CtrlK
BlogDocsLog inGet started
Tessl Logo

grill-me

A relentless interview to sharpen a plan or design.

59

0.12x
Quality

61%

Does it follow best practices?

Impact

5%

0.12x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/grill-me/SKILL.md

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

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.

The body is extremely lean and unambiguous: a single concrete instruction that delegates to a named Skill invocation. For a simple delegating skill it meets the conciseness and workflow bars; the only minor gap is the lack of any example of what the grilling produces.

DimensionReasoningScore

Conciseness

The body is a single line ("Call the Skill tool with \"grilling\".") with no padding and no explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

It gives a concrete, executable instruction (invoke the Skill tool with a specific argument "grilling"), but offers no example of expected output or how the grilling proceeds, leaving a minor gap versus copy-paste-ready full coverage.

4 / 5

Workflow Clarity

This is a simple single-action skill and the simple-skill exception applies: the one action (call the Skill tool with "grilling") is unambiguous, and there is no destructive or batch operation that would trigger the validation cap.

5 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and the content is under 50 lines with no need for external references, so the well-organized single instruction satisfies the simple-skill exception for a top score.

5 / 5

Total

19

/

20

Passed

Description

30%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.

The description is concise but too vague: it conveys a metaphorical purpose without concrete actions, natural trigger phrases, or an explicit "Use when..." clause. It would be hard for Claude to reliably route to this skill from a user request.

Suggestions

Replace the metaphor with concrete actions, e.g. "Interrogates a plan or design with targeted questions to surface assumptions, gaps, and risks before implementation."

Add a "Use when..." trigger clause naming phrases users actually say, e.g. "Use when the user wants to stress-test, pressure-test, or poke holes in a plan or design before committing to it."

Clarify the input/output ("Give it a plan or design; it returns a list of unresolved questions and weak spots") so the skill is distinguishable from generic review skills.

DimensionReasoningScore

Specificity

The phrase "relentless interview to sharpen a plan or design" names a domain (interview/grilling of a plan) but gives only one generic, metaphorical action ("interview") rather than listing concrete operations; matches the "names the domain but actions are minimal or generic" anchor.

2 / 5

Completeness

There is a vague "what" (an interview that sharpens a plan/design) but no "Use when..." trigger guidance, which the guidelines say should cap completeness at 3; placed at 2 because the "what" itself is abstract.

2 / 5

Trigger Term Quality

"interview" and "plan or design" are generic terms a user would rarely say when they actually need this skill; users more likely say "stress-test my plan" or "poke holes in this design", and those natural trigger phrases are absent.

2 / 5

Distinctiveness Conflict Risk

"Sharpen a plan or design" carves out a niche distinct from generic file/code skills, but the language is broad enough to overlap with planning or review-style skills, matching "somewhat specific but could still overlap with similar skills".

3 / 5

Total

9

/

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
The-Vibe-Company/companion
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.