interview

Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.

Quality

63%

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 ./crates/tui/assets/skills/interview/SKILL.md

Quality

Content

68%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 model of conciseness with clear sectioning and a sensible workflow plus an explicit failure-handling path, but the workflow steps stay at the instructional level without executable patterns or explicit validation checkpoints, holding actionability and workflow_clarity at the midpoint.

Suggestions

Add a concrete example of one structured question with concrete options (e.g. 'Decision: auth strategy. Options: (a) JWT (b) session cookies') to make the guidance copy-paste-ready and lift actionability.

Insert an explicit validation checkpoint in the workflow (e.g. 'Confirm the answer resolves the blocking decision before continuing') to raise workflow_clarity above 3.

Show a minimal brief/spec template so 'Produce a short brief/spec' has an actionable format rather than an abstract instruction.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient, assuming Claude's competence with no padding or explanation of concepts Claude already knows; every line (When to use, Non-goals, Workflow, Failure mode) earns its place.	5 / 5
Actionability	Guidance is concrete in intent ('State the missing decision', 'Offer concrete options', 'Record the answer') but the steps are abstract instructions rather than executable, copy-paste-ready patterns, leaving key execution details (how to phrase options, how to format the brief) unspecified.	3 / 5
Workflow Clarity	A clear 4-step sequence is present, and the Failure mode section adds a labeled feedback path (decline -> proceed with explicit assumptions), but the steps themselves lack explicit validation checkpoints for confirming an answer is sufficient before moving on.	3 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections (When to use, Non-goals, Workflow, Failure mode) appropriate for a sub-50-line single-purpose skill with no external references, with only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

58%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 specific and carves out a distinct, non-generic niche with concrete actions, but it omits an explicit 'Use when...' trigger clause and uses process jargon rather than natural user-facing keywords, capping completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause such as 'Use when the request lacks a material product or implementation choice that cannot be discovered from the workspace or tools.' to lift completeness above 3.

Reword with natural user-facing keywords (e.g. 'clarify requirements', 'ask the user', 'gather missing decisions') so the description matches phrases users actually say.

Lead with the core action verb in third person (e.g. 'Interviews the user...') to strengthen the trigger-term and specificity signals.

Dimension	Reasoning	Score
Specificity	Names the domain (asking about missing product/implementation choices) and several concrete actions ('Ask one useful structured question at a time', 'remember answers and produce a brief/spec', 'Discoverable facts should be investigated'), with only minor gaps in coverage.	4 / 5
Completeness	The 'what' is clear (ask one structured question when a choice is missing, record answers, produce a brief/spec), but the 'when' is only weakly implied via the condition 'only when material product/implementation choices are genuinely missing' rather than an explicit 'Use when...' trigger.	3 / 5
Trigger Term Quality	It lacks natural keywords a user would say; the phrasing is process-oriented jargon ('material product/implementation choices', 'brief/spec') rather than the user-facing terms ('ask me', 'clarify requirements') that would naturally surface this skill.	3 / 5
Distinctiveness Conflict Risk	The skill targets a specific niche (structured interviewing for genuinely missing choices) and carves out a clear distinction from discovery/investigation, with only minor overlap risk with general planning or clarification skills.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Hmbown/CodeWhale
Path: crates/tui/assets/skills/interview/SKILL.md
Commit: 8ae401b

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.