interview

Socratic interview to crystallize vague requirements

Quality

58%

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 ./skills/interview/SKILL.md

Quality

Content

62%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 delivers a well-sequenced, highly actionable interview orchestration workflow with strong validation checkpoints and feedback loops. Its main weaknesses are verbosity (discursive philosophical prose that does not earn its tokens) and a monolithic structure that inlines material better suited to separate reference files.

Suggestions

Move the data-context lane essay and the fan-out submission contract into a dedicated reference file (e.g. references/fanout-contract.md), keeping only a one-line pointer plus the binding rules in SKILL.md.

Cut the philosophical justifications (e.g. paragraphs on why a constant exists, why a measurement carries no cost metadata) down to the operative rule; assume Claude understands the rationale.

Extract the PATH 1a/1b/2/3/4 routing criteria and JSON templates into references/routing.md or a condensed table to reduce the inline volume while preserving actionability.

Dimension	Reasoning	Score
Conciseness	The body is ~900 lines with several padded discursive essays (e.g. the data-context lane philosophy on read-only tools, repeated rhetorical justifications for why constants exist) that explain rationale Claude does not need. It is not a 1 because the core procedural content is concrete and not merely restating concepts Claude already knows; not a 3 because the volume of unnecessary explanatory prose clearly exceeds 'some' over-explanation.	2 / 5
Actionability	It provides concrete, executable guidance: real bash commands (curl version check, uv/pipx upgrade), JSON ask_user templates, MCP tool argument blocks, and a fully specified PATH 1a/1b/2/3/4 routing decision tree. It is not a 5 because many arguments remain placeholders (<session ID>, <user's topic>) and the fan-out submission schema, while detailed, leaves some assembly to Claude; not a 3 because the guidance is concrete and mostly copy-paste ready, not pseudocode.	4 / 5
Workflow Clarity	The flow is explicitly sequenced (Step 0 version check, Step 0.5 MCP load, Path A steps 1-11, Path B fallback) with explicit validation checkpoints (Refine gate, Seed-ready Acceptance Guard tri-panel, Restate gate), feedback loops (Retry on Failure, Path B fallback), and checklists (Non-Skippable Gates, Dialectic Rhythm Guard). This matches the anchor for clear sequence with explicit validation, error-recovery loops, and process checklists.	5 / 5
Progressive Disclosure	No bundle files (references/, scripts/, assets/) exist; the skill is a single monolithic SKILL.md with heavy inlined content (fan-out submission semantics, data-measurement essay, MCP meta-field handling) that clearly belongs in separate reference files. It is not a 2 because section headers and the external references to seed-closer.md / socratic-interviewer.md are clearly signaled, giving real structure; not a 4 because large tracts of reference-grade detail are inlined rather than split out.	3 / 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 states a clear purpose and a distinct niche, but lacks an explicit "Use when..." trigger clause and the natural trigger phrases ("interview me", "clarify requirements") live only in the body. It is adequate but not exemplary.

Suggestions

Add an explicit 'Use when...' clause to the description, e.g. 'Use when the user says "interview me", asks to clarify or crystallize vague requirements, or needs to turn a fuzzy idea into a specification.'

Expand trigger-term coverage in the description itself with synonyms users actually say ('clarify requirements', 'gather specs', 'nail down what I want') rather than leaving them only in the body.

Optionally name one more concrete capability (e.g. '...and route code-answerable vs human-judgment questions') to lift specificity from one action toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The phrase "Socratic interview to crystallize vague requirements" names the domain and one concrete action (turning vague requirements into clear ones), matching the anchor that names a domain plus 1-2 actions without being comprehensive. It is not a 2 because "crystallize vague requirements" is a more concrete action than the generic "Processes PDF files"; not a 4 because only a single action is stated with no breadth of capabilities.	3 / 5
Completeness	It gives a clear "what" (Socratic interview to crystallize vague requirements) but no "when" / "Use when..." clause; per the guideline a missing explicit trigger clause caps completeness at 3. Not a 4 because there is no "when" at all, even a weak one; not a 2 because the "what" is clear rather than vague.	3 / 5
Trigger Term Quality	"interview" and "requirements" are natural terms a user might say, but the description omits common variations/synonyms like "clarify", "spec", or "gather requirements" (those appear only in the body, not the description field). It is above a 2 because two genuine natural keywords are present, but below a 4 because several natural phrasings users would actually say are missing from the description itself.	3 / 5
Distinctiveness Conflict Risk	"Socratic interview to crystallize vague requirements" carves a clear niche (requirements elicitation via Socratic questioning) with distinct triggers and low overlap risk. It is not a 5 because it could still mildly overlap with generic "clarify" or "planning" skills; not a 3 because the Socratic-requirements framing is specific rather than broadly overlapping.	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 (914 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: skills/interview/SKILL.md
Commit: 80333ae

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.