grill-me is agent-read markdown (skill) from leeyudok/agents-scaffold: Use when the user invokes /grill-me or asks to have an idea, feature request, or spec grilled, stress-tested, interrogated, or challenged before implementation. Opt-in alternative to superpowers:brainstorming — the user picks one or the other per task..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Grill Me — adversarial requirements interrogation
> An original skill inspired by — and designed as an opt-in alternative to — the
> `brainstorming` skill from [obra/superpowers](https://github.com/obra/superpowers) (MIT);
> the downstream workflow (plan → TDD → review) follows the superpowers process.
Interrogate the user's idea until the spec stops changing, then hand a hardened spec
to the normal implementation flow. Explicitly invoking this skill substitutes for
`superpowers:brainstorming` for the current task; everything downstream
(plan → TDD → review) is unchanged.
**This is a multi-round interview, not a questionnaire.** The failure mode to avoid:
firing one batch of clarifying questions, accepting the answers at face value, and
jumping to design. Each round digs into the previous round's answers.
## Procedure
1. **Announce the mode.** One line: you will grill the idea before any code, and the
output will be a hardened spec. No implementation, no design proposals until step 5.
2. **Round loop.** Ask **at most 3 questions per round**, all on one theme, then wait
for answers. Pick the sharpest unresolved theme each round, in rough order:
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_7zenxyk6jono7crw
GET https://markdownregistry.com/api/v1/resolve?ref=leeyudok/agents-scaffold/grill-me
GET https://markdownregistry.com/api/v1/blob/f26db5598714f486859c83c2805fd4985cf159c96c5730167e9de963a80ae958
Your agent 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.
leeyudok/agents-scaffold · .claude/skills/docs-sync/SKILL.md · 코드·설정·프리셋 변경 뒤 문서를 현행화한다. "문서 현행화", "README 갱신", "문서 최신화" 요청 시, 그리고 동작·경로·버전·수치를 바꾼 PR 을 올리기 직전에 사용. 문서의 주장을 실제 코드·명령…
leeyudok/agents-scaffold · .claude/skills/grill-me/SKILL.md · 사용자가 /grill-me 를 호출하거나 아이디어·기능 요청·스펙을 구현 전에 굽고(grill)·압박 검증하고·심문해 달라고 할 때 사용. superpowers:brainstorming 의 opt-in 대체재 —…
leeyudok/agents-scaffold · .claude/skills/handoff/SKILL.md · 세션을 끊고 다음 세션에 넘긴다 — 재개 가능한 상태를 HANDOFF.md 에 적고, 협업 인프라(GitHub·GitLab·Forgejo·Jira·Plane·Slack)가 있으면 같은 내용으로 이슈를 만들어 URL…
leeyudok/agents-scaffold · .claude/skills/memory-factcheck/SKILL.md · 에이전트 영속 메모리를 실제 소스와 대조 — 각 메모리의 핵심 단언을 코드·DB·이슈 트래커·파일시스템에 대조해 stale 을 정정하고 dead 를 아카이브 후보로 리포트. 메모리가 30개를 넘거나, 스택/인프라…
leeyudok/agents-scaffold · .claude/skills/review/SKILL.md · 코드 변경사항 전체 리뷰. code-reviewer 에이전트 + security-audit 에이전트를 순차 실행하는 래퍼 스킬. PR/MR 생성 전 또는 리뷰 요청 시 사용.
leeyudok/agents-scaffold · .claude/skills/search-first/SKILL.md · 코드를 새로 짜기 전에 기존 솔루션(레포 내부 → 사내 미러 → 패키지 레지스트리 → MCP/스킬 → GitHub)을 먼저 검색하는 워크플로. 새 기능/유틸/의존성 추가 직전, "X 기능 넣어줘" 요청에 코드부터…
leeyudok/agents-scaffold · .claude/skills/security-precheck/SKILL.md · 외부 보안팀 코드 검사 전 자체 사전점검. security-audit 에이전트(+ 설정돼 있으면 SonarQube 보안 핫스팟)를 돌려 P0/P1/P2로 정리하고, 발견사항을 이슈로 쪼개 병렬 서브에이전트로…
leeyudok/agents-scaffold · .claude/skills/skill-evolve/SKILL.md · 스킬 실행 후 피드백을 받아 해당 SKILL.md를 자동 개선하는 메타 스킬. 스킬이 틀렸거나 누락이 있을 때, 또는 새로 배운 함정을 기록할 때 사용.
leeyudok/agents-scaffold · presets/lang-en/base/.claude/skills/docs-sync/SKILL.md · Bring documentation back in line with the code after changes to behavior, paths, versions, or generated output. Use on…
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…
youdotcom-oss/agent-skills · .agents/skills/grill-me/SKILL.md · Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of…
dianel555/dskills · skills/grill-me/SKILL.md · Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report…
eai-org/agent-toolkit · skills/grill-me/SKILL.md · Interview the user relentlessly about a plan, design, or idea until reaching shared understanding, resolving each…
akillness/jeo-skills · .agent-skills/grill-me/SKILL.md · A relentless interview to sharpen a plan or design. Use when the user wants a plan or design stress-tested. Triggers…
