CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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".

Quality

92%

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 agranado2k/google-books-clojure

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplarily lean instruction-only skill: concrete behavioral directives, an unambiguous interview loop with termination condition, and no token waste. The only improvement opportunity is an illustrative example question to sharpen the expected grilling style.

DimensionReasoningScore

Conciseness

The body is six lean directive sentences with zero explanation of concepts Claude already knows; every instruction (one question at a time, recommended answer per question, prefer codebase exploration) earns its place. The short attribution footer carries required license and variant-skill information without padding.

5 / 5

Actionability

The behavioral guidance is concrete and executable — "Ask the questions one at a time", "For each question, provide your recommended answer", "If a question can be answered by exploring the codebase, explore the codebase instead" — but there is no example of what a good grilling question looks like, which is the minor gap that keeps it below anchor 5.

4 / 5

Workflow Clarity

As a simple single-purpose skill the loop is unambiguous: branch-by-branch ordering ("Walk down each branch of the design tree, resolving dependencies between decisions one-by-one"), explicit pacing, a decision rule for codebase-answerable questions, and a clear termination condition ("until we reach a shared understanding"). No destructive or batch operations are involved, so no validation checkpoint is required.

5 / 5

Progressive Disclosure

The skill is well under 50 lines with no content that warrants external files; the body is organized into short, single-idea paragraphs. Per the rubric's simple-skill guidance, this merits a 5 without external references.

5 / 5

Total

19

/

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: third-person voice, explicit what and when, concrete trigger phrases including the distinctive verbatim "grill me". Its only weaknesses are slight gaps in action enumeration and synonym coverage for trigger terms.

DimensionReasoningScore

Specificity

The description lists several concrete behaviors — "Interview the user relentlessly", "resolving each branch of the decision tree", "until reaching shared understanding" — specifying both method and termination. It falls just short of anchor 5 because it does not enumerate multiple distinct capabilities, and sits above anchor 3 since the actions are notably more specific than that anchor's example.

4 / 5

Completeness

It explicitly answers both what ("Interview the user relentlessly about a plan or design until reaching shared understanding, 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 — a direct match for anchor 5.

5 / 5

Trigger Term Quality

"stress-test a plan", "get grilled on their design", and the verbatim "grill me" are natural phrases users would say, with synonym coverage. A few common variants (e.g., "poke holes in my plan", "devil's advocate", "interrogate me") are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The adversarial plan-interview niche and the verbatim "grill me" trigger make it clearly distinguishable from general planning, review, or brainstorming skills, with minimal risk of triggering for the wrong skill.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agranado2k/tic-tac-toe-with-agentic-sdlc

Path

.claude/skills/grill-me/SKILL.md

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.