Grilling

Stress-tests plans, decisions, and ideas through probing questions and co-creation. Use when the user asks to be grilled or wants to develop and challenge their thinking through an interview.

9 stars 1 forksTesting & QA Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add HelmholtzAI-Consultants-Munich/helmholtz-agent-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add HelmholtzAI-Consultants-Munich/helmholtz-agent-skills --skill grilling
Manual install
git clone --depth 1 https://github.com/HelmholtzAI-Consultants-Munich/helmholtz-agent-skills.git /tmp/helmholtz-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/helmholtz-agent-skills/plugins/method-skills/skills/grilling ~/.claude/skills/grilling

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Grilling

Interview the user relentlessly until you reach a shared understanding. Focus on alignment while occasionally drawing out experience and ideas that could change the plan and that you could not supply without the user's expertise.

## Work the decision tree

Map material decisions as a design tree: decisions branch into the decisions that depend on them. Treat its framing as provisional.
Ask only when the answer could materially change the goal, scope, workflow, or a significant tradeoff. Bundle routine, reversible details as recommended defaults; do not seek approval for each.
Work in rounds. The frontier contains questions whose prerequisites are settled. Ask the whole frontier, number each question, and wait for answers before the next round.
Questions that depend on an unanswered question belong to a later round. Recompute the tree after each reply; never treat silence or your recommendation as agreement.
Start each numbered item with a direct question about an unresolved choice or observation, not a proposed design awaiting approval. For decisions, explain the tradeoff, then give your recommended answer and a short reason in the ❓/➡️ format. Include implementation details only when they affect the answer.

Find facts you can look up yourself. Delegate independent investigation when subagents are available; a pending result blocks only its dependent questions.
Read the full skill on GitHub

Details

Skill name
grilling
Path
plugins/method-skills/skills/grilling/SKILL.md
License
Apache-2.0
Repo updated
26 October 2026

FAQ

What does the Grilling skill do?

Stress-tests plans, decisions, and ideas through probing questions and co-creation. Use when the user asks to be grilled or wants to develop and challenge their thinking through an interview.

How do I install the Grilling skill?

Claude Code plugin: /plugin marketplace add HelmholtzAI-Consultants-Munich/helmholtz-agent-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Grilling popular?

It lives in HelmholtzAI-Consultants-Munich/helmholtz-agent-skills, which has 9 GitHub stars and 1 forks.

Related skills

Dataset Scouting

9

HelmholtzAI-Consultants-Munich/helmholtz-agent-skills

use this whenever the user is examining public data, asking whether a study's metadata or raw data is actually usable, looking for exact raw-data download links, extracting the preprocessing or technical details a paper reports, building or updating a candidate list / shortlist / inclusion table, deciding which accessions are worth the download

Research & Science

Pureclip Optimization

9

HelmholtzAI-Consultants-Munich/helmholtz-agent-skills

Tune PureCLIP parameters for protein-RNA crosslink site calling on eCLIP, iCLIP or PAR-CLIP data

Other

Midnight Test Runner

9

UvRoxx/midnight-agent-skills

Run and debug Midnight contract tests using Vitest simulators. Use this skill when testing contracts, debugging test failures, or writing new tests. Triggers on "run tests", "test contract", "debug test", "test fails", or "vitest".

Testing & QA

Self Test Skill Invocation

9

konflux-ci/agent-plugins

Use when user asks to "test skill invocation framework" or mentions "canary skill test". This is a self-test skill to verify the test framework correctly loads and invokes skills.

Testing & QA18

Scylladb Benchmark

9

scylladb/agent-skills

Run a repeatable load test of a ScyllaDB Cloud cluster on AWS with cassandra-stress, from loader VMs in a peered VPC, and write a report with a fixed results table. The default fast path measures the maximum 50/50 read/write rate at p99 ≤ 10 ms on a pinned X Cloud cluster; a user profile tests the schema and queries of the user's application. Use this skill when a user asks to benchmark, load test, or stress test ScyllaDB Cloud, to measure p50, p90, and p99 latency at a target rate, to find the maximum throughput under a latency SLA, or to check if a cluster size is enough. It does not benchma

Testing & QA

Onboard Workshop

9

canonical/use-workshop-skill

Analyze an arbitrary repository and bootstrap a tailored Workshop definition from its existing build, test, and debug toolchain — feasibility verdict first, then propose, generate, launch, and verify. Use when a repo has no workshop definition yet and the user wants one derived from how the repo already builds and tests — "set up a workshop for this repo", "workshop-ify this project", "can this repo run in Workshop?".

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.