CtrlK
BlogDocsLog inGet started
Tessl Logo

grill-me

Grill the user relentlessly about a plan, design, decision, or set of review findings — working the decision tree in rounds until nothing is left silently assumed. Use when the user wants to stress-test their thinking, says "grill me", or when another skill (for example /review-pr) delegates its evaluation pass here.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured, mostly lean instruction skill with a clear round-based workflow and explicit checkpoints; its only weakness is minor over-explanation and the absence of a worked example question.

Suggestions

Tighten the delegation section ('When a caller delegates a set of findings') by trimming explanatory phrasing to lift conciseness toward 5.

Add one fully filled-in example question (title, body, and recommended answer) to make the format template copy-paste ready.

Consider splitting the delegation-specific rounds into a separate reference file so the core grilling method stays the lean entry point.

DimensionReasoningScore

Conciseness

Efficient prose that assumes Claude's intelligence and avoids explaining known concepts, with a few dense explanatory passages in the delegation section that could be trimmed; not perfectly lean.

4 / 5

Actionability

Provides a concrete question-format template, a recommended-answer format, and explicit operating rules, but no fully filled-in example question, leaving a minor gap.

4 / 5

Workflow Clarity

Sequences the multi-round process explicitly with a clear stopping condition ('done when the frontier is empty'), wait-for-answer checkpoints, and an explicit confirmation close; the destructive/batch cap does not apply to this interactive interview skill.

5 / 5

Progressive Disclosure

A compact single-purpose instructional skill under ~50 lines with no need for bundle files, organized into clearly headed sections, satisfying the simple-skill exception for progressive disclosure.

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.

A strong, specific description with an explicit Use-when trigger and a clear niche; its only weakness is slightly limited trigger-term synonym coverage and a moderately sized action list.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('working the decision tree in rounds', 'until nothing is left silently assumed') with only minor coverage gaps; not a comprehensive multi-action list like the score-5 PDF example.

4 / 5

Completeness

Explicitly answers both what (grill the user about a plan/design/decision/findings via a decision tree in rounds) and when ('Use when the user wants to stress-test their thinking, says "grill me", or when another skill ... delegates').

5 / 5

Trigger Term Quality

Includes natural user phrases like 'stress-test their thinking' and 'grill me', giving good keyword coverage, though a few synonymous phrasings users might say are absent.

4 / 5

Distinctiveness Conflict Risk

'Grill me' is a distinctive trigger and the delegation path from /review-pr carves a clear niche, keeping conflict risk minimal.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
nrwl/nx
Reviewed

Table of Contents

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.