agentsclimarketplace

Grilling

Skill jwoo0122/harness/.agents/skills/grilling

Interview the user relentlessly about a plan or design until every important branch is resolved. Use when requirements or a proposed solution need to be stress-tested before implementation.From its SKILL.md

Install
npx -y skills add jwoo0122/harness --skill grilling

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.2 KB, 200 tokens by cl100k_base, as published. Nobody here has run it

Grilling loop

Use this as the reusable requirements-refinement primitive behind grill-with-docs.

  • Ask one question at a time. Multiple questions in one message make the decision tree hard to follow.
  • For each question, state a recommended answer and why it is the safest or most repository-consistent default.
  • Explore the design tree in dependency order instead of jumping to implementation details.
  • If a fact can be learned by reading the repository, inspect it rather than asking the user. Decisions, priorities, trade-offs, and acceptable risk belong to the user.
  • Probe concrete scenarios, edge cases, failure paths, boundaries, non-goals, and success evidence.
  • Reflect each answer back in precise language and call out contradictions with earlier answers or repository behavior.
  • Continue until the goal, scope, domain language, decisions, alternatives, acceptance criteria, and verification plan are unambiguous.
  • Do not enact the plan until the user explicitly confirms that the shared understanding is complete.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,614. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.