CtrlK
BlogDocsLog inGet started
Tessl Logo

grill-me

Interrogate a vague or broad feature request BEFORE dispatching the harness orchestrator, to surface what the user has not anticipated. Use in the main thread when a

69

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

grill-me

Ask probing questions about the request before any plan or code, to surface what the user has NOT anticipated, not just confirm what they already said.

How

  • One question at a time, in prose. Never a multiple-choice menu, never a batch of five at once.
  • Read the answer, then ask the next most valuable question given it.
  • Stop as soon as the scope is answerable (roughly: you could write the orchestrator dispatch prompt without guessing). Do not interrogate for its own sake.

Cover, at minimum

  1. Scope-out: what is explicitly NOT in scope? What might look included but isn't?
  2. Edge cases: empty / invalid input, network or backend error, two users at once.
  3. Existing interactions: does this touch behavior already in place (permissions, RLS, cached data, shared views, another resource)?
  4. Definition of done: what manual check confirms it works? Who validates before merge?
  5. Reversibility: if it turns out wrong, how hard is it to undo?

If the user answers "I don't know" to a structural question, propose an explicit hypothesis and ask them to confirm rather than silently choosing.

After grilling

Fold the answers into the orchestrator dispatch prompt (scope-out and acceptance become ticket constraints). Then dispatch the harness as usual.

The orchestrator never invokes this skill: it runs headless and cannot hold an interactive back-and-forth. Grilling is a main-thread, pre-dispatch step.

Repository
marmelab/atomic-crm
Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.