grill-me

Interview the user relentlessly about a plan to reach shared understanding, resolving each branch of the decision tree. Use when stress-testing a plan or "grill me".

Quality

85%

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

86%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 lean and actionable for a single-purpose conversational skill, with a clear interview workflow and a single one-level reference to one-sentence-test. It avoids over-explaining and respects Claude's intelligence throughout.

Dimension	Reasoning	Score
Conciseness	A lean ~8-line body that assumes Claude's competence, introduces no concept padding, and has every token earning its place.	5 / 5
Actionability	Gives concrete executable directives ('Ask the questions one at a time', 'explore the codebase instead', 'apply one-sentence-test before declaring shared understanding'); minor gap is the absence of a worked example dialogue.	4 / 5
Workflow Clarity	Clear sequence (ask one at a time -> resolve branches -> apply one-sentence-test -> declare shared understanding) with an explicit stopping/checkpoint via one-sentence-test; no error-recovery loop is needed since this is non-destructive.	4 / 5
Progressive Disclosure	Short single-purpose body with one clearly signaled one-level-deep reference ([one-sentence-test](../one-sentence-test/SKILL.md)); no nesting and easy navigation, appropriate for a sub-50-line skill.	5 / 5
	Total	18 / 20 Passed

Description

83%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, third-person, and clearly pairs a concrete 'what' with an explicit 'Use when' trigger anchored on the natural phrase 'grill me'. It is specific and largely free of fluff, with only minor room for additional synonyms.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Interview the user relentlessly', 'resolving each branch of the decision tree', 'provide your recommended answer') with only minor coverage gaps around how the interview concludes.	4 / 5
Completeness	Explicitly answers both what (interview the user about a plan, walking the decision tree, recommending answers) and when ('Use when stress-testing a plan or "grill me"') with concrete triggers.	5 / 5
Trigger Term Quality	Includes the natural trigger phrase 'grill me' and 'stress-testing a plan', which a user would actually say; a few synonyms (e.g., 'interrogate', 'pressure-test') are missing.	4 / 5
Distinctiveness Conflict Risk	The 'grill me' / stress-test-a-plan niche is distinct from most skills, with only minor overlap risk against general planning or design-review skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/grill-me/SKILL.md
Commit: abe10f3

Reviewed: 5 days 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.