deep-interview

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 concrete templates, schemas, and a well-sequenced, validation-gated workflow, scoring top marks on actionability and workflow clarity. It loses points on conciseness (heavy cross-section repetition of the pipeline and threshold handling) and progressive disclosure (a large monolithic file with no reference-file split).

Suggestions

De-duplicate the deep-interview -> omc-plan -> pending approval -> execution pipeline and the threshold-source handling, which recur across Execution_Policy, Steps, Tool_Usage, Final_Checklist, and Advanced; state each once and cross-reference.

Move large inline material (the spec template, the ambiguity-scoring prompt, the state JSON schema, the configuration/challenge-mode tables) into separate reference files under references/ and link to them from SKILL.md to improve progressive_disclosure.

Trim the repeated path-discipline and approval-gate reminders to a single canonical statement plus the Final_Checklist entries to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is specific and procedural rather than generic concept-explanation, but the same material (the deep-interview -> omc-plan -> pending approval -> execution pipeline, threshold-source handling, and path discipline) is restated across Execution_Policy, Steps, Tool_Usage, Final_Checklist, and Advanced, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	It provides fully specified, copy-paste-ready artifacts: exact state_write JSON schemas, the ambiguity scoring prompt template, the spec structure template, exact file paths, concrete Skill() invocations with flags (--consensus --direct), and Good/Bad examples, matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	The process is clearly sequenced (Phase 0 -> Phase 1 -> Round 0 -> Phase 2 loop -> Phase 3 -> Phase 4 -> Phase 5) with explicit validation checkpoints (Phase 0 prerequisite verified in 3.5, ambiguity <= threshold gate, pending-approval execution gate, round soft/hard caps), feedback loops (ambiguity stalls -> Ontologist mode, 'Refine further' option), and a comprehensive Final_Checklist, matching the top anchor.	3 / 3
Progressive Disclosure	The body is well-organized into labeled sections, but no bundle reference files exist and the ~800-line skill keeps large templates, the scoring prompt, the state schema, and configuration tables inline rather than split into one-level-deep referenced files, fitting 'some structure but ... content that should be separate is inline'.	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 a tight, distinctive conceptual label but uniformly lands at the middle anchor: it states what the skill is in abstract terms, yet omits explicit 'when to use it' triggers, concrete action verbs, and natural user phrasings beyond 'deep interview'. Adding a trigger clause and concrete actions would lift all four dimensions.

Suggestions

Append a 'Use when...' clause naming explicit triggers (e.g., 'Use when the user has a vague idea and says "interview me", "ask me everything", or wants validated requirements before execution') to satisfy completeness and distinctiveness.

Replace jargon ('mathematical ambiguity gating', 'explicit execution approval') with natural trigger terms a user would actually say to raise trigger_term_quality toward 3.

List concrete actions (e.g., 'asks one question at a time, scores clarity across dimensions, and writes a spec before execution') instead of a single conceptual noun phrase to move specificity from 2 to 3.

Dimension	Reasoning	Score
Specificity	The phrase 'Socratic deep interview with mathematical ambiguity gating before explicit execution approval' names the method and the gating mechanism, but it is a single compound conceptual label rather than a list of multiple concrete actions (e.g., asking targeted questions, scoring clarity, writing a spec), so it matches 'names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It answers 'what' (a Socratic interview with ambiguity gating) but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric a missing explicit-when clause caps completeness at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	'deep interview' is a natural term a user would say, but the rest is jargon ('mathematical ambiguity gating', 'explicit execution approval') users would not utter, and common variations ('interview me', 'ask me everything') are absent, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The Socratic/ambiguity-gating framing is a recognizable niche, but without explicit triggers it could overlap with sibling planning skills (omc-plan, ralplan) that also handle vague ideas, matching 'somewhat specific but could still overlap with similar skills'.	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 (803 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-claudecode
Commit: 6c59219

Reviewed: about 8 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.