interview-me

Thinking partner that refines a half-baked idea into a clear spec through guided questions. Use this skill when the user asks to interview them about any raw idea.

Quality

70%

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 ./interview-me/SKILL.md

Quality

Content

78%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 tight, well-structured instruction skill with concrete question templates, a clear multi-step workflow, and an explicit convergence checkpoint. It assumes Claude's competence and avoids padding, with only minor room to tighten and add error-recovery guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and task-focused with no padding or explanation of concepts Claude already knows; only minor lines (e.g. 'Do this in the background — don't narrate it') could be trimmed, matching the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	Provides concrete executable guidance — specific tool calls (AskUserQuestion, Glob, Grep), categorized question templates per mode, and a defined output structure — with only minor gaps, fitting the 4-anchor; absence of code is fine for an instruction-only skill.	4 / 5
Workflow Clarity	A clear five-step sequence (mode -> repo exploration -> iterative interview -> convergence -> spec) with an explicit convergence checkpoint in Step 3; no destructive/batch operations so the cap does not apply, but there are no explicit error-recovery feedback loops, keeping it at 4 rather than 5.	4 / 5
Progressive Disclosure	A single well-organized SKILL.md with clearly labeled sections and no nested or external references; per the simple-skill guidance, well-organized single-file content with no need for external references scores 5.	5 / 5
	Total	17 / 20 Passed

Description

62%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 communicates a distinct purpose and includes an explicit trigger clause, but the trigger phrasing ('interview them about any raw idea') is awkward and the capability list is a single composite action rather than several concrete ones.

Suggestions

Reword the trigger to a natural user phrase, e.g. 'Use when the user wants to be interviewed about a rough idea to turn it into a spec.'

Split the capability into a few concrete actions (e.g. 'asks targeted clarifying and challenging questions, explores the repo for context, and writes a structured product or technical spec') to lift specificity.

Add common synonyms users might say ('brainstorm', 'spec out', 'refine my idea') to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (refining a half-baked idea into a spec) and one composite concrete action ('through guided questions'), but does not list multiple distinct specific actions; matches the '1-2 concrete actions, not comprehensive' anchor rather than the 4-anchor's 'several specific actions'.	3 / 5
Completeness	Explicitly answers both 'what' (refines a half-baked idea into a clear spec through guided questions) and 'when' ('Use this skill when the user asks to interview them about any raw idea'), but the 'when' clause is slightly awkward and could be more natural, fitting the 4-anchor rather than the fully polished 5-anchor.	4 / 5
Trigger Term Quality	Includes relevant terms ('half-baked idea', 'raw idea', 'interview', 'spec') but the trigger phrasing 'interview them' is awkward rather than a natural user phrase, and common synonyms like 'brainstorm' or 'refine my idea' are missing.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (interview-style idea refinement into specs) with low conflict risk, but the slightly generic 'half-baked idea' / 'raw idea' framing leaves minor overlap with general brainstorming or planning skills, so it sits at 4 rather than 5.	4 / 5
	Total	14 / 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: figlabhq/agent-skills
Path: interview-me/SKILL.md
Commit: abac51b

Reviewed: 3 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.