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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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 exceptionally concise and gives reasonably concrete direction for a simple instruction-only skill, with a clear implicit workflow. The main gaps are the absence of an example question/recommended-answer exchange and any structural sectioning or checkpoints for ambiguous answers.

Suggestions

Add one short worked example showing a sample question plus a recommended answer, so the 'provide your recommended answer' instruction is unambiguous.

Add a brief checkpoint for ambiguity (e.g., 'If the user's answer is contradictory or unclear, restate the contradiction and ask them to resolve it before moving to the next branch') to give the workflow an explicit feedback loop.

Introduce minimal section headers (e.g., '## How to grill', '## When to explore the codebase') to add light structure even within a short skill.

Dimension	Reasoning	Score
Conciseness	Four lean sentences with no padding and no explanation of concepts Claude already knows; every token earns its place and it fully assumes Claude's competence. Firmly matches the 'lean and efficient' anchor.	5 / 5
Actionability	Gives concrete, executable direction for an instruction-only skill: 'Walk down each branch of the design tree, resolving dependencies between decisions one-by-one', 'For each question, provide your recommended answer', and 'explore the codebase instead' when an answer is discoverable there. Not a 5 because the guidance stays somewhat abstract (no example question/recommended-answer pair) leaving minor gaps.	4 / 5
Workflow Clarity	A clear implicit sequence for a simple single-purpose skill — interview branch-by-branch, resolve dependencies one-by-one, propose a recommended answer per question, and prefer codebase exploration when possible. Not a 5 because there are no explicit checkpoints or a feedback loop for when the user's answer is ambiguous or contradictory.	4 / 5
Progressive Disclosure	The body is appropriately minimal and self-contained for an under-50-line single-task skill with no need for external references, and no bundle files exist. Not a 5 because the two paragraphs have no section headers or structural signaling, which is a minor organization gap even for a short skill.	4 / 5
	Total	17 / 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.

The description is strong: it clearly states what the skill does and provides explicit, natural trigger phrases including the distinctive 'grill me'. The main weakness is specificity — the described actions are somewhat abstract rather than a comprehensive concrete list.

Suggestions

Tighten the 'what' clause with more concrete interviewing actions (e.g., 'ask one focused question at a time, propose a recommended answer, then probe the user's agreement or objections') to lift specificity.

Add one or two synonymous trigger phrasings (e.g., 'pressure-test my design', 'interrogate my plan') to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Interview the user relentlessly about a plan or design') and 1-2 concrete actions ('resolving each branch of the decision tree', 'reaching shared understanding'), but the actions are somewhat abstract rather than a comprehensive concrete list. Not a 4 because it does not list several specific distinct actions, only the overarching interviewing behavior.	3 / 5
Completeness	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.	5 / 5
Trigger Term Quality	Includes natural user phrasing — 'stress-test a plan', 'get grilled on their design', and the literal trigger 'grill me' — giving good keyword coverage. Not a 5 because it lacks synonyms/file-extension-style breadth, but the direct 'grill me' trigger is strong.	4 / 5
Distinctiveness Conflict Risk	The literal 'grill me' trigger carves a clear niche that is unlikely to fire for unrelated skills, though the broader 'stress-test a plan' framing has minor overlap risk with general planning or brainstorming skills. Not a 5 because of that residual overlap with planning-oriented skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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: openstatusHQ/data-table-filters
Path: .agents/skills/grill-me/SKILL.md
Commit: 5017387

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.