Interview the user relentlessly about a plan, project, workflow, or design until you reach shared understanding. Make sure to use this whenever the user wants to be grilled, stress-test an idea, clarify a new project, surface missing context, or think through decisions before execution.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
Interview me relentlessly about every important aspect of this plan until we reach a shared understanding.
Walk down each branch of the decision tree, resolving dependencies one by one. For each question, provide your recommended answer, but stay open to correction.
Ask questions one at a time.
If a question can be answered by exploring the codebase, existing docs, available memory, or context already present in the session, explore that first instead of asking me to repeat it.
When relevant, begin by identifying what kind of project this is and what context already exists. Distinguish between:
- what is already decided
- what is assumed but unverified
- what is still open
Do not depend on any specific file path or agent harness. Use whatever context is available in the current environment. If important context is missing, ask me to provide it.
As the discussion progresses, periodically checkpoint the emerging understanding in a lightweight way. Keep track of:
- key decisions made
- important constraints
- assumptions
- unresolved questions
- items that need external verification
…
The line at the top of this page pins the label git:20260611.b2584e4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_vepx7njojrmjbyhq
GET https://markdownregistry.com/api/v1/resolve?ref=valtterimelkko/agent-workflow-skills/grill-me
GET https://markdownregistry.com/api/v1/blob/17511776a906320947c5f660a8afa138f3562df64189cdb8863da7a6a9e12057
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
valtterimelkko/agent-workflow-skills · skills/academic-writing/SKILL.md · Comprehensive guide for British academic writing best practices. Use when helping users write academic papers, research…
valtterimelkko/agent-workflow-skills · skills/agent-os-child/SKILL.md · Execute one dispatched task as a child worker (implementer, researcher or reviewer) under a parent agent, in…
valtterimelkko/agent-workflow-skills · skills/agy-p/SKILL.md · Reference for building scripted and programmatic integrations around the Antigravity CLI (`agy`) non-interactive print…
valtterimelkko/agent-workflow-skills · skills/artifact-variations/SKILL.md · Generate many design, copy, or layout variations as a single browsable HTML artifact so the user can pick favorites…
valtterimelkko/agent-workflow-skills · skills/audio-transcription-workflow/SKILL.md · Transcribe local audio files or voice notes into markdown files using the legacy VoiceNote Bot workflow: local Whisper…
valtterimelkko/agent-workflow-skills · skills/capture-dashboard/SKILL.md · Capture authenticated dashboards as screenshots and/or HTML using cookies, with safe same-origin crawling. Use when the…
valtterimelkko/agent-workflow-skills · skills/claude-channels/SKILL.md · Build MCP channel plugins that push external events into a running Claude Code interactive session and bridge…
valtterimelkko/agent-workflow-skills · skills/claude-p/SKILL.md · Use when running multi-turn Claude Code CLI sessions programmatically via 'claude -p', integrating Claude into…
valtterimelkko/agent-workflow-skills · skills/context7-docs/SKILL.md · Fetch up-to-date documentation from Context7 for a library. Use when you need current API syntax, code examples, or…
valtterimelkko/agent-workflow-skills · skills/context7-search/SKILL.md · Search for libraries in Context7. Use when the user mentions a library by name and you need to find its exact Context7…
plugin87/ux-ui-agent-skills · .claude/skills/grill-me/SKILL.md · Interrogate the brief before a line is built — ask only the questions whose answers change the work, and put every…
zhongkaifu/tensorsharp · TensorAgent/skills/grill-me/SKILL.md · Interview the user to stress-test a plan or decision, one independent set of questions at a time.
serejaris/personal-corp-os · skills/grill-me/SKILL.md · Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of…
intent-driven-dev/intent-driven-template · .agents/skills/grill-me/SKILL.md · Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of…
