skills/grilling-designs/SKILL.md
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to get grilled on a design, stress-test a plan, or mentions "grill me".
npx skillsauth add narumiruna/agent-skills grilling-designsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Grill a user's plan or design with a one-question-at-a-time interview until decisions, dependencies, assumptions, tradeoffs, and verification are explicit.
Question: the single thing the user must answer next.Options: a numbered list of likely answers the user can choose from.Recommended answer: the option number you would choose, with enough rationale to be useful.Prefer questions that resolve, in order:
Do not draft a plan while the interview is still resolving major branches. If the user asks to create or update a plan document after grilling, load writing-plans and follow its file/output rules using the agreed decisions.
Stop only when no major unresolved branch remains. End with the agreed decisions, remaining risks or unknowns, and the recommended next step.
development
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
development
Assess or improve an existing codebase's architecture when the user asks about module boundaries, coupling, scattered ownership, testability, change locality, deep modules, seams, or behavior-preserving structural refactoring. Use for cross-module design rather than ordinary diff review or a confirmed edge-case bug fix.
development
Perform read-only security audits, vulnerability assessments, or threat-focused reviews of diffs, pull requests, code paths, or explicitly scoped repositories when security is the primary objective or acceptance criterion. Use reviewing-code for ordinary review with baseline security coverage and hardening-code-paths for fixing confirmed findings.
development
Run iterative multi-reviewer panels over a code diff, verify their findings, apply explicitly authorized fixes, and re-review the updated change until it passes or reaches a stopping condition. Use when the user asks for a panel loop, multi-model code-review consensus, or a review-fix-re-review cycle.