narumiruna/grilling-designs
skills/writing-research/grilling-designs/SKILL.md
Interview the user one decision at a time to stress-test a plan or design until goals, constraints, assumptions, tradeoffs, risks, and verification are explicit. Use only when the user asks to be grilled or names “grilling designs.”
$ install --global
skillsauthnpx skillsauth add narumiruna/agent-skills grilling-designsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 23, 2026, 6:34 AM123.8s2 files scanned
SKILL.md
- name:
- grilling-designs
- description:
- Interview the user one decision at a time to stress-test a plan or design until goals, constraints, assumptions, tradeoffs, risks, and verification are explicit. Use only when the user asks to be grilled or names “grilling designs.”
Grilling Designs
Build a live decision tree from the user's goal, constraints, stakeholders, flows, dependencies, risks, and success criteria.
Loop
- Resolve answers available from repository files, callers, configuration, docs, tests, or commands before questioning the user.
- Select the highest-leverage unresolved decision that unlocks later branches.
- Ask exactly one question with:
- Question: the one decision needed next.
- Options: a numbered list of credible choices.
- Recommended answer: the option you recommend and the deciding rationale.
- Incorporate the answer, resolve dependent branches, and repeat. If it conflicts with evidence or an earlier decision, state the conflict and ask the smallest clarifying question.
Prioritize goal/success, constraints/non-goals, architecture facts, interfaces/data/state ownership, failure/security/migration/rollout/observability, then test and verification criteria.
Do not draft a plan while major branches remain. When the user requests a plan after the interview, use writing-plans with the agreed decisions.
Stop when no major unresolved branch remains. Return the agreed decisions, remaining risks or unknowns, and the recommended next action.
Related Skills
narumiruna/scoring-agent-skills
development
VerifiedTrustedCommunity
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.
8SKILL.mdUpdated Jul 29, 2026
narumiruna/improving-codebase-architecture
development
VerifiedTrustedCommunity
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.
8SKILL.mdUpdated Jul 29, 2026
narumiruna/auditing-code-security
development
VerifiedTrustedCommunity
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.
8SKILL.mdUpdated Jul 29, 2026
narumiruna/running-panel-review-loops
development
VerifiedTrustedCommunity
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.
8SKILL.mdUpdated Jul 26, 2026