deep-interview

Socratic deep interview with mathematical ambiguity gating before execution

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/oh-my-codex/skills/deep-interview/SKILL.md

Quality

Content

70%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 is highly actionable and exceptionally clear in its multi-phase workflow with strong validation checkpoints, but it is notably verbose due to repeated tool-invocation and fallback-ordering restatements, and it keeps all detail inline rather than splitting into referenced files.

Suggestions

De-duplicate the omx question invocation contract and OMX_QUESTION_RETURN_PANE prefix, stating them once in Tool_Usage and cross-referencing from Phase 2b and Execution_Policy.

Move the six execution handoff contracts and the autoresearch specialization into separate reference files (e.g. HANDOFFS.md, AUTORESEARCH.md) with one-level-deep links from the body.

Consolidate the repeated $ultragoal/$ralph/$team fallback-ordering guidance into a single stated rule to cut token cost.

Dimension	Reasoning	Score
Conciseness	The ~580-line body restates the same omx question invocation contract and return-pane prefix across Execution_Policy, Tool_Usage, and Phase 2b, and repeats the $ultragoal/$ralph/$team fallback ordering several times, producing noticeably verbose padded sections despite accurate content.	2 / 5
Actionability	It provides fully executable, copy-paste-ready guidance: concrete omx state write commands, complete omx question JSON payloads, canonical artifact paths, ambiguity formulas, and a stride-contract JSON block covering the common cases.	5 / 5
Workflow Clarity	The process is clearly sequenced into Phase 0-5 with explicit validation checkpoints (per-round ambiguity re-scoring, readiness gates for Non-goals and Decision Boundaries, a mandatory pressure pass, a closure audit, and a Final_Checklist) plus feedback loops for error recovery.	5 / 5
Progressive Disclosure	The skill is internally well-organized via section tags and phase headers, but it is a monolithic file with no bundle references and large blocks (six handoff contracts, autoresearch specialization, config schema) that could live in separate one-level-deep reference files.	3 / 5
	Total	15 / 20 Passed

Description

48%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 distinctive and names the domain well, but it is too abstract: it states what the skill is rather than concrete actions it performs, and it omits any explicit "Use when..." trigger guidance.

Suggestions

Add concrete actions, e.g. "Asks targeted clarifying questions, scores ambiguity quantitatively, and crystallizes execution-ready specs."

Append an explicit "Use when..." clause naming natural triggers users say, e.g. "Use when a request is vague or the user says 'deep interview', 'interview me', or 'don't assume'."

Include common synonyms/file-context terms (e.g. requirements clarification, ambiguity scoring) to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Socratic deep interview", "mathematical ambiguity gating") but lists no concrete actions the skill performs, only implying a gating action; actions are minimal rather than comprehensive.	2 / 5
Completeness	It gives a clear "what" (Socratic deep interview with ambiguity gating before execution) but entirely lacks a "when"/"Use when..." clause, which the rubric caps at 3.	3 / 5
Trigger Term Quality	"deep interview" is a natural trigger term users would say, but the description omits common synonyms/extensions like "interview me", "ask me everything", or "clarify requirements" that the body itself lists.	3 / 5
Distinctiveness Conflict Risk	"Socratic deep interview with mathematical ambiguity gating" carves a fairly distinct niche with minimal overlap risk, though it could still brush against generic planning/requirements skills.	4 / 5
	Total	12 / 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 (581 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: 3ad79a8

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.