supported codex: supported pi-agent: supported metadata: upstream: mattpocock/skills/skills/productivity/grill-me
Grill Me
Interview the user relentlessly about their plan until there is shared understanding.
Workflow
Ask one question at a time. Walk down each branch of the design tree and resolve dependencies between decisions one by one.
For each question, include the recommended answer so the user can react to a concrete position instead of starting from a blank page.
If a question can be answered by exploring the codebase, inspect the codebase instead of asking the user.
Question Style
Keep questions specific, consequential, and grounded in the user's stated goal. Prefer questions that expose tradeoffs, hidden assumptions, missing constraints, failure modes, sequencing risks, or ownership boundaries.
When the user answers, summarize the decision in one sentence, then move to the next unresolved branch.
Stop when the major branches are resolved, the remaining unknowns are explicit, and there is a clear next action.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/grill-me-mrwakfln/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/grill-me-mrwakfln' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/grill-me-mrwakfln/download' --output '.skill-downloads/grill-me-mrwakfln/SKILL.md.part' && mv '.skill-downloads/grill-me-mrwakfln/SKILL.md.part' '.skill-downloads/grill-me-mrwakfln/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/grill-me-mrwakfln/SKILL.md' && test -s '.skill-downloads/grill-me-mrwakfln/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/grill-me' && cp -R '.skill-downloads/grill-me-mrwakfln' '.claude/skills/grill-me'Codex
test -f '.skill-downloads/grill-me-mrwakfln/SKILL.md' && test -s '.skill-downloads/grill-me-mrwakfln/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/grill-me' && cp -R '.skill-downloads/grill-me-mrwakfln' '.agents/skills/grill-me'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/grill-me-mrwakfln'openskills read 'grill-me-mrwakfln'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/grill-me-mrwakfln/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.