agentleFS
Sign inStart free
Aquarius-muAquarius-mu/skillManager/skills/gameserver-agent-skills/grill/SKILL.md

grill

Skill1 starsChanged 52 days agoMITView on GitHub

Interview the user or a design relentlessly until reaching shared understanding. Walk down every branch of the decision tree, resolving dependencies one by one. Use when stress-testing a plan, clarifying design, or the user says "grill me".

87 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use write-skill, root-cause and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NoaiRoxSkill

    write-skill

    Use when creating a new skill, editing an existing skill, or verifying a skill works before deployment.

    Also in 5 projects that use this

  • Ingramradical235Skill

    root-cause

    Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

    Also in 4 projects that use this

  • Neko-Catpital-LabsSkill

    prove-it

    Shared evidence rule for investigating, diagnosing, debugging, proving, or explaining what happened or why for any problem or situation: do not assert something is fixed, working, passing, merged, or running unless you personally observed it this turn and can show what you saw; do not assert it was caused by X until a repro and controlled isolation prove that cause.

    Also in 4 projects that use this

  • sahinSkill

    execute

    Also in 5 projects that use this

  • assisjpSkill

    file-pr

    Prepare and open or update an authorized pull request with a concise problem-first description and verifiable evidence. Use when the user asks to create, file, open, or update a PR. Do not use merely to review a diff or when publication is not authorized.

    Also in 3 projects that use this

  • Arman-KudaibergenovSkill

    write-plan

    Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md. SHOULD также вызывать как промежуточный шаг между brainstorm и subagent-dev. Do NOT использовать для обсуждения идеи — используй brainstorm; для выполнения задач — используй subagent-dev.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 69 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the plan, design doc, or feature description provided

    line 14
  2. Distinctive:

    Ask the most important unresolved question first, with your recommended answer

    line 16
  3. Distinctive:

    When the user answers, update your understanding and ask the next question

    line 17
  4. Distinctive:

    When grilling a game server design, specifically probe:

    line 29

“Common” is measured: kept by at least 6 in 10 of the 69 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Grill

Interview relentlessly about every aspect of a plan or design until reaching shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one by one.

For each question, provide your recommended answer so the user can agree, correct, or redirect.

Process

  1. Read the plan, design doc, or feature description provided
  2. Identify the open decision tree — what is undecided, ambiguous, or potentially wrong?
  3. Ask the most important unresolved question first, with your recommended answer
  4. When the user answers, update your understanding and ask the next question
  5. Continue until all branches are resolved or the user is satisfied

Rules

  • One question at a time — never ask multiple questions in one message
  • Always provide your recommendation — don't ask open-ended questions without a suggested answer
  • Walk dependencies first — resolve foundational decisions before detail decisions
  • Be relentless — don't stop because an answer "seems fine"

C++ Game Server Focus

When grilling a game server design, specifically probe:

  • Protocol layer: Is the CmdId range available? Are CS/SC structs clearly defined?
  • Logic layer: Which Manager owns this feature? Are the data structures in SdpData clearly defined?
  • Persistence: What data needs setChanged()? When is it saved to DB?
  • Error codes: Are new ERR_ codes needed? Are they in ErrorDefine.sdp?
  • Registration: Does this need REGISTER_COMMAND in CommandRegister.h?
  • Concurrency: Is there any cross-module state access that needs care?
  • Edge cases: What happens when the player is offline? When the data doesn't exist yet?

Example

User: "I want to add a daily reward system"

Grill: "Should the daily reward reset at midnight server time or at a rolling 24h window
from the player's last claim? I'd recommend midnight server time — it's simpler to reason
about and consistent with most other daily systems in the codebase."

User: "Midnight server time"

Grill: "Should claiming the daily reward be possible while the player is offline (e.g. via
an automated system) or only when they actively log in? I'd recommend login-only — it keeps
the flow simple and doesn't require a background job."

... and so on

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free