Grill me codex

Skill Rijul1204/rashedul-agentic-engineering/skills/grill-me-codex

My agentic-engineering workbench — Claude Code skills, subagents, and CI workflows I reuse across projects.

Install

npx -y skills add Rijul1204/rashedul-agentic-engineering --skill grill-me-codex

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Interview the user relentlessly about a plan or design until the important decisions are explicit and defensible. Use when the user wants to stress-test a plan, get grilled on a design, or says "grill me".

SKILL.md

1.9 KB, as published. Nobody here has run it

Grill Me

Use this skill to pressure-test a plan, architecture, or delivery approach until the key decisions, constraints, and risks are explicit.

Workflow

Restate the target briefly so both sides are aligned.
Explore the repo, docs, and current implementation for anything discoverable before asking questions.
Ask one high-signal question at a time. Every question must expose a real decision, dependency, ambiguity, or risk.
For each question, provide:
- why it matters
- your recommended answer
- what changes if the opposite answer is chosen
Keep drilling until the following are explicit:
- goal and success criteria
- users or stakeholders
- inputs, outputs, and interfaces
- constraints and non-goals
- edge cases and failure modes
- testing and rollout expectations
End with either:
- a concise decision-complete summary, or
- a short list of unresolved decisions that still block implementation

Rules

Prefer repo exploration over questioning when the answer is discoverable.
Challenge weak assumptions directly and concretely.
Avoid filler, repetition, and generic brainstorming.
If the user jumps to implementation before defining the problem, recover the problem statement first.
If the plan already looks solid, focus on hidden coupling, omitted failure cases, vague acceptance criteria, and operational risk.

Output Shape

Use a compact structure:

Current understanding
Questions and recommended answers
Decision summary or remaining blockers

Keep the conversation moving. The goal is not to admire the plan. The goal is to make it hard to ship something underspecified.