deep-interview

Socratic deep interview with mathematical ambiguity gating before execution

Quality

65%

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 ./skills/deep-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 content is a well-sequenced, highly actionable workflow with strong validation gates and feedback loops, but it is a verbose monolith that restates key policies many times and keeps material that could live in reference files inlined. Consolidating the duplicated guidance and splitting stable reference material into bundle files would improve both conciseness and progressive disclosure.

Suggestions

Deduplicate the oversized-context gate and the omx question / structured-input guidance: state each once authoritatively and cross-reference it from the other sections to reduce padding.

Extract stable reference material (the autoresearch specialization, execution-contract schemas, and suggested-config TOML) into files under references/ and link to them one level deep, moving progressive disclosure from 3 toward 4-5.

Tighten the Execution_Policy bullet list by merging near-duplicate rules (e.g., the several omx question / answers[] contract restatements) into a single canonical statement.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several repeated sections: the oversized-context summary gate is restated roughly six times and the omx question / structured-input guidance is duplicated across Execution_Policy, Steps 2b, and Tool_Usage, fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor rather than the mostly-efficient anchor at 3.	2 / 5
Actionability	It gives concrete commands (omx state write, omx question), real JSON payloads with field-level guidance, and explicit artifact paths, which is mostly executable guidance with only minor template placeholders, fitting the 4 anchor better than the pseudocode/incomplete anchor at 3.	4 / 5
Workflow Clarity	Phases 0-5 are clearly sequenced with explicit validation checkpoints (ambiguity threshold, readiness gates, pressure pass, practical closure audit), a re-score feedback loop after each answer, and a Final_Checklist, matching the 'clear sequence with explicit validation steps; feedback loops; checklists' anchor at 5.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the entire ~570-line skill is inlined in SKILL.md; section structure is present but content that could be split (autoresearch specialization, execution contracts, advanced config) is inline with no external references, fitting the 'some structure but content that should be separate is inline' anchor at 3.	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 is specific and distinctive about the skill's purpose but is jargon-heavy, omits explicit 'when to use' trigger guidance, and does not surface the natural trigger phrases the body itself lists. Adding a 'Use when...' clause with user-natural phrasing would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'when the user says deep interview, interview me, or asks you not to assume'.

Soften or gloss 'mathematical ambiguity gating' so the description reads in terms a user would actually say, improving trigger-term quality.

List 1-2 more concrete capabilities (e.g., produces an execution-ready spec, scores ambiguity per round) to lift specificity from 3 toward 4.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Socratic deep interview') and one concrete action ('mathematical ambiguity gating before execution') but is not comprehensive on capabilities, matching the 'names domain and 1-2 concrete actions' anchor rather than the several-actions anchor at 4.	3 / 5
Completeness	It clearly answers 'what' (Socratic deep interview with ambiguity gating before execution) but provides no explicit 'Use when...' trigger clause; per the rubric guideline a missing trigger clause caps completeness at 3, so it cannot reach 4.	3 / 5
Trigger Term Quality	'deep interview' is a natural phrase a user might say, but the description leans on jargon ('mathematical ambiguity gating') and omits common variations present in the body ('interview me', 'ask me everything'), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The combination 'Socratic deep interview' + 'ambiguity gating' carves a fairly distinct niche with only minor overlap risk against general plan/interview skills, fitting 'mostly distinct; minor overlap risk' better than the broader anchor at 3.	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 (572 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: skills/deep-interview/SKILL.md
Commit: 1dcf513

Reviewed: 4 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.