Grill Me
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".
Install
$ agentstack add skill-rijul1204-rashedul-agentic-engineering-grill-me-codex ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-rijul1204-rashedul-agentic-engineering-grill-me-codex) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Rijul1204
- Source: Rijul1204/rashedul-agentic-engineering
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.