deep-interview

Socratic deep interview with mathematical ambiguity gating before execution

Quality

67%

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 ./plugins/oh-my-codex/skills/deep-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 content is highly actionable and clearly sequenced with strong validation gates, but it is verbose with cross-section repetition and monolithic rather than progressively disclosed. Tightening repetition and splitting the large handoff/autoresearch/config blocks into reference files would improve the weaker dimensions.

Suggestions

Move the six detailed execution-handoff contracts and the autoresearch specialization into separate reference files, keeping SKILL.md a concise overview with one-level-deep links.

Deduplicate the repeated "$ultragoal as default, $ralph only as fallback" guidance and consolidate overlap between Execution_Policy, Steps, and Tool_Usage.

Trim verbose prose in Execution_Policy to imperative bullets so every remaining token earns its place.

Dimension	Reasoning	Score
Conciseness	The body is operational and runtime-specific (not concepts Claude already knows), but at 579 lines it repeats guidance across Execution_Policy, Steps, Tool_Usage, and the six verbose handoff options, so it could be tightened considerably, fitting the score-2 anchor.	2 / 3
Actionability	It provides copy-paste-ready JSON state schemas, concrete `omx state write`/`omx question` commands with full payload examples, exact artifact paths, and numeric thresholds, matching the score-3 anchor for fully executable guidance.	3 / 3
Workflow Clarity	Phases 0–5 are explicitly sequenced with numbered steps, readiness gates (Non-goals, Decision Boundaries), per-round ambiguity re-scoring, escalation/stop conditions, and a Final Checklist, matching the score-3 anchor for clear sequence with validation and feedback loops.	3 / 3
Progressive Disclosure	There are no bundle files and the skill is a single 579-line document with the handoff contracts, autoresearch specialization, and config all inline; it is sectioned but content that should be separate is not split out, fitting the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 distinctive and names a clear niche, but it is jargon-heavy and omits any explicit "when to use it" trigger guidance. Adding a Use-when clause and more natural trigger terms would lift the weaker dimensions.

Suggestions

Append a "Use when..." clause naming concrete triggers (e.g. vague requests, missing acceptance criteria, the user saying "interview me" or "deep interview").

Soften jargon and add natural-language keyword variations so trigger_term_quality reflects what users actually say.

List one or two more concrete actions (e.g. "asks targeted questions and scores ambiguity until requirements are execution-ready") to improve specificity.

Dimension	Reasoning	Score
Specificity	Phrases like "Socratic deep interview" and "mathematical ambiguity gating" name the domain and a core action, but the description stops at one action rather than listing multiple concrete capabilities, matching the score-2 anchor.	2 / 3
Completeness	The description states what the skill does but provides no "Use when..." clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	"deep interview" is a natural keyword a user might say, but the rest ("Socratic", "mathematical ambiguity gating", "before execution") is technical jargon with no common variations, fitting the score-2 anchor of some relevant keywords but missing variations.	2 / 3
Distinctiveness Conflict Risk	"Socratic deep interview with mathematical ambiguity gating" carves a clear, narrow niche with a distinctive trigger unlikely to overlap with other skills, matching the score-3 anchor.	3 / 3
	Total	9 / 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 (580 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: Yeachan-Heo/oh-my-codex
Path: plugins/oh-my-codex/skills/deep-interview/SKILL.md
Commit: 435d4a9

Reviewed: 2 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.