Skip to content
Skillv1.0.0

grill-me

Systematic plan stress-testing through relentless one-question-at-a-time decision-tree interviewing

by akillness(0) 0 installs
Free
Sign in to install

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from akillness/jeo-skills (.agent-skills/grill-me/SKILL.md). Install upstream with npx skills add akillness/jeo-skills --skill grill-me. Copyright stays with the author.

Grill Me

Thoroughly vet plans and designs through systematic, relentless questioning.

When to use this skill

  • Before committing to an architectural decision
  • When a design feels right but hasn't been challenged
  • Stress-testing assumptions before implementation begins
  • Exploring edge cases and failure modes in a proposal

When not to use this skill

  • Quick clarifying questions → just ask directly
  • Validating against domain docs → use grill-with-docs
  • Writing implementation tickets → use to-issues

Process

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

Rules:

  • Ask one question at a time
  • Wait for feedback before continuing
  • Provide a recommended answer with each question
  • Explore the codebase instead of asking when the answer is findable there
  • Keep going until all branches of the decision tree are resolved

What gets covered

The grilling session explores:

  • Why this approach? — What alternatives were considered and rejected?
  • What breaks first? — Edge cases, failure modes, error states
  • What are the dependencies? — What must be true for this to work?
  • What changes later? — Which parts are likely to evolve?
  • What can't change? — Which decisions are load-bearing and hard to reverse?
  • Who is affected? — Callers, consumers, downstream systems

Output

By the end of the session:

  • Every major decision point has been examined
  • Dependencies between decisions have been resolved in order
  • Remaining open questions are documented
  • Shared understanding exists about trade-offs made

Activation

User says: "grill me", "stress-test this plan", "challenge my design", "ask me hard questions about this"

Instructions

  1. Identify the task trigger and expected output.
  2. Follow the workflow steps in this skill from top to bottom.
  3. Validate outputs before moving to the next step.
  4. Capture blockers and fallback path if any step fails.

Examples

  • Example: Apply this skill to a small scope first, then scale to full scope after validation passes.

Best practices

  • Keep outputs deterministic and auditable.
  • Prefer small reversible changes over broad risky edits.
  • Record assumptions explicitly.

References

  • Project standards: .agent-skills/skill-standardization/SKILL.md
  • Validator script: .agent-skills/skill-standardization/scripts/validate_skill.sh

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml
targets:
  - https://api.opensmartroute.ai/api/v1/registry/akillness-jeo-skills-grill-me/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

akillness-jeo-skills-grill-me.ocm.jsonjson
{
  "ocm": "1",
  "id": "akillness-jeo-skills-grill-me",
  "kind": "skill",
  "name": "grill-me",
  "description": "Systematic plan stress-testing through relentless one-question-at-a-time decision-tree interviewing",
  "publisher": "akillness",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "design-review",
      "stress-testing",
      "planning",
      "architecture",
      "questioning",
      "validation",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Systematic plan stress-testing through relentless one-question-at-a-time decision-tree interviewing"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/akillness/jeo-skills",
      "path": ".agent-skills/grill-me/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/akillness/jeo-skills/blob/HEAD/.agent-skills/grill-me/SKILL.md",
      "key": "akillness/jeo-skills/.agent-skills/grill-me/SKILL.md"
    },
    "compatibility": "Works for any plan, design, or architectural proposal. Pairs with grill-with-docs when domain documentation should be updated during the session, and with to-issues when the vetted plan should be conv",
    "allowed_tools": [
      "Read",
      "Grep",
      "Glob",
      "Bash",
      "Write",
      "Edit"
    ]
  },
  "instructions": "# Grill Me\n\nThoroughly vet plans and designs through systematic, relentless questioning.\n\n## When to use this skill\n\n- Before committing to an architectural decision\n- When a design feels right but hasn't been challenged\n- Stress-testing assumptions before implementation begins\n- Exploring edge cases and failure modes in a proposal\n\n## When not to use this skill\n\n- Quick clarifying questions → just ask directly\n- Validating against domain docs → use `grill-with-docs`\n- Writing implementation tickets → use `to-issues`\n\n## Process\n\nInterview relentlessly about every aspect of the plan until shar",
  "cost": {
    "context_tokens": 627
  }
}

Fetch it by URL: GET /api/v1/registry/akillness-jeo-skills-grill-me/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.