plan-interview

Ensures alignment between user and Codex during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-interview before implementing a new feature, refactoring, or any non-trivial implementation task. The skill runs an upfront interview to gather requirements across technical constraints, scope boundaries, risk tolerance, and success criteria before any codebase exploration. Do NOT use this skill for: pure research/exploration tasks, simple bug fixes, or when the user just wants standard planning without the interview process.

Quality

82%

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

Quality

Content

81%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 a well-sequenced, highly actionable planning workflow with concrete tools, templates, checkpoints, and a worked example, plus an appropriately split one-level-deep reference. Its main weakness is repetition of guardrail phrasing that could be consolidated for token efficiency.

Suggestions

Consolidate the repeated 'do NOT oversimplify / do NOT remove agreed features' guardrail into a single stated rule and reference it by name in the refinement loop, multi-plan synthesis, and fast mode sections rather than restating it each time.

Define the 'fresh-eyes start' step once and reference it by label in each refinement pass and context-refresh section instead of repeating the full instruction.

Consider moving the full worked Example into references/ to keep SKILL.md a tighter overview, since the required-elements template and phase descriptions already convey the workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient process guidance that avoids explaining concepts Claude already knows, but the 'do NOT oversimplify / do NOT remove agreed features' guardrail and the 'fresh-eyes' instruction are repeated across several sections and could be tightened.	3 / 5
Actionability	Highly actionable with concrete tool names (AskUserQuestion, TodoWrite), a specific file path pattern (docs/plans/plan-NNN-<slug>.md), batch sizing ('2-3 questions per batch'), a copy-paste-ready required-elements template, and a full worked example.	5 / 5
Workflow Clarity	The four phases are clearly sequenced with explicit validation checkpoints (cover all four domains before proceeding, refinement stop conditions), feedback loops (fresh-eyes validate -> fix -> retry), and checklists for the complex refinement process.	5 / 5
Progressive Disclosure	Good structure with headers and one well-signaled, one-level-deep reference ('Reusable prompt templates... live in references/iterative-plan-refinement-prompts.md', a verified file), though the body itself remains fairly long with substantial inline content.	4 / 5
	Total	17 / 20 Passed

Description

83%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 clearly states both what the skill does and when to use it, with concrete trigger terms and helpful negative-trigger guidance that reduces conflict risk. It is specific and well-targeted, with only minor gaps in keyword synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (feature/spec planning) and several concrete actions via 'structured interview process' that gathers requirements across four named domains (technical constraints, scope boundaries, risk tolerance, success criteria), with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (structured interview to ensure alignment and gather requirements) and when ('Use this skill when the user invokes /plan-interview before implementing a new feature, refactoring, or any non-trivial implementation task'), with concrete trigger phrases and an explicit do-NOT-use clause.	5 / 5
Trigger Term Quality	Includes natural trigger terms ('new feature', 'refactoring', 'non-trivial implementation task', '/plan-interview') plus negative triggers, giving good keyword coverage though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The interview-process framing tied to the /plan-interview command plus the 'Do NOT use for... standard planning without the interview process' carve-out makes it mostly distinct, with only minor overlap risk against general planning skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pskoett/pskoett-ai-skills
Path: .agents/skills/plan-interview/SKILL.md
Commit: 8a71d70

Reviewed: 6 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.