grill-me

A relentless interview to sharpen a plan or design.

0.12x

Quality

75%

Does it follow best practices?

Impact

0.12x

1 of 3 eval scenarios. Add 2 more for a full score.

Securityby

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

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.

The body is a minimal, perfectly clean delegator instruction: it is maximally concise, fully executable, and unambiguous about its single action. Its quality rests entirely on the delegation target ('grilling') carrying the actual substance, which is an appropriate design for a user-invoked alias skill.

Dimension	Reasoning	Score
Conciseness	The body is a single line — 'Call the Skill tool with "grilling".' — with zero padding and nothing that explains concepts Claude already knows. Every token earns its place, matching the 'Lean and efficient' anchor; there is nothing that could be trimmed, so it cannot be a 4.	5 / 5
Actionability	The instruction is fully executable and copy-paste ready: an exact tool name ('Skill tool') with an exact argument ('grilling'). For this single-purpose delegator skill nothing concrete is missing from what is written, matching the 'Fully executable' anchor rather than 4's 'minor gaps'.	5 / 5
Workflow Clarity	Per the rubric's simple-skill guideline, a single-task skill with an unambiguous action can score 5: the one action (invoke the 'grilling' skill) is completely unambiguous. There are no destructive or batch operations, so the validation-cap rule does not apply; below 5 would require gaps that do not exist in a one-step workflow.	5 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external reference files (the delegation target is another skill, not a bundled file, and no references/scripts/assets directories exist), and inlines nothing that belongs elsewhere — meeting the simple-skill exception for a top score. No buried or nested references exist that would pull it down.	5 / 5
	Total	20 / 20 Passed

Description

37%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 and has a clear identity, but it omits any usage trigger ('Use when...'), lists no concrete actions beyond a single metaphorical one, and lacks the natural keywords users would say when they need it. It reads more like a tagline than a capability description with invocation guidance.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user has a plan, design, or proposal they want stress-tested, challenged, or pressure-cooked before committing to it.'

Enumerate 1-2 concrete actions instead of the single metaphorical 'relentless interview' — e.g., 'Asks probing follow-up questions, surfaces hidden assumptions, identifies failure modes, and forces explicit decisions'.

Include natural user phrasings as trigger terms such as 'poke holes in my plan', 'challenge my design', 'interview me about this', or 'stress-test this proposal' to improve both trigger quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	"A relentless interview to sharpen a plan or design" names the domain (plan/design refinement) but offers only a single generic action with no concrete capabilities enumerated, matching the anchor 'Names the domain but actions are minimal or generic' ('Processes PDF files'). It is not a 3 because no 1-2 concrete actions (e.g., what the interview does — asks questions, identifies risks, forces decisions) are actually listed.	2 / 5
Completeness	A clear-enough 'what' is present (an interview that sharpens a plan or design) but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3. It cannot be a 4 because the 'when' is not merely implicit, it is wholly missing.	3 / 5
Trigger Term Quality	The only keywords are "interview", "plan", and "design" — one or two generic terms with no natural trigger phrasing a user would actually say (e.g., 'stress-test my plan', 'poke holes in this design', 'challenge my assumptions'). It is not a 3 because even common variations or synonyms of the core use cases are missing, and not a 1 because the language is not pure technical jargon.	2 / 5
Distinctiveness Conflict Risk	"relentless interview" gives the skill a somewhat distinctive character, but the "plan or design" territory overlaps with planning, review, and architecture-design skills and there are no distinct trigger phrases to disambiguate. It fits 'Somewhat specific but could still overlap with similar skills' rather than 4's 'minor overlap risk only'.	3 / 5
	Total	10 / 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: koenighotze/wheel-of-meeting
Path: .agents/skills/grill-me/SKILL.md
Commit: 4aca8e3

Reviewed: 16 hours 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.