agentleFS
Sign inStart free
me-cedricme-cedric/agent-compass/skills/grill/SKILL.md

grill

Skill3 starsChanged 27 days agoMITView on GitHub

Interview the user about a plan until each open question has an answer or an owner. Writes one RAID file per open question and one ADR per decision. Use to stress-test a plan or to fill the RAID register.

87 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use write-skill, root-cause and 9 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

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 5 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 69 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the upstream skill grill-me or grilling is installed (source id mattpocock), follow its loop.

    line 14
  2. Very specific:

    Read the plan, {{OPENSPEC_DIR}} and the code that the plan touches.

    line 16
  3. Distinctive:

    Ask one question at a time.

    line 17
  4. Distinctive:

    Ask the question that unblocks the most other questions first.

    line 18
  5. Distinctive:

    Stop when no open question blocks the plan, or when the user says stop.

    line 19
  6. Very specific:

    Write one file for each finding: {{DELIVERY_DIR}}/questions/Q-NNN.md.

    line 34
  7. Distinctive:

    Write all nine keys. Keep an empty key bare.

    line 57
  8. Very specific:

    Never overwrite a file. Skip a clarification when a file holds it for the same specRef.

    line 63
  9. Very specific:

    Never delete a file. Set status: folded instead.

    line 64
  10. Very specific:

    Put an answer under ## Answer.

    line 65
  11. Distinctive:

    Do not edit a spec. The user folds an answer into the spec as a separate change.

    line 66
  12. Very specific:

    Write each decision that the user makes as an ADR in {{ADR_DIR}}.

    line 70
  13. Very specific:

    Read references/decider-view.md when the user asks for a document to send to a decider.

    line 74

“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

Loop

  1. If the upstream skill grill-me or grilling is installed (source id mattpocock), follow its loop. Else use steps 2 to 5. To install it, add mattpocock to upstream in .agents/compass.json, then run ac sync.
  2. Read the plan, {{OPENSPEC_DIR}} and the code that the plan touches. Answer from them first.
  3. Ask one question at a time. Give your recommended answer with each question.
  4. Ask the question that unblocks the most other questions first.
  5. Stop when no open question blocks the plan, or when the user says stop.

Harvest

Also scan {{OPENSPEC_DIR}} for findings:

  1. A [NEEDS CLARIFICATION] marker.
  2. A ## Clarifications session. Each - Q: <question> → A: <answer> line is one finding.
  3. Hedged prose such as "TBD", "to be confirmed", "we assume", "subject to". Match the language of the specs.
  4. An unstated premise behind an estimate in {{COSTING_DIR}}. Set kind: assumption.

Quote the source line for each finding. Never invent a finding. Stop at 20 findings for each run.

RAID files

Write one file for each finding: {{DELIVERY_DIR}}/questions/Q-NNN.md.

---
id: Q-014
kind: question
status: open
raisedAt: <YYYY-MM-DD>
raisedBy: assistant
owner:
specRef: <spec path>#<heading>
taskRef:
ticket:
---
## Question

<one sentence>

## Answer

## Consequence
  • Write all nine keys. Keep an empty key bare.
  • kind is question, risk, assumption, issue or dependency.
  • status is open, assigned, answered or folded.
  • Take the highest Q-NNN of all file names and all id keys. Add one. Pad to three digits. An empty register starts at Q-001.
  • A reworded question keeps its id.
  • List the register first. Read the target path again just before each write. If it has content, take the next id.
  • Never overwrite a file. Skip a clarification when a file holds it for the same specRef.
  • Never delete a file. Set status: folded instead.
  • Put an answer under ## Answer. Set status: answered. A clarification pair without an answer is open.
  • Do not edit a spec. The user folds an answer into the spec as a separate change.

ADRs

Write each decision that the user makes as an ADR in {{ADR_DIR}}. Use the skill adr.

A document for a decider

Read references/decider-view.md when the user asks for a document to send to a decider.

Report

Report three lists:

  1. The ids that you created, with kind and source.
  2. The ids that you skipped, with the reason.
  3. The findings that you did not write.

Do not commit.

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