grill-with-docs

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is extremely concise and clearly delegates to two other skills, fitting a simple single-action skill well. Its only weakness is actionability depth — it names what to invoke but not how the session should be conducted.

Dimension	Reasoning	Score
Conciseness	The body is a single lean line ('Run a `/grilling` session, using the `/domain-modeling` skill.') with no padding and no explanation of concepts Claude already knows.	3 / 3
Actionability	It gives a concrete delegation directive to two named skills, which is actionable, but provides no specifics on how to run the session or what to produce, leaving key details missing.	2 / 3
Workflow Clarity	As a simple single-action skill the instruction ('Run a /grilling session, using the /domain-modeling skill') is unambiguous, which the rubric's simple-skills note allows to score 3.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no bundle files and no need for external references, so the well-organized single-line form qualifies for a 3 per the rubric guidance.	3 / 3
	Total	11 / 12 Passed

Description

50%

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

The description conveys a recognizable purpose but lacks an explicit trigger clause and relies on evocative rather than concrete, user-natural language. It is competent but not exemplary.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g. when the user wants to stress-test or refine a plan/design).

Reword 'relentless interview' into natural trigger terms users would actually say, such as 'interview', 'pressure-test', 'stress-test a plan', or 'challenge a design'.

Replace evocative framing with concrete actions, e.g. 'Questions a plan/design through an interview, then records decisions as ADRs and a glossary.'

Dimension	Reasoning	Score
Specificity	Names the domain ('interview to sharpen a plan or design') and a secondary action ('creates docs (ADR's and glossary)') but uses evocative framing rather than a list of concrete actions, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It states what the skill does but provides no explicit 'when' trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some relevant keywords (interview, plan, design, ADR's, glossary), but 'relentless interview' is idiosyncratic phrasing a user would not naturally say and there is no 'Use when...' clause covering common variations.	2 / 3
Distinctiveness Conflict Risk	It has a fairly distinct niche but the abstract 'sharpen a plan or design' framing could overlap with general planning/design skills, and there are no clearly distinct triggers to push it to a 3.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: coder/agent-tty
Commit: fae02cb

Reviewed: 3 days 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.