maicongambini/omp-harness-guide/grill-with-docs

Claude Code and agent skill by maicongambini/omp-harness-guide

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Conducts design interviews while generating ADRs and glossaries. Use when stress-testing designs requiring durable docs. Do NOT use for quick questioning without docs (use grilling).

Install

npx vskill@latest install maicongambini/omp-harness-guide/grill-with-docs

SKILL.md

The same SKILL.md was published earlier as maicongambini/omp-harness-guide/grill-with-docs.

Run a /grilling session, using the /domain-modeling skill.

Modes

HITL (default) — interview the operator live, one question at a time. Use when a human is driving and reachable.

AUTO (AFK) — self-driven, no live operator. Use when a scheduler (e.g. spec-lead inside an authorized run) needs the plan sharpened without pausing. In this mode:

  • Do not pause to ask the operator. Walk each branch of the decision tree and, for every question, take your own recommended answer — resolving it from the codebase, existing ADRs, CONTEXT.md, and stated requirements.
  • Record every resolved question as a decision, and label the ones you answered on assumption as assumptions, so the plan review can see them.
  • Write ADRs and glossary entries via /domain-modeling exactly as in HITL — the docs are the same, only the questioner changed.
  • Escalate to the operator only on a genuine blocker: an ambiguity no source can settle, a decision that is hard to reverse and has no defensible default, or a scope change. Everything else resolves autonomously. (Same halt bar as an autonomous run.)

The mode is chosen by the caller; absent an explicit AUTO instruction, run HITL.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/maicongambini/omp-harness-guide/grill-with-docs/badge)](https://verified-skill.com/skills/maicongambini/omp-harness-guide/grill-with-docs)

Something wrong with this skill or its page? Tell us.