Agent skill

Grill The Brief

by OneWave-AI in OneWave-AI/claude-skills

Use before building anything from a vague request — a feature, an app, an agent, an automation, a page.

MITAuto-check passed

Install Grill The Brief

skills CLI
$ npx skills add OneWave-AI/claude-skills --skill grill-the-brief -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OneWave-AI/claude-skills grill-the-brief --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OneWave-AI/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/grill-the-brief .claude/skills/grill-the-brief && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
grill-the-brief
GitHub stars
336
Token cost
~901 tokens
SKILL.md length
500 words
Files
1
Skills in repo
69
Repo updated
First seen
Licence
MIT

At a glance

Use before building anything from a vague request — a feature, an app, an agent, an automation, a page.

  • The user says build me X without specifics
  • SKILL.md covers Core Behavior, What to Interrogate, Questioning Rules and Output Format, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • A brief could be read two ways

What it does

Grill The Brief is an agent skill from OneWave-AI/claude-skills. Use before building anything from a vague request — a feature, an app, an agent, an automation, a page. Trigger when the user says "build me X" without specifics, when a brief could be read two ways, or when the user asks to be challenged, interrogated, or pushed on requirements before code gets written.

Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture. Built and maintained by OneWave AI. The licence is MIT.

When your agent uses it

  • The user says build me X without specifics
  • A brief could be read two ways
  • The user asks to be challenged
  • Pushed on requirements before code gets written

Example prompts

  • “build me X”
  • “/grill-the-brief”

What it can do on your machine

Read from SKILL.md and the folder at commit fc5b785. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Grill The Brief loads about 901 tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~901

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OneWave-AI/claude-skills at commit fc5b785, republished under its MIT licence (© OneWave-AI). 500 words, ~901 tokens.

Download SKILL.mdSave it as .claude/skills/grill-the-brief/SKILL.md (or your agent's skills folder).
name
grill-the-brief
description
Use before building anything from a vague request — a feature, an app, an agent, an automation, a page. Trigger when the user says "build me X" without specifics, when a brief could be read two ways, or when the user asks to be challenged, interrogated, or pushed on requirements before code gets written.

Grill the Brief

Most rework comes from building the wrong thing confidently. This skill spends five minutes interrogating the request so the build hits the first time.

Core Behavior

Ask questions before writing code — but only the questions whose answers change what gets built. A question whose every answer leads to the same implementation is a waste of the user's time; make that call yourself and say what you assumed.

Ask in one batch, not one at a time. Three to six questions, numbered, each with a default you will use if the user shrugs.

What to Interrogate

Work down this list and pull only what is genuinely unresolved:

The actual job. What does the user do today that this replaces? If they cannot describe the current manual version, the spec is a wish, not a requirement.

Who touches it. One person, a team, or customers? That single answer decides auth, permissions, and polish level.

Done looks like. The observable condition that ends the work. If nobody can name it, the project has no end.

Scale and shape of the data. Ten rows or ten million. One file or a live feed. This decides architecture more than any preference does.

What it must not do. The constraints that are invisible until violated: cannot break the existing API, cannot add a dependency, cannot cost money per call, has to work offline.

The deadline and the stakes. A demo tomorrow and a production system get different code. Ask which one this is.

What exists already. Existing repo, existing schema, existing design system. Building beside something is different from building fresh.

Show full SKILL.md (232 more words)Show less

Questioning Rules

  • Never ask what you can read. Check the repo, the files, the git history first — asking the user something the code answers is a tell that you did not look.
  • Attach a default to every question: "Which auth? (default: Google SSO, since the repo already has it)". The user can answer with silence and still get moving.
  • Push back once, concretely, when the brief has a real problem — then build what they asked if they confirm. One flag, not a debate.
  • Stop at six questions. Beyond that you are stalling.
  • No question that only serves your comfort. "What framework do you prefer?" is a decision you can make.

Output Format

Before I build — <n> things that change the shape of this:

1. <question> (default: <what I'll assume>)
2. <question> (default: <what I'll assume>)
3. <question> (default: <what I'll assume>)

Say "go" and I'll build with the defaults.

Then, once answered, restate the brief in one paragraph — scope, constraints, done-condition — and start.

Red Flags to Name Out Loud

Call these out when you see them, in a sentence each:

  • The request names a solution but never the problem.
  • "Just like <big product>" with no cut-down of scope.
  • Success measured by something nobody tracks today.
  • Two incompatible goals in one brief (fast and configurable, simple and enterprise-ready).
  • A build where an existing tool already does the job — say so once, then build it anyway if they still want it.

When to Skip This

Clear, small, or reversible work. A bug fix, a copy change, a one-file tweak. Grilling a two-minute request wastes the time it is supposed to save.

© OneWave-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in grill-the-brief of OneWave-AI/claude-skills.

Open the folder on GitHubat commit fc5b785

Compare with similar skills

Grill The Brief next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Grill The Brief compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Grill The Brief this skillOneWave-AI/claude-skills336—~901Automated safety check: PassMIT
Briefalirezarezvani/claude-skills28k—~967Automated safety check: PassMIT
Grillasgeirtj/system_prompts_leaks69k—~1.7kAutomated safety check: PassMIT
Grill Menrwl/nx29k—~1.2kAutomated safety check: PassMIT
Briefdavepoon/buildwithclaude3.6k—~1.3kAutomated safety check: NotesMIT
Grillingvinvcn/mattpocock-skills-zh-CN4.7k—~226Automated safety check: PassMIT

Similar skills

  • Brief

    alirezarezvani/claude-skills

    /cs:brief <topic — Generate a one-page strategy brief from an office-hours intake.

    28k GitHub stars~967 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Grill

    asgeirtj/system_prompts_leaks

    Run an explicitly requested decision interview and record each settled decision in durable project documentation.

    69k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • Grill Me

    nrwl/nx

    Grill the user relentlessly about a plan, design, decision, or set of review findings — working the decision tree in rounds until nothing is left silently assumed.

    29k GitHub stars~1.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Brief

    davepoon/buildwithclaude

    Session-start briefing from Origin. An agent skill from davepoon/buildwithclaude.

    3.6k GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check: notes
  • Grilling

    vinvcn/mattpocock-skills-zh-CN

    围绕计划、decision 或 idea 持续追问用户。适用于用户想对自己的思路做压力测试,或使用任何 “grill” 触发措辞时。

    4.7k GitHub stars~226 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Grill Me

    feiskyer/claude-code-settings

    针对方案或设计的高强度追问式面试(adversarial design review / grill session),暴露假设漏洞与缺失约束,过程中同步维护领域模型(术语表和 ADR)。手动调用 /grill-me。

    1.7k GitHub stars~913 tokensUpdated 13 days ago
    Agent WorkflowsAuto-check passed

More from OneWave-AI/claude-skills

All 69 skills in this repo
  • CRM Data Cleanup

    OneWave-AI/claude-skills

    Finds duplicate and junk records in a CRM CSV export with fuzzy matching, normalizes fields and writes a reviewable merge plan plus import-ready files without touching the live CRM.

    336 GitHub stars~2.5k tokensUpdated 9 days ago
    Auto-check passed
  • Design Export Repair

    OneWave-AI/claude-skills

    Repairs broken decks and PDFs exported from Claude Design or similar AI deck generators: clipped text, wrong fonts and corrupted .pptx package structure.

    336 GitHub stars~2.6k tokensUpdated 9 days ago
    Auto-check passed
  • Bi Measure Builder

    OneWave-AI/claude-skills

    Writes, explains, debugs, and optimizes BI calculations - Power BI / Fabric DAX measures and calculated columns, Tableau calculated fields (FIXED/INCLUDE/EXCLUDE LOD expressions, table…

    336 GitHub stars~2.2k tokensUpdated 9 days ago
    Auto-check passed
  • Bookkeeping Close

    OneWave-AI/claude-skills

    Categorizes transactions, reconciles bank and card statements to the ledger, works a month-end checklist and prepares a close package, without ever forcing a balance.

    336 GitHub stars~2k tokensUpdated 9 days ago
    Auto-check passed
  • CSV and Excel Merger

    OneWave-AI/claude-skills

    Combines CSV, TSV and Excel files into one verified table with pandas, by stacking or joining, mapping columns, normalizing keys and removing duplicates.

    336 GitHub stars~1.6k tokensUpdated 9 days ago
    Auto-check passed
  • Sec Filing Puller

    OneWave-AI/claude-skills

    Pulls financial statement numbers for US public companies straight from SEC EDGAR's free official XBRL APIs (companyfacts, companyconcept, frames, submissions) into a cited table.

    336 GitHub stars~2.1k tokensUpdated 9 days ago
    Auto-check passed

Questions about Grill The Brief

What does Grill The Brief do?

Use before building anything from a vague request — a feature, an app, an agent, an automation, a page. Grill The Brief is an agent skill from OneWave-AI/claude-skills. Use before building anything from a vague request — a feature, an app, an agent, an automation, a page.

When should I use Grill The Brief?

Grill The Brief fits situations like: the user says build me X without specifics; A brief could be read two ways; the user asks to be challenged; pushed on requirements before code gets written.

How do I install Grill The Brief in Claude Code?

Run `npx skills add OneWave-AI/claude-skills --skill grill-the-brief -a claude-code`. Or copy the skill folder (grill-the-brief in OneWave-AI/claude-skills) into .claude/skills/grill-the-brief in your project. Claude Code loads it when a task matches its description.

How do I install Grill The Brief in Codex?

Run `npx skills add OneWave-AI/claude-skills --skill grill-the-brief -a codex`. Or copy the skill folder (grill-the-brief in OneWave-AI/claude-skills) into .agents/skills/grill-the-brief in your project. Codex loads it when a task matches its description.

Can I use Grill The Brief in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OneWave-AI/claude-skills --skill grill-the-brief -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grill-the-brief, .gemini/skills/grill-the-brief, .github/skills/grill-the-brief and .opencode/skills/grill-the-brief in your project.

What does Grill The Brief need to run?

SKILL.md names no scripts, command-line tools or credentials: Grill The Brief is instructions for the agent only.

Does Grill The Brief access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Grill The Brief safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Grill The Brief use?

Grill The Brief is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Grill The Brief use?

About 901 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Grill The Brief?

Skills that share tags, products or a category with Grill The Brief: Brief (alirezarezvani/claude-skills, 28k stars), Grill (asgeirtj/system_prompts_leaks, 69k stars), Grill Me (nrwl/nx, 29k stars) and Brief (davepoon/buildwithclaude, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Grill The Brief?

OneWave-AI (a GitHub organization) maintains it in OneWave-AI/claude-skills, which has 336 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on October 2, 2026.

Source: OneWave-AI/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.