Frank
cedef97c99
Rewritten per grilling-on-grilling (2026-10-18, all branches settled via ask rounds): ask tool is the default round vehicle (one artefact per question, recommended:0 = bare-yes semantics, hybrid boundary ask-default / prose-exception); todo as visible decision tree (phase=branch, blocked reasons) + durable local://grilling-state.md ledger surviving the Esc-aborts-the-run path; scout=environment facts (spawn-before-ask, exclusive concurrency), web_search=world facts, inline=cheap lookups; completion gate = summary + one closing ask, then distilled decisions land in omp-docs/log.md via branch -> PR. Absorbs managed skill one-decision-per-ask-question (Frank's choice; reworded: ideas heavily encouraged via own atomic question, ban is on smuggling into option text only). Managed skill deleted here; heartbeat drops it from the live tree.
4.2 KiB
name, description
| name | description |
|---|---|
| grilling | Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases. |
Authored override. Extracted 2026-10-18 from
mattpocock/skills(identical to upstream at extraction) into the command-center repo so Frank can customize it. Removed from theskillsCLI global store (~/.agents/.skill-lock.jsonpruned) soskills update -gnever resurrects a duplicate. omp-aware redesign same day; absorbed theone-decision-per-ask-questionmanaged skill. Edits to this file are repo prose: branch → PR → Frank OK.
Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.
Work the tree in rounds. The frontier is every decision whose prerequisites are already settled. A question whose answer depends on an unsettled fact or another open question belongs to a later round, not this one. Ask the whole frontier in one round, then wait.
The round: ask is the default vehicle
Every frontier decision that fits 2–5 options goes through the ask tool - one question per decision, recommended: 0 (the recommended answer is always option 0; the user's single Enter is the bare "yes" that accepts it). Prose in chat is the exception, reserved for genuinely open narrative ("walk me through the deploy flow") - never as buttons.
Per-question discipline (absorbed law, was the one-decision-per-ask-question managed skill):
- One question decides exactly one artefact. Name it before sending; two names → split. A round may carry many single-artefact questions; a question may not.
- Shared plumbing is not grounds for merging: two products sharing an endpoint, service, or build step are still two questions.
- Ideas are heavily encouraged - the interviewer's own idea gets its own atomic question like any other. What is banned is smuggling an unasked-for artefact into another question's option text ("...and also X" in a label or preview).
- Option wording derives from the user's stated goal, never from your scaffolding (todo text, table rows, runbook headings).
multi: truefor pick-many;previewfor code/config evidence (renders as markdown);headerfor the branch chip.
Fallback: a harness without ask degrades to the classic text round - ❓ **Q1** - **title**: body / ➡️ recommendation, worded so a bare "yes" accepts every recommendation.
Dialog mechanics you must respect: ask is exclusive - spawn scouts before the ask call in the same message or they stall behind the dialog. The dialog cannot be interrupted by arriving facts; results land between rounds. Esc aborts the whole run with no post-cancel turn - the durable ledger is the safety net. Questions are spoken aloud when speech is enabled.
The ledger: todo is the tree, local:// is the save-file
todo: phase = design-tree branch, task text = the decision ("<decision> - via: <parent>"carries the edge; todo has no edges).pending= frontier,blockwith a one-line reason = waiting on a fact or an open decision (the HUD stays visible while anything is blocked),done= settled.unblockthe moment its prerequisite settles.write local://grilling-state.mdat the end of every round: the tree with each decision's verdict + one-line rationale. This is the only thing that survives an Esc-abort - keep it current.
Facts are yours; decisions are the user's
- Environment facts (filesystem, repo, live config):
task+scout, one batch, one scout per fact-cluster; on this box at most 3 run at once, so cluster rather than spray. - Outside-world facts: call
web_searchdirectly - no spawn hop. - Cheap lookups:
read/grepinline. - Only the main session may ask; every spawn carries the exact facts to return.
Completion
Frontier empty and nothing blocked → write the settled-decisions summary from the ledger, then one closing ask: "Shared understanding reached - proceed?" Nothing executes before that yes. After it: distill the settled decisions into an omp-docs/log.md work-log entry through the normal branch → PR path, and refresh the ledger file to final form.