grill-with-docs

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is grill-with-docs in mattpocock/skills

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable instruction skill with a clear sequenced workflow and an embedded feedback loop. The one real defect is that two referenced format files do not exist in the bundle, weakening progressive disclosure.

Suggestions

Add the referenced CONTEXT-FORMAT.md and ADR-FORMAT.md files under ./references/ (or remove the links and inline the minimal format spec), so the body's references resolve to real bundle files.

If the format specs are short, consider inlining them as a compact code block instead of offloading to separate files, which would also remove the dependency on missing bundle artifacts.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it uses compact <what-to-do>/<supporting-info> tags and file-structure diagrams without explaining concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	Gives concrete, executable guidance: "Ask the questions one at a time, waiting for feedback on each question before continuing," explicit example challenge phrases in quotes, and a precise three-criteria ADR test — copy-paste ready direction for an instruction-only skill.	3 / 3
Workflow Clarity	The interview process is clearly sequenced (walk each branch, resolve dependencies one-by-one, explore the codebase when a question is answerable there) with an explicit feedback loop ("waiting for feedback on each question before continuing"); the operation is conversational, so destructive/batch validation checkpoints are not required.	3 / 3
Progressive Disclosure	Sections are well-organized and references are clearly signaled one level deep, but the body links to [CONTEXT-FORMAT.md](./CONTEXT-FORMAT.md) and [ADR-FORMAT.md](./ADR-FORMAT.md) which are not present in any bundle directory, so the references are broken.	2 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with a clear what-and-when structure and a distinct DDD/documentation niche. Its only weak spot is trigger-term coverage, which is good but somewhat jargon-heavy and narrow in variation.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the grilling/sharpening/updating actions) and when via a clear "Use when..." clause, matching the anchor for clearly answering both with explicit triggers.	3 / 3
Trigger Term Quality	The trigger "Use when user wants to stress-test a plan against their project's language and documented decisions" contains some natural terms, but coverage of common variations is limited and phrasing leans on DDD jargon rather than the fuller range of phrasings a user might say.	2 / 3
Distinctiveness Conflict Risk	The niche — grilling a plan against the project's domain language and documented decisions (CONTEXT.md, ADRs) — is distinct and tied to specific triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: flutter/agent-plugins
Path: .agents/agents/reidbaker-agent/skills/grill-with-docs/SKILL.md
Commit: 8aaa41d

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.