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

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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, directive body: every line is an executable instruction covering pacing, question strategy, recommended answers, and a codebase-first shortcut, with a clear termination condition. As a sub-50-line single-purpose skill needing no external content, it fully satisfies the simple-skill exceptions for workflow clarity and progressive disclosure.

DimensionReasoningScore

Conciseness

The body is ~10 lines of pure directive text — "Interview me relentlessly about every aspect of this plan", "Ask the questions one at a time" — with zero concept explanation or padding. The only non-instruction text is a two-line MIT attribution footer, which is required licensing, so every token earns its place.

5 / 5

Actionability

Every operational decision is explicitly specified: pacing ("Ask the questions one at a time"), question content ("Walk down each branch of the design tree, resolving dependencies between decisions one-by-one"), per-question behavior ("provide your recommended answer"), and a codebase-first rule ("If a question can be answered by exploring the codebase, explore the codebase instead"). Per the rubric's instruction-skill note, the absence of code is not penalized when the guidance is this concrete.

5 / 5

Workflow Clarity

This is a simple single-task skill and the single action is unambiguous: iterate the design tree branch-by-branch, one question at a time, until the explicit termination condition "until we reach a shared understanding". The simple-skill exception applies, and there are no destructive or batch operations, so no validation cap is triggered.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and consists of well-organized short directives — matching the rubric guideline that such skills can score 5 with just good organization. The footer's pointer to the sibling /grill-with-docs skill for glossary/ADR projects actively aids navigation.

5 / 5

Total

20

/

20

Passed

Description

78%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 both what the skill does and when to use it, with an explicit 'Use when' clause and the distinctive literal trigger "grill me". It falls just short of the top anchors on specificity (the action description is one behavior with its mechanism rather than an enumeration) and on trigger coverage (missing common synonyms).

Suggestions

Enumerate the concrete behaviors in the 'what' clause, e.g. "challenges assumptions, surfaces risks and tradeoffs, and pins down blocking decisions" in addition to interviewing.

Add natural trigger synonyms such as "poke holes in my plan", "pressure-test my design", or "interrogate my plan" to the 'Use when' clause.

Narrow the broad "stress-test a plan" trigger (e.g. "stress-test a plan by being interviewed on it") to reduce overlap with general plan-review skills.

DimensionReasoningScore

Specificity

"Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree" names the domain and 1-2 concrete actions (interview; resolve decision-tree branches), but does not enumerate several specific actions. It is above score 2 because the actions are concrete rather than generic, but below score 4 because coverage is not a list of several specific behaviors.

3 / 5

Completeness

It explicitly answers both questions: the "what" ("Interview the user relentlessly... resolving each branch of the decision tree") and the "when" with concrete trigger phrases ("Use when user wants to stress-test a plan, get grilled on their design, or mentions 'grill me'"). This matches the anchor for a clear, explicit what AND when with concrete triggers.

5 / 5

Trigger Term Quality

The trigger clause includes natural phrases users would actually say — "stress-test a plan", "get grilled on their design", and the literal trigger "grill me". It falls short of 5 because common synonyms like "poke holes in my plan", "pressure-test", or "interrogate my design" are missing, but is above 3 since several natural terms are present.

4 / 5

Distinctiveness Conflict Risk

The interview/grill niche is clear and the trigger "grill me" is highly distinctive, but the broader phrase "stress-test a plan" carries minor overlap risk with general plan-review or brainstorming skills. Not 5 because of that overlap; not 3 because the grilling framing and literal trigger set it apart from similar skills.

4 / 5

Total

16

/

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/ai-report-platform

Path

.agents/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.