grill-with-docs · 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: User-invoked when preparing a plan or design change. Suitable for codebase-based projects since it produces persistent documentation assets. /ask-matt's main flow starts with recommending /grill-with-docs.
Mechanism: Delegates to a /grilling session — questions the user one by one, walking every decision tree branch. Simultaneously invokes /domain-modeling to build the domain model during conversation: updates CONTEXT.md when terms are resolved, creates ADRs when hard-to-reverse decisions are made. Continues until every branch is resolved.
Output: A user-aligned, thoroughly validated plan/design, plus persistent documentation assets in the project (CONTEXT.md glossary and ADRs). Unlike /grill-me (no persistence), knowledge generated here is archived in the project filesystem.

Use Cases

Two Typical Use Cases

Scenario 01

Aligning requirements before building a new feature

A team preparing to build a new "order cancellation" feature invokes `/grill-with-docs`. The agent relentlessly asks "How is inventory handled after cancellation?", "Is partial cancellation allowed?", "What's the cancellation window?" Each resolved term ambiguity (e.g., distinguishing "cancellation" from "refund") triggers an automatic CONTEXT.md update. When the team decides to use a state machine for order lifecycle, the skill records this in an ADR. The output is not just aligned understanding but persistent documentation assets.

Scenario 02

Validating a technical design before refactoring

An architect plans to refactor the payment module and first invokes `/grill-with-docs` to validate the plan. The agent uses /grilling to walk through key decisions: module boundaries, interface contracts, migration strategy. /domain-modeling sharpens vague terms like "payment processing" into precise concepts: "authorization", "capture", "refund". Each refinement is immediately written to CONTEXT.md. The result is a documented domain model ready for the implement skill.

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

ask-mattWorkflow

Tier 2 · Current Skill

grill-with-docsWorkflow

Tier 3 · I Use These 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/grill-with-docs/
▸grill-with-docs
- ·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