clio-kit-grill-me

Host compatibility

This copy is adapted from Clio Coder. Apply the procedure using the current host's available tools and the user's authorized scope. The tool names, /skill invocations, .clio-coder paths, fleets, approval gates and completion gates below describe Clio Coder; they are not installed or enforced by this skill in another host. Use the host's actual skill invocation and equivalent tools. If no equivalent exists, report the missing capability. Do not assume a tool is unavailable merely because the original headless workflow says so. A referenced agent or skill must be installed before relying on it. Scientific MCPs must be configured separately.

Adapted skills use the clio-kit- prefix to distinguish them from upstream audited skills. For a companion skill named below, select its clio-kit- copy from this collection; native agents, fleets and external programs retain their original names.

Grill Me

Run a rigorous, repo-aware interview that turns a vague plan into explicit decisions. The point is not to interrogate for sport; it is to surface hidden branches before anyone writes code.

Arguments

grill me on <plan, feature, or idea>

There is no flag syntax; the trigger is conversational — "grill me on X", "stress-test this design", "poke holes in this idea". Whatever the user names is the subject. A referenced file, doc, or repo path in the same request is Step 1's grounding to read first, not a separate argument.

This run has no back-and-forth. There is no second turn in which a user reads your question and replies to it — whatever you ask, you must also answer yourself, in this same turn, before it ends. Do not write a question and stop to wait for a reply, in ask_user or in plain chat text; nothing is coming. Ending the turn on an open question — even one question, even a well-posed one — is this skill's single most common failure and worse than skipping the interview format entirely.

There is no operator in a headless run: ask_user is not registered, so any call is refused as an unregistered tool rather than answered, every time, with no exceptions. Calling it again will not produce a different result, so one call is enough to confirm it (not required: reasoning from this paragraph alone is just as valid as calling it and observing the refusal). Whichever phase this lands in — even round 1 — switch immediately to the assumed-confirm monologue for every phase from here on, in the same turn: state the question you would have asked, give your own best/recommended answer with the reasoning behind it, mark it assumed — confirm, and move to the next phase. Do not re-call ask_user hoping a later round behaves differently — that only burns the max_rounds budget without ever converging. Keep working the phase map, phase by phase, all the way through Step 5's decision log before ending the turn — never end on "Answer 1/2/3" or any other place a reply is expected.