Examine a plan, decision, or idea through structured rounds of questions with recommended answers. Organize dependent decisions into a branching map, resolve assumptions, and build a shared understanding before taking action.
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.
Review the instructions the agent will receive before you install.
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: the questions you can ask now without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
Format a round like so:
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
---
❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
Word each question so "yes" accepts your recommended answer.
Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.
Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.
The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Choose which related skill to use and in what order for planning, building, debugging, or maintaining software. It explains routes through the available workflows and helps select the next step based on your situation and project size.
Coordinate subagents, separate agents assigned tasks, to pursue a long-running goal in one session. Maintain dialogue with the user while improving working conditions, shared rules, and access to information needed for future tasks.
Summarize an ongoing conversation and launch a fresh background agent to continue the work. The handoff includes the next focus, references to existing documents, and suggested skills, with sensitive information removed.
Review code changes from a chosen Git reference against two separate criteria: documented coding standards and the original requirements. Independent reviewers check each criterion, then present findings separately so convention problems and requirement gaps remain visible.
Design modules that offer substantial behavior through a small interface, the rules callers must understand. Use shared design terms to simplify usage, contain complexity, choose where implementations can vary, and make behavior easier to test.
Investigate difficult bugs and performance slowdowns by building a repeatable test or script that detects the exact symptom. Reduce the failing case, compare possible causes, and verify the fix with checks that catch the bug if it returns.