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

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

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

Quality

Content

75%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 well-structured, lean, and actionable with concrete script commands and a clear six-step workflow plus a copy-paste output template. It misses top marks mainly because two reference files are not navigated from the overview and the workflow lacks explicit validation checkpoints.

Suggestions

Link forcing_question_patterns.md and when_to_stop_grilling.md from SKILL.md (e.g. under a References section) so all bundle files are discoverable from the overview.

Add an explicit validation/verification checkpoint in the Workflow (e.g. confirm each branch is truly resolved before moving on, and verify the locked-in decisions against the original plan before reporting 'shared understanding reached').

Trim the top derivation note and trailing Version/Derived footers, or consolidate them into the existing blockquote, to remove provenance padding.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no padding of known concepts, but the top derivation note and trailing "Version / Derived" footers are mild provenance padding that could be trimmed, placing it just below the level-5 anchor.	4 / 5
Actionability	Concrete script invocations ("scripts/grill_session_tracker.py --action start") and a copy-paste output-pattern template give mostly executable guidance, but full CLI arguments are deferred to the companion reference and the output pattern is a template rather than a fully worked example, leaving minor gaps versus level 5.	4 / 5
Workflow Clarity	The six-step Workflow is clearly numbered and sequenced with a concrete termination condition ("When all branches resolved: report 'shared understanding reached'"), but it lacks explicit validation checkpoints; this conversational skill avoids the destructive/batch cap but still sits at level 4 rather than the checkpoint-rich level-5 anchor.	4 / 5
Progressive Disclosure	The body is a clear overview with a well-signaled one-level reference to references/companion_tooling.md, but two reference files (forcing_question_patterns.md, when_to_stop_grilling.md) exist in the bundle without being surfaced or linked from SKILL.md, a minor organization gap versus the level-5 anchor.	4 / 5
	Total	16 / 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 clearly answers both what the skill does and when to invoke it, with natural trigger phrases and a distinctive "grill me" hook. It is held back only by behavioral-rather-than-mechanical action specificity and minor overlap with general design-review skills.

Dimension	Reasoning	Score
Specificity	"Interview the user relentlessly", "resolving each branch of the decision tree", "stress-test a plan", and "get grilled on their design" name the domain plus several specific actions, but the actions are behavioral rather than mechanically comprehensive, leaving minor gaps versus the level-5 anchor.	4 / 5
Completeness	It explicitly states 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, matching the level-5 anchor; the present 'Use when' clause avoids the level-3 cap.	5 / 5
Trigger Term Quality	Natural phrases like "stress-test a plan", "get grilled on their design", and the literal "grill me" give good keyword coverage with synonyms, but a few natural variations (e.g. "interrogate my plan", "poke holes in my design") are absent, stopping short of the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The relentless one-question-at-a-time interview niche with the distinctive "grill me" trigger is mostly distinct, but it has minor overlap risk with general plan-review or Socratic-questioning skills, so it sits at level 4 rather than the minimal-conflict level-5 anchor.	4 / 5
	Total	17 / 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: alirezarezvani/claude-skills
Path: engineering/grill-me/skills/grill-me/SKILL.md
Commit: 19392f7

Reviewed: ~6 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.