grill-me SKILL.md skillA

grill-me from melvynx/ai-maxxing-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add melvynx/ai-maxxing-skills/grill-me@git:20261019.89dfcfa

Pins git:20261019.89dfcfa in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
melvynx/ai-maxxing-skills
Path
skills/grill-me/SKILL.md
Versions recorded
5
Latest version
git:20261019.89dfcfa, committed Oct 19, 2026
First version recorded
Oct 19, 2026
Size
5,675 bytes
Repository stars
3
License
MIT

Interview the user in batches of 10 questions with recommended answers to sharpen a plan, an idea or an app before building. Use when the user says grill me, wants a rigorous interview, or when create-software, create-internal-app or create-landing needs a confirmed brief.

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

Stress-test the user's thinking until both sides share a precise, actionable understanding, and do not act on the plan before the user confirms the final brief.

1. Inspect the available environment first. Resolve discoverable facts through files, tools, documentation, or other in-scope evidence instead of asking the user.
2. Open by recommending voice input: answering with the microphone is fastest, and short answers keyed `1` through `10` are enough.
3. Ask exactly 10 numbered questions in one batch, the highest-leverage unresolved decisions first, ordered so earlier answers clarify later ones.
4. Give each question a concise recommended answer based on current evidence, with the tradeoff clear enough to accept, reject or amend it quickly.
5. Invite one grouped reply covering `1` through `10`. Accept terse answers, corrections, skipped items, or a blanket acceptance of the recommendations.
6. After the reply, summarize what is established, call out contradictions or missing dependencies, and investigate any newly discoverable facts.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add melvynx/ai-maxxing-skills/grill-me@sha256:5b0d8251e1a6d43c

The line at the top of this page pins the label git:20261019.89dfcfa, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_te4lgpmaiqgfpolx.svg)](https://markdownregistry.com/a/art_te4lgpmaiqgfpolx)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, all committed on Oct 19, 2026.

versioncommittedcommitsizeaudit
git:20261019.89dfcfa latest2026-10-19 89dfcfa 5,675 BA view · diff
git:20261019.6bd83672026-10-19 6bd8367 6,866 BA view · diff
git:20261019.6a20a852026-10-19 6a20a85 5,811 BA view · diff
git:20261019.662813d2026-10-19 662813d 4,220 BA view · diff
git:20261019.894f03d2026-10-19 894f03d 4,178 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5675 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

melvynx/ai-maxxing-skills · 3 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_te4lgpmaiqgfpolx
GET https://markdownregistry.com/api/v1/resolve?ref=melvynx/ai-maxxing-skills/grill-me
GET https://markdownregistry.com/api/v1/blob/5b0d8251e1a6d43c9f962ee000e9df34ee6e21c199efa710dafb02d134741bc5

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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from melvynx/ai-maxxing-skills

audit-safety SKILL.md skill
melvynx/ai-maxxing-skills · skills/audit-safety/SKILL.md · Audit one feature of a web app (TanStack Start, Next.js, Convex) for authorization, tenant isolation, ownership…
git:20261021.81ed9c7 · audit A · 3 stars
cloudflare SKILL.md skill
melvynx/ai-maxxing-skills · skills/cloudflare/SKILL.md · Run every Cloudflare job through the official `cf` CLI - domains, DNS, Workers deploys, secrets and custom domains, KV…
git:20261021.b9e7ed0 · audit A · 3 stars
code-debug SKILL.md skill
melvynx/ai-maxxing-skills · skills/code-debug/SKILL.md · Debug hard bugs and performance regressions with a tight red-capable loop, falsifiable hypotheses, a focused fix…
git:20261017.7124864 · audit A · 3 stars
connect-tool SKILL.md skill
melvynx/ai-maxxing-skills · skills/connect-tool/SKILL.md · Connect any tool (Notion, Stripe, ClickFunnels...) to every agent: install its official CLI, or write a one-file Python…
git:20261021.81ed9c7 · audit A · 3 stars
connect-vps SKILL.md skill
melvynx/ai-maxxing-skills · skills/connect-vps/SKILL.md · Connect the user's VPS (Hostinger, Hetzner, OVH...) to their terminal as `ssh hermes`, finding the server and its SSH…
git:20261021.a064743 · audit B · 3 stars
convex SKILL.md skill
melvynx/ai-maxxing-skills · skills/convex/SKILL.md · Set up, secure and optimize a Convex backend. Use for Convex project setup, schema and indexes, queries and mutations…
git:20261021.b9e7ed0 · audit A · 3 stars
create-internal-app SKILL.md skill
melvynx/ai-maxxing-skills · skills/create-internal-app/SKILL.md · Create a private internal app on the user's VPS through Dokploy, locked by password and IP allowlist, then hand it to…
git:20261021.81ed9c7 · audit A · 3 stars
create-landing SKILL.md skill
melvynx/ai-maxxing-skills · skills/create-landing/SKILL.md · Create a landing page, sales page or waitlist on Cloudflare with TanStack Start, shadcn/ui, a Lumail email form and an…
git:20261021.81ed9c7 · audit A · 3 stars
create-software SKILL.md skill
melvynx/ai-maxxing-skills · skills/create-software/SKILL.md · Create and deploy a public web app on Cloudflare with TanStack Start, shadcn/ui, Convex, Better Auth, Lumail and…
git:20261021.81ed9c7 · audit A · 3 stars
dev-browser SKILL.md skill
melvynx/ai-maxxing-skills · skills/dev-browser/SKILL.md · Drive the user's dedicated Chrome AI window with the dev-browser CLI to open sites, click, fill forms, read pages, take…
git:20261021.81ed9c7 · audit B · 3 stars
install-skills SKILL.md skill
melvynx/ai-maxxing-skills · skills/install-skills/SKILL.md · Install skills of the ai-maxxing package on the user's VPS so their Hermes agent (and Claude Code on the server) can…
git:20261021.ed411d1 · audit A · 3 stars
lumail SKILL.md skill
melvynx/ai-maxxing-skills · skills/lumail/SKILL.md · Manage Lumail email marketing from Claude with the Lumail CLI or MCP. Use for setup and login, sending domains and DNS…
git:20261021.b9e7ed0 · audit A · 3 stars

Every file in melvynx/ai-maxxing-skills

Other files named grill-me

grill-me SKILL.md skill
vinvcn/mattpocock-skills-zh-cn · skills/productivity/grill-me/SKILL.md · 一个用来打磨计划或设计的持续追问式访谈。
git:20260921.49ef591 · audit B · 5,110 stars
grill-me SKILL.md skill
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…
git:20261008.e34244d · audit A · 2,665 stars
grill-me SKILL.md skill
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.
git:20261015.4e92754 · audit A · 598 stars
grill-me SKILL.md skill
kunolu/640-skills · sbtd-workflow-onboard/assets/external-skills/stable/skills/grill-me/SKILL.md · A relentless interview to sharpen a plan or design.
git:20260827.561ec6a · audit B · 555 stars
grill-me SKILL.md skill
asymmetric-al/core · .agents/skills/grill-me/SKILL.md · A relentless interview to sharpen a plan or design.
git:20260923.15c9348 · audit B · 379 stars
grill-me SKILL.md skill
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…
git:20260701.d165932 · audit A · 231 stars
grill-me SKILL.md skill
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…
git:20260510.a8b8231 · audit A · 177 stars
grill-me SKILL.md skill
open-octo/octo-agent · internal/skills/defaults/grill-me/SKILL.md
git:20260713.070d20e · audit B · 135 stars

Browse by kind, by grade A, or by owner.