Grill Me

v1.0.0

Stress-test a plan, idea, or design by interviewing the user relentlessly until reaching shared understanding. Resolves each branch of the decision tree one-...

⭐ 0· 207·1 current·1 all-time

by0xNox@nox-admin

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for nox-admin/nox-grill-me.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "Grill Me" (nox-admin/nox-grill-me) from ClawHub.
Skill page: https://clawhub.ai/nox-admin/nox-grill-me
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install nox-grill-me

ClawHub CLI

Package manager switcher

npx clawhub@latest install nox-grill-me

Security Scan

VirusTotal

Benign

View report →

OpenClaw

Benign

medium confidence

✓

Purpose & Capability

Name/description (interview/grill a plan) align with the instructions: the skill repeatedly questions and resolves design branches. It does not request unrelated binaries, env vars, or services.

ℹ

Instruction Scope

SKILL.md is broad: it directs the agent to 'interview relentlessly' and to 'explore the codebase' when questions can be answered that way. Exploring the codebase is coherent with design review, but the phrasing is open-ended and could lead the agent to read large or sensitive files in the workspace or to solicit unnecessary private data unless the user scopes the task.

✓

Install Mechanism

No install spec and no code files — lowest-risk arrangement. Nothing will be written to disk or downloaded by the skill itself.

✓

Credentials

The skill declares no environment variables, credentials, or config paths. There are no disproportionate credential requests.

✓

Persistence & Privilege

always:false and no special privileges requested. The skill does not ask to modify agent configs or persist itself.

Assessment

This skill appears to be what it says: an instruction-only interviewer for plans and designs. Before running it, decide and communicate scope limits (which files/folders it may inspect, what topics are off-limits), avoid providing secrets or credentials in conversation, and monitor the agent's questions to stop overly broad data collection. If you plan to let it inspect code, consider running it in a workspace copy that excludes secrets or private configs.

Like a lobster shell, security has layers — review code before you run it.

latestvk972wyyx9ze51gs9qeth3yw9958399za

207downloads

0stars

2versions

Updated 1mo ago

v1.0.0

MIT-0

Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.

If a question can be answered by exploring the codebase, explore the codebase instead.

Comments

Loading comments...