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

86%

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

Quality

Content

86%Weight 40%Scale 1-5

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

The body is lean and well-structured with explicit stop conditions and a clear closing step, assuming Claude's competence throughout. Adding a short example exchange (a sample question plus its recommended answer) would lift actionability from strong to fully executable.

Suggestions

Add one short example exchange showing a sample question and its recommended answer to make the interaction pattern fully concrete.

Show a brief example of how a branch is resolved (the dependency-walking step) so the 'walk down each branch... one-by-one' instruction has a concrete referent.

Clarify how to resume or carry forward items captured in the closing 'still open' summary, giving the workflow a light feedback loop.

Dimension	Reasoning	Score
Conciseness	Roughly 20 lean lines with no concept explanations or padding; the single rationale line ('Without a stop condition, pure socratic loops wander') is brief and purposeful, and every token earns its place.	5 / 5
Actionability	Provides concrete, specific behavioral instructions ('Ask the questions one at a time', 'For each question, provide your recommended answer', 'explore the codebase instead') but includes no example interaction showing a sample question and recommended-answer format.	4 / 5
Workflow Clarity	Clear sequence with explicit stop-condition checkpoints and a closing summarize step, but it is a genuinely multi-step process without an error-recovery feedback loop, so it stops short of the top anchor.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, and well-organized with a dedicated '## Stop conditions' section, satisfying the simple-skills exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 is strong: it explicitly answers both what and when with concrete triggers, and proactively distinguishes itself from a sibling skill to avoid misuse. Trigger-term coverage and capability specificity are good but leave room for a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete procedural actions ('One question at a time, walk the decision tree, recommend an answer for each branch') but describes a single coherent process rather than comprehensive multi-capability coverage.	4 / 5
Completeness	Clearly states both what it does ('Pure socratic interrogation... walk the decision tree, recommend an answer for each branch') and when to use it ('Use grill-me ONLY when the user is brainstorming entirely outside a codebase...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('brainstorming entirely outside a codebase', 'a fresh idea before any code exists', 'a hypothetical', 'a non-software design problem') but misses common synonyms like whiteboarding or spitballing.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche and explicitly contrasts with the sibling skill ('use grill-with-docs by default... Use grill-me ONLY when...'), minimizing conflict risk.	5 / 5
	Total	18 / 20 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: belchman/claude-skills
Path: plugins/agentic-engineering/skills/grill-me/SKILL.md
Commit: 77a9e6b

Reviewed: 11 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.