shipshitdev/grilling
skills/grilling/SKILL.md
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, asks to be grilled, or another skill needs the interview primitive.
$ install --global
skillsauthnpx skillsauth add shipshitdev/library grillingInstall 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: Aug 31, 2026, 3:20 AM36.4s1 file scanned
SKILL.md
- name:
- grilling
- description:
- Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, asks to be grilled, or another skill needs the interview primitive.
- license:
- MIT
- version:
- 1.0.0
- tags:
- interview, grilling, discovery, planning, frontier
- author:
- Ship Shit Dev
- source:
- https://github.com/mattpocock/skills/blob/main/skills/productivity/grilling/SKILL.md
- upstream_repo:
- mattpocock/skills
- upstream_ref:
- main
- upstream_commit:
- 8b78b531ab96
- last_synced:
- 2026-08-14
Grilling
Interview the user relentlessly until every branch of the design tree is resolved. This is the reusable interview primitive. Orchestrators (interview, shape) invoke it; they own grounding, artifacts, and routing.
Contract
Inputs:
- A plan, decision, idea, or design question
- Optional repo or docs context already loaded by the calling skill
Outputs:
- Settled decisions across the design tree
- Remaining open questions only when a fact-finding sub-agent is still running
Creates/Modifies:
- None. Calling skills persist briefs, glossaries, or issues.
External Side Effects:
- Read-only lookups to settle facts. No tracker writes, no code edits.
Confirmation Required:
- Before acting on the settled tree. Stop at a shared understanding; do not implement.
Delegates To:
- None. Fact-finding may dispatch a read-only exploration sub-agent.
Design tree
Map the topic as a design tree: every decision branches into the decisions that hang off it.
The frontier is every decision whose prerequisites are already settled — the questions that can be asked now without guessing at answers not yet heard.
Work the tree in rounds. Ask the whole frontier in one round. Wait for answers before the next round.
Round format
Number each frontier question. Recommend an answer so the user can accept it in a word.
**Q1 — <question title>**: <question body, including choices when they exist>
Recommended: <recommended answer>
A question whose answer depends on another question still open in this round belongs to a later round, not this one.
Facts vs decisions
Finding facts is the agent's job. When a frontier question needs a fact from the environment (filesystem, tracker, docs), dispatch a sub-agent to find it. Do not ask the user for anything that can be looked up.
Do not block the rest of the frontier on that lookup. A running exploration is an unsettled prerequisite, so only questions downstream of it wait — ask the rest of the frontier now.
Decisions are the user's. Put each to them and wait.
Done when
The frontier is empty: every branch of the design tree visited, nothing left silently assumed.
Do not act on the tree until the user confirms a shared understanding.
Related Skills
shipshitdev/weekly-review
development
VerifiedTrustedCommunity
Coordinates a weekly engineering review of board accuracy, recent code changes, operational health, and scoped cleanup. Use for a recurring repository health review or a review of the last several days.
35SKILL.mdUpdated Sep 6, 2026
shipshitdev/project-board
testing
VerifiedTrustedCommunity
Audits project board configuration and prepares explicitly requested setup, copy, or normalization changes while preserving the existing workflow and provider boundaries. Use when inspecting a board's fields, columns, scope, or configuration.
35SKILL.mdUpdated Sep 6, 2026
shipshitdev/board-sync
testing
VerifiedTrustedCommunity
Reconciles a project board with current work and delivery evidence, reports incomplete coverage and metadata gaps, and applies only approved provider-supported field changes. Use when auditing board drift, reviewing blocked work, or assessing upcoming delivery.
35SKILL.mdUpdated Sep 6, 2026
shipshitdev/how
development
VerifiedTrustedCommunity
Walk through how a subsystem works. Use for "how does X work", code walkthroughs before changing something, and placement or ownership questions. Explains architecture, runtime flow, and onboarding mental models. Can critique architecture. Use why for motivation.
35SKILL.mdUpdated Aug 31, 2026