interview

Socratic interview to crystallize vague requirements

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude-plugin/skills/interview/SKILL.md

Quality

Content

66%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 skill body is highly actionable with crisp tooling examples and a well-gated workflow, but it is noticeably verbose and monolithic, repeating rules inline instead of offloading detail to bundle reference files.

Suggestions

Move the large fan-out submission contract and data-measurement lane spec into a references/ file and link to it from SKILL.md to fix the monolithic structure.

Deduplicate the Refine-gate and short-PATH-2 skip rules that are restated in Step 4, Step 9, and the Interviewer Behavior section; state each rule once.

Trim the meta-rationale paragraphs (e.g., why a constant exists, 'this is exactly why the declaration exists') since Claude can infer these justifications.

Dimension	Reasoning	Score
Conciseness	The ~880-line body restates the Refine-gate and short-PATH-2 exception rules multiple times, belabors the deferred-schema guard, and pads many paragraphs with rationale Claude could infer, matching the score-2 anchor of noticeably verbose with several unnecessary explanations.	2 / 5
Actionability	It provides exact MCP tool names, copy-paste JSON argument blocks, concrete bash for the version check, exact answer prefixes, and a full worked example session, fully executable and covering the common cases.	5 / 5
Workflow Clarity	Steps are explicitly sequenced (Step 0 through 11) with named validation gates (Refine, Seed-ready Acceptance Guard, Restate), a Dialectic Rhythm Guard, and a Retry-on-Failure feedback loop, giving clear checkpoints and error-recovery loops.	5 / 5
Progressive Disclosure	No bundle files exist and the body is a monolithic wall of text that inlines large protocol specs (fan-out submission contract, data-measurement lane) that clearly belong in separate referenced files, with only buried inline source-path references.	2 / 5
	Total	14 / 20 Passed

Description

53%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 third-person and names a clear, distinct purpose but is terse and lacks an explicit 'when to use' trigger clause, which caps completeness and leaves keyword coverage thin.

Suggestions

Add a 'Use when ...' clause with concrete trigger phrases (e.g., 'Use when the user says interview me, clarify requirements, or needs to turn a vague idea into a spec').

Expand the action list with concrete verbs (e.g., 'asks Socratic questions, inspects the codebase, structures answers, and confirms a one-line goal') to lift specificity.

Include natural synonyms and the file/command trigger (e.g., 'ooo interview') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description 'Socratic interview to crystallize vague requirements' names the domain and a concrete intended outcome, but 'crystallize' is metaphorical and the action set is not comprehensive, matching the score-3 anchor that lists domain plus 1-2 actions.	3 / 5
Completeness	It clearly states the 'what' (a Socratic interview that crystallizes vague requirements) but has no 'Use when...' trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Only 'interview' is a natural user keyword; 'Socratic' is jargon users rarely say, and the description omits common variations/synonyms, matching the score-3 anchor with some relevant but incomplete keyword coverage.	3 / 5
Distinctiveness Conflict Risk	'Socratic interview to crystallize vague requirements' carves a fairly distinct niche for requirement-discovery with low conflict risk, with only minor overlap against general spec/requirements skills.	4 / 5
	Total	13 / 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
skill_md_line_count	SKILL.md is long (885 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Q00/ouroboros
Path: .claude-plugin/skills/interview/SKILL.md
Commit: 645a2f0

Reviewed: 1 day 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.