grill-me

Pure socratic interrogation with NO project artifacts at all — no codebase, no CONTEXT.md, no ADRs to reference. One question at a time, walk the decision tree, recommend an answer for each branch. Rare edge case — most grilling happens inside a project, so use grill-with-docs by default (it handles the no-CONTEXT.md case by creating one lazily). Use grill-me ONLY when the user is brainstorming entirely outside a codebase (a fresh idea before any code exists, a hypothetical, a non-software design problem).

Quality

92%

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.

A lean, well-structured conversational skill that efficiently communicates the Socratic interrogation pattern with clear stop conditions. Its main weakness is the lack of concrete examples — a sample question/recommended-answer pair or a template for the closing summary block would make the skill more actionable without adding much length.

Suggestions

Add one brief example showing a sample question with a recommended answer to illustrate the expected format and depth.

Provide a short template or example of the closing summary block ('what crystallized and what's still open') so Claude knows the expected output structure.

Dimension	Reasoning	Score
Conciseness	Every sentence earns its place. No unnecessary explanations of what Socratic questioning is or how design trees work. The skill assumes Claude's intelligence and provides only the behavioral directives needed.	3 / 3
Actionability	The guidance is clear in intent but somewhat abstract — 'walk down each branch of the design tree' and 'resolving dependencies between decisions one-by-one' are directional rather than concrete. No example of what a good question looks like, what a recommended answer format should be, or what the closing summary block should contain.	2 / 3
Workflow Clarity	For this type of conversational skill, the workflow is well-defined: ask one question at a time, provide a recommended answer, explore codebase when possible, and stop when explicit conditions are met. The stop conditions with a closing summary block serve as validation/checkpoint. The single-task nature is unambiguous.	3 / 3
Progressive Disclosure	This is a simple, short skill (under 50 lines) with no need for external references. The content is well-organized into a clear main instruction and a separate stop conditions section. No bundle files are needed or referenced.	3 / 3
	Total	11 / 12 Passed

Description

100%

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

This is an excellent skill description that clearly defines what the skill does (socratic interrogation with decision tree walking), when to use it (brainstorming outside a codebase), and critically, when NOT to use it (explicitly deferring to grill-with-docs for in-project scenarios). The description is concise yet comprehensive, with natural trigger terms and strong distinctiveness from related skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'socratic interrogation', 'one question at a time', 'walk the decision tree', 'recommend an answer for each branch'. These are specific, actionable descriptions of what the skill does.	3 / 3
Completeness	Clearly answers both what ('Pure socratic interrogation... one question at a time, walk the decision tree, recommend an answer') and when ('ONLY when the user is brainstorming entirely outside a codebase — a fresh idea before any code exists, a hypothetical, a non-software design problem'). Also explicitly distinguishes from a sibling skill.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'brainstorming', 'fresh idea before any code exists', 'hypothetical', 'non-software design problem', 'grill-me'. These cover the natural ways a user would describe this scenario.	3 / 3
Distinctiveness Conflict Risk	Exceptionally distinctive — explicitly differentiates itself from 'grill-with-docs' and defines its narrow niche ('no project artifacts at all', 'entirely outside a codebase'). The boundary between this skill and its sibling is crystal clear, minimizing conflict risk.	3 / 3
	Total	12 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: belchman/claude-skills
Commit: be88d6c

Reviewed: 23 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.