grilling · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger: Automatically loaded by the model when the user wants to stress-test a plan/decision/idea or uses any "grill" trigger phrases. Not directly invoked by users (they should use /grill-me or /grill-with-docs); consumed by other skills as the underlying reusable loop.
Mechanism: Core interview loop: (1) ask one question at a time to avoid confusion; (2) "look up verifiable facts independently, decisions belong to the user" — filesystem queries, tool outputs, etc. are handled by the agent; (3) provide a recommended answer for each question; (4) walk each decision tree branch one by one, resolving inter-branch dependencies; (5) take no action until the user confirms shared understanding. Concise — only 12 lines of Markdown.
Output: Shared understanding between user and agent. All decision tree branches covered, ambiguity resolved, and the agent knows the user's intent. Ready for upstream skills to act upon.

Use Cases

Two Typical Use Cases

Scenario 01

Structured interviewing during requirements clarification

A user says "I want to build an order management feature" but the description is vague. `/grilling` skill automatically starts asking questions one at a time: "What states does an order have?", "Does cancellation require a refund?", "Is partial refund needed?", "Who should be notified on state change?" Each question waits for an answer. Verifiable facts like "does existing code support cancellation" are looked up independently without wasting the user's time. Stops only when shared understanding is confirmed.

Scenario 02

Comprehensive validation before architectural decisions

A team discussing database selection at a tech review invokes `/grilling` to ensure all branches are covered. The skill asks: "What's the read/write ratio?", "How strong are consistency requirements?", "Which DB is the team familiar with?", "What's the ops capability?" When the user says "our team knows PostgreSQL," the skill accepts the decision without challenging it. Each question provides a recommended answer but the user makes the final decision.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

Tier 2 · Current Skill

grillingWorkflow

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md50.0%
other50.0%

▸skills/grilling/
▸grilling
- ·SKILL.md
- ▸agents
  - ·openai.yaml

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

ask-matt

A router skill for the entire skillset: when the user can't remember which skill to use or which flow fits their situation, they invoke this to get a recommendation. It describes the main "idea → ship" flow (grill-with-docs → to-spec/to-tickets → implement), plus on-ramps (triage, diagnosing-bugs, wayfinder), codebase health (improve-codebase-architecture), vocabulary layers (domain-modeling, codebase-design), and standalone skills (grill-me, prototype, research, teach). Following its map leads users to the correct workflow entry point.

Workflow

code-review

A two-axis code review skill: reviews a diff (from a fixed point to HEAD) along both Standards (coding standards + Fowler smell baseline) and Spec (faithful implementation of the originating issue/PRD). Both axes run as parallel sub-agents to avoid context pollution. The report aggregates findings without merging conclusions, ensuring "passes standards but implements the wrong thing" and "implements the right thing but breaks conventions" are both surfaced independently.

Workflow

codebase-design

A shared vocabulary skill for deep module design: provides a precise set of design terms (Module, Interface, Depth, Seam, Adapter, Leverage, Locality) guiding agents and developers to design "deep modules" — a lot of behaviour behind a small interface. Includes design principles (the deletion test, the interface is the test surface) and testability guidelines. A reference skill consumed by other skills (e.g., improve-codebase-architecture, tdd) and invoked directly by engineers.

Style Guide

diagnosing-bugs

A disciplined diagnosis loop for hard bugs and performance regressions. The core idea is to first build a tight feedback loop — no hypothesis phase without one. Six phases: build feedback loop → reproduce + minimise → generate 3-5 falsifiable hypotheses → instrument by prediction → fix + regression test → cleanup + post-mortem. If the codebase architecture can't lock down the bug, it recommends handing off to the improve-codebase-architecture skill.

Workflow