interview

Socratic interview to crystallize vague requirements

Quality

63%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validation-gated workflow, but it is a monolithic ~820-line document with redundant re-explanations of the Refine gate and no progressive disclosure into bundle reference files.

Suggestions

Split the detailed advisory fan-out lanes and PATH 1-4 routing into a separate reference file (e.g. references/routing.md) and keep SKILL.md as an overview, to lift progressive_disclosure.

Consolidate the Refine gate into one canonical definition and have Steps 5, the Restate exception, and Path B reference it rather than re-explaining it, to tighten conciseness.

Trim repeated emphasis words ("IMPORTANT", "CRITICAL", "MUST") where the imperative is already clear, reducing padding without losing the instruction.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural MCP-contract detail that earns its place, but the Refine gate is re-explained in Steps 4, 5, the Restate exception, and Path B, and repeated emphasis ("IMPORTANT", "CRITICAL", "MUST") pads the text — matching the score-2 "mostly efficient but could be tightened" anchor rather than the lean score-3 anchor.	2 / 3
Actionability	It provides fully executable guidance: concrete tool/argument blocks ("Tool: ouroboros_interview / Arguments:"), copy-paste JSON ask_user payloads, an executable curl version-check, and exact answer prefixes like "[from-code][auto-confirmed]", matching the score-3 "fully executable; copy-paste ready" anchor.	3 / 3
Workflow Clarity	It has a clearly numbered sequence (Step 0, 0.5, Path A steps 1-11) with explicit validation checkpoints (Seed-ready Acceptance Guard, Restate gate, Dialectic Rhythm Guard) and a Retry-on-Failure feedback loop with fallback to Path B, matching the score-3 "clear sequence with explicit validation steps and feedback loops" anchor.	3 / 3
Progressive Disclosure	No references/, scripts/, or assets/ bundle files exist, so all ~820 lines live in one SKILL.md; section headings give some structure, but large blocks (advisory fan-out lanes, path-by-path routing) that should be split into reference files are inline, matching the score-2 "content that should be separate is inline" anchor.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concise and third-person with a clear niche, but it states only a single action and omits an explicit "Use when..." trigger clause, leaving every dimension at the midpoint.

Suggestions

Add a "Use when..." clause naming explicit triggers, e.g. "Use when the user says 'interview me' or asks to clarify vague requirements into a spec."

List two or three concrete actions (e.g., "asks Socratic questions, routes code vs human-judgment answers, restates a one-line goal") to lift specificity from 2 to 3.

Add natural keyword variations ("clarify requirements", "requirements gathering", "spec") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action ("Socratic interview to crystallize vague requirements"), but it lists only a single conceptual action rather than multiple specific concrete actions, so it sits between the score-2 anchor and the multi-action score-3 anchor.	2 / 3
Completeness	It answers "what" (an interview that crystallizes vague requirements) but contains no "Use when..." clause or explicit trigger guidance in the description itself, so per the guideline a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some relevant natural keywords ("interview", "requirements") but "Socratic" and "crystallize" are somewhat metaphorical/jargon, and common variations like "clarify", "spec", or "requirements gathering" are missing — matching the score-2 "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	"Socratic interview to crystallize vague requirements" carves a recognizable niche but, without explicit triggers in the description, it could still overlap with general requirements-gathering or planning skills, matching the score-2 "somewhat specific but could still overlap" anchor.	2 / 3
	Total	8 / 12 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 (826 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: f09fa36

Reviewed: about 3 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.