CtrlK
BlogDocsLog inGet started
Tessl Logo

grill-me

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".

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is grill-me in mattpocock/skills

SKILL.md
Quality
Evals
Security

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 exemplary concise, actionable instruction-only skill body: every line is a concrete directive with no wasted tokens. It is simple enough that the lack of multi-step validation workflows or external references is not a deficiency.

DimensionReasoningScore

Conciseness

Six lean lines with zero padding and no explanation of concepts Claude already knows; every directive earns its place, matching the 3 'lean and efficient' anchor.

3 / 3

Actionability

Concrete behavioral directives ('Ask the questions one at a time', 'provide your recommended answer', 'explore the codebase instead') give specific, actionable guidance; absence of code is appropriate for this instruction-only skill per the rubric's code_vs_instruction note.

3 / 3

Workflow Clarity

The single-purpose process is clearly sequenced (interview -> walk each branch one-by-one -> recommend answers -> defer to codebase exploration), and as a simple non-destructive skill it qualifies for 3 under the simple_skills note without needing validation checkpoints.

3 / 3

Progressive Disclosure

At under 50 lines with no external references needed and no bundle files present, the well-organized short body meets the 3 threshold for simple skills per the rubric's judging guidelines.

3 / 3

Total

12

/

12

Passed

Description

90%

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 description with explicit third-person capability statement and a clear, natural 'Use when' trigger clause. Its only weakness is that it describes one richly elaborated action rather than enumerating multiple concrete capabilities.

DimensionReasoningScore

Specificity

Names a concrete domain (interviewing about a plan/design) and elaborates the action ('resolving each branch of the decision tree'), but describes one enriched action rather than a list of multiple distinct concrete actions, so it sits below the 3 anchor.

2 / 3

Completeness

It clearly answers both what ('Interview the user relentlessly... resolving each branch of the decision tree') and when (explicit 'Use when... stress-test a plan, get grilled... or mentions "grill me"'), matching the 3 anchor.

3 / 3

Trigger Term Quality

Natural phrases a user would actually say appear explicitly: 'stress-test a plan', 'get grilled on their design', and the literal 'grill me', giving good coverage of likely trigger language.

3 / 3

Distinctiveness Conflict Risk

The grilling/interviewing niche with the distinctive 'grill me' trigger is clearly distinguishable from other skills and unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
webiny/webiny-js
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.