Name: grill-me
Rating: 64 (1 reviews)
Author: alirezarezvani

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

76%

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

Fix and improve this skill with Tessl

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

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

Quality

Content

71%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 admirably lean and the workflow is clearly sequenced, but its actionability and progressive disclosure are undermined because all referenced scripts and the companion reference file are absent from the bundle, leaving dangling links and non-executable commands.

Suggestions

Ship the referenced bundle files (scripts/decision_tree_extractor.py, scripts/question_generator.py, scripts/grill_session_tracker.py, references/companion_tooling.md) or remove the references and inline the actual instructions so commands are executable.

Replace the placeholder output template (Q[i]/[total]: [question]...) with at least one concrete filled-in example so the pattern is unambiguous.

Add an explicit mid-session validation checkpoint (e.g., 'After each answer, confirm the decision is locked before moving to the next branch') to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~45-line body is lean and directive — "Ask the questions one at a time", "If a question can be answered by exploring the codebase, explore the codebase instead" — with no padding or explanation of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	It gives concrete structure (a 6-step workflow, named scripts, an output template) but the referenced scripts — `scripts/decision_tree_extractor.py`, `scripts/question_generator.py`, `scripts/grill_session_tracker.py` — do not exist in the bundle, and the output "code" block is a placeholder template (`[question]`, `[your call + 1-sentence rationale]`), so the guidance is not actually executable as written.	3 / 5
Workflow Clarity	The 6-step numbered workflow is clearly sequenced with named tool invocations and a terminal checkpoint ("When all branches resolved: report 'shared understanding reached'"); it misses 5 only because there is no mid-process validation step, though that is forgivable for a non-destructive interview skill.	4 / 5
Progressive Disclosure	The body is well sectioned and clearly signals references to `references/companion_tooling.md` and three `scripts/*.py` files, but no bundle directories exist, so every referenced path is a broken/dangling link — navigation is structurally signaled but functionally dead, capping it below 4.	3 / 5
	Total	15 / 20 Passed

Description

82%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 cleanly states what the skill does and when to use it, with the literal "grill me" trigger and natural synonyms. Its only weakness is that the concrete actions are inherently soft interview behaviors rather than a comprehensive, enumerable action set.

Dimension	Reasoning	Score
Specificity	It names the domain and a couple of concrete actions — "Interview the user relentlessly", "resolving each branch of the decision tree", "stress-test a plan" — but the actions are soft interview behaviors rather than a comprehensive list of concrete operations, so it sits at the 1-2 concrete actions anchor rather than 4-5.	3 / 5
Completeness	It explicitly answers both "what" ("Interview the user relentlessly... 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, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	The "Use when... stress-test a plan, get grilled on their design, or mentions \"grill me\"" clause includes natural user phrases and the literal verbatim trigger "grill me"; it falls short of 5 only because a few common synonyms (e.g., "challenge my assumptions", "poke holes in my plan") are absent.	4 / 5
Distinctiveness Conflict Risk	The grilling/interview niche with triggers like "grill me" and "get grilled on their design" is clearly distinct from other skills and unlikely to fire for the wrong skill.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/grill-me/SKILL.md
Commit: 19392f7

Reviewed: ~8 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.