cross-examine

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Quality

100%

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-me in mattpocock/skills

Quality

Content

100%

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

An exceptionally economical body that gives complete, unambiguous behavioral guidance in four sentences, with no wasted tokens and no need for external references or sections.

Dimension	Reasoning	Score
Conciseness	Four lean sentences with no padding and no explanation of concepts Claude already knows; every line carries an actionable instruction.	3 / 3
Actionability	Instruction-only skill with concrete, executable directives — 'Ask the questions one at a time', 'provide your recommended answer', and 'explore the codebase instead' — so absence of code is not penalized.	3 / 3
Workflow Clarity	A simple single-task skill under 50 lines with a clear sequence (walk each branch, resolve dependencies one-by-one, give recommended answers) and no destructive or batch operations requiring validation checkpoints.	3 / 3
Progressive Disclosure	Self-contained under-50-line skill with no external references needed and a clear logical flow, satisfying the simple-skill allowance for full progressive-disclosure credit.	3 / 3
	Total	12 / 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.

A tight, well-formed description that specifies a concrete behavioral mechanism, provides explicit third-person triggers in natural user language, and cleanly separates capability from invocation conditions.

Dimension	Reasoning	Score
Specificity	Concrete mechanism is explicitly stated — 'resolving each branch of the decision tree' and 'resolving dependencies between decisions one-by-one' — naming multiple specific actions rather than vague language.	3 / 3
Completeness	Clearly answers both 'what' (interview the user, resolve each branch of the decision tree) and 'when' via an explicit 'Use when...' clause with concrete triggers.	3 / 3
Trigger Term Quality	Includes natural user phrasing — 'stress-test a plan', 'get grilled on their design', and the explicit quoted trigger 'grill me' — covering the ways a user would actually request this.	3 / 3
Distinctiveness Conflict Risk	Occupies a distinct niche (relentlessly cross-examining a plan) with specific triggers like 'grill me', making it unlikely to fire for unrelated skills.	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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zebbern/claude-code-guide
Path: skills/cross-examine/SKILL.md
Commit: af7d491

Reviewed: about 8 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.