Skip to content
Skills Library
Management & product · Planning

grilling

/grilling

Grill the user on every decision only they can make. Use when asked to grill, or when a task needs the user's own judgement. Not for facts a source can answer (research) or options not yet generated (ideation).

Licence
MIT
Last repository change
27.10.2026

Assessment and security

91/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content26 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Grill the user on every decision only they can make. Use when asked to grill, or when a task needs the user's own judgement. Not for facts a source can answer (research) or options not yet generated (ideation).

Original author description

Grill the user on every decision only they can make. Use when asked to grill, or when a task needs the user's own judgement. Not for facts a source can answer (research) or options not yet generated (ideation).

How it works

  1. Handing off
Original SKILL.md headings · 25 lines, 346 words
SKILL.md preview
---
name: grilling
description: Grill the user on every decision only they can make. Use when asked to grill, or when a task needs the user's own judgement. Not for facts a source can answer (research) or options not yet generated (ideation).
---

Grill the user relentlessly. Write the decisions to a **map** — one node per decision, each naming its prerequisite — at `docs/plan/YYYY-MM-DD-<name>/<name>.map.md`, in the per-change directory [write-specs](../write-specs/SKILL.md#referencing) defines. Where the change already has that directory, the map goes in it.

Under [frontier](../frontier/SKILL.md), write no map and no record of your own: frontier's map and tickets hold every decision, and frontier writes them through its own operations. Hand back each confirmed answer, and each new prerequisite as a sharp question.

Work the map in **rounds**. A decision is **settled** once the user has answered it. The **frontier** is every unsettled decision whose prerequisites are all settled. Ask the whole frontier in one round — a round is one user round-trip, and splitting it costs a turn per split for no new information.

Write each question as markdown:

```
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>
```

Where the round holds four or fewer questions, each a closed choice of two to four short options, ask it through the **AskUserQuestion** tool (Copilot: `ask_user`) instead — four questions per call is the tool's limit. Put your recommended option first and end its label with `(Recommended)`; the tool has no slot for the ➡️ line. A larger round stays markdown.

Finding _facts_ is your job — dispatch [research](../research/SKILL.md); put only the _decisions_ to the user. Every question in a round has been checked against the material first. A running dispatch is an unsettled prerequisite, so only the questions downstream of it wait; ask the rest of the frontier now.

Done when every decision on the map is settled, a re-read of the map surfaces no new prerequisites, and the user has confirmed the answers as written. What a caller gets back is the map: every decision with the user's answer on it — under frontier, the answers and new prerequisites handed back.

## Handing off

A decision that outlives the effort goes to [write-adr](../write-adr/SKILL.md). If the map is fogged — too many sessions to hold — [frontier](../frontier/SKILL.md) owns it.

Versions

RepositoryScoreLicence
This page · j0hanz/j0hanz-marketplace91MIT
nikospavlopoulos/devops-mutant-powers100MIT
RIJUDEVx/agent-skills100MIT
yuan88964/RelayStudio100MIT
SimplySylvia/Claude-Quorum100MIT
FrancoStino/opencode-skills-collection100MIT
cravingmaker/skills100MIT
helmholtzai-consultants-munich/helmholtz-agent-skills100Apache-2.0
bendrucker/claude100MIT

Database snapshot: 13.11.2026 · package version 85a6bc458b2e (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 82workflow-grilling
    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
  • 100kit-grill
    Ask the user the hard questions about an idea, plan or decision in their own terms, one decision per question, with a recommended answer first. Use in the explore skill's decide stage, for wayfinder grilling tickets, and whenever a plan has open decisions the user should make.…
  • 100grill-docs
    Grill the user about a plan (same interview as grilling) and record it — Q→A transcript in grills/, each decision appended to the repo's decisions doc (both under skilleddocs/ by default). Use for "grill me and document it", "grill with docs".
  • 100grilling-sleek
    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.