What makes Grilling notable?

1.9K downloads. Trust evidence available

How should Grilling be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Grilling

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases. Skill: Grilling Owner: wufei-png Summary: Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases. Tags: latest:1.0.6 Version history: v1.0.6 | 2026-07-13T14:57:56.878Z | user Focus grilling on meaningful tradeoffs v1.0.5 | 2026-07-02T15:14:19.619Z | user Sync latest SKILL.md v1.0.4 | 2026-07-02T15:10:30.801Z | user Mov

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.9k

Updated

Oct 9, 2026

Version

1.0.6

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.9K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 1.9K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.6release · observed Jul 13, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17ff8qt8kgjp387vqdhv9ht3583grte:grilling

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wufei-png-grilling/snapshot"

Documentation

CLAWHUB

35,605 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: grilling
description: Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
---

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.

When one option is clearly preferable, choose it without discussion. Ask only about decisions that involve genuine tradeoffs; for each, list the viable options, compare their tradeoffs, and recommend one.

Ask one question at a time and wait for feedback. If the user gives a per-turn maximum, treat it as a ceiling: ask multiple questions only when they are tightly related and on the same decision branch.

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

README.md

# Grilling

Interview the user relentlessly about a plan or design until the important
decisions are explicit and shared.

## Difference From Upstream

This skill is a small variant of
[mattpocock/skills `productivity/grilling`](https://github.com/mattpocock/skills/blob/main/skills/productivity/grilling/SKILL.md).

The upstream skill keeps a strict one-question-at-a-time cadence. This fork keeps
that default and adds two behavioral extensions:

- If the user gives a per-turn maximum, treat it as a ceiling. Ask multiple
  questions only when they are tightly related and on the same decision branch.
- Choose clearly preferable options without discussion. Ask only about genuine
  tradeoffs; list the viable options, compare their tradeoffs, and recommend one.

![Diff showing the per-turn maximum behavior](docs/images/skill-diff.png)

## Install

### With `npx skills add`

Install the skill directly from this GitHub repository:

```bash
npx skills add wufei-png/grilling -g -y --agent codex
```

To install only this skill when the repository contains more skills in the
future:

```bash
npx skills add wufei-png/grilling --skill grilling -g -y --agent codex
```

### With `curl`

Install the source `SKILL.md` into Codex's user skill directory:

```bash
mkdir -p "${CODEX_HOME:-$HOME/.codex}/skills/grilling"
curl -fsSL \
  https://raw.githubusercontent.com/wufei-png/grilling/main/SKILL.md \
  -o "${CODEX_HOME:-$HOME/.codex}/skills/grilling/SKILL.md"
```

For agent setups that read from `~/.agents/skills`, use:

```bash
mkdir -p "$HOME/.agents/skills/grilling"
curl -fsSL \
  https://raw.githubusercontent.com/wufei-png/grilling/main/SKILL.md \
  -o "$HOME/.agents/skills/grilling/SKILL.md"
```

## Publish

Publish this skill to ClawHub from the repository root:

```bash
clawhub skill publish . \
  --slug grilling \
  --name "Grilling" \
  --owner wufei-png \
  --source-repo wufei-png/grilling \
  --source-commit "$(git rev-parse HEAD)" \
  --source-ref main \
  --source-path . \
  --changelog "Describe the release"
```

Add `--dry-run` to preview the release without publishing it.

_meta.json

{
  "ownerId": "kn70g9q3r6kyhzymhp4akb8as982fn93",
  "slug": "grilling",
  "version": "1.0.6",
  "publishedAt": 1783954676878
}

skill-card.md

## Description:

Interview the user about a plan or design until important decisions are explicit and shared.

This skill is ready for commercial/non-commercial use.

## Publisher:

[wufei-png](https://clawhub.ai/user/wufei-png)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, planners, and other agent users use this skill to stress-test a plan or design by making assumptions, dependencies, and meaningful tradeoffs explicit before implementation.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The README installation examples use mutable or unpinned installer content.

Mitigation: Review the skill text before installing and prefer a pinned release or commit when installing from external sources.

## Reference(s):

- [Upstream mattpocock/skills grilling skill](https://github.com/mattpocock/skills/blob/main/skills/productivity/grilling/SKILL.md)

## Skill Output:

**Output Type(s):** [text, markdown, guidance]

**Output Format:** [Markdown conversation with questions, tradeoff comparisons, and recommendations]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include shell commands only when codebase exploration is needed to answer a question.]

## Skill Version(s):

1.0.6 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 7h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.