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".

72

Quality

88%

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

88%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 tight, actionable instruction body for a simple skill with no unnecessary padding. Adding brief section headers and an example question would round out progressive disclosure and actionability.

Suggestions

Add a couple of lightweight section headers (e.g., '## How to interview', '## When to explore the codebase') to give the short body clear organization.

Include one or two example questions to make the interviewing style concrete and lift actionability.

Optionally note how to know when shared understanding is reached, so the workflow has an explicit stopping condition.

DimensionReasoningScore

Conciseness

Lean four-line body where every line earns its place ('Ask the questions one at a time', 'If a question can be answered by exploring the codebase, explore the codebase instead') with no padding or over-explanation.

5 / 5

Actionability

Gives concrete, executable directives (one question at a time, provide a recommended answer per question, explore the codebase when an answer is findable there) but lacks concrete examples of question types to fully cover common cases.

4 / 5

Workflow Clarity

As a simple, non-destructive interactive skill the single action is unambiguous and well-sequenced (ask one at a time, resolve branches one-by-one, recommend an answer, defer to codebase exploration), satisfying the simple-skill exception.

5 / 5

Progressive Disclosure

Short self-contained body with no nested references, but it has no section headers or organizational markers, so it falls just short of the 'well-organized sections' expected for a 5.

4 / 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 description that clearly states what the skill does and when to use it, with natural trigger phrases and a distinctive invocation. Minor room for more comprehensive action coverage and additional synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Interview the user relentlessly about a plan or design', 'resolving each branch of the decision tree', 'reaching shared understanding') rather than vague language, though not the comprehensive multi-action coverage of a 5.

4 / 5

Completeness

Explicitly answers both what ('Interview the user relentlessly... resolving each branch of the decision tree') and when ('Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me"') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('stress-test a plan', 'get grilled on their design', 'grill me') with good coverage, though a few common synonyms like 'pressure test' or 'poke holes' are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche with a distinctive literal trigger ('grill me') and specific framing (decision-tree grilling), giving it minimal conflict risk with other skills.

5 / 5

Total

18

/

20

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.