plan-interview

Ensures alignment between user and Claude 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.

2.70x

Quality

84%

Does it follow best practices?

Impact

100%

2.70x

Average score across 3 eval scenarios

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 content is a well-structured, highly actionable planning workflow with clear sequencing and validation checkpoints, supported by one cleanly signaled reference file. Its main weakness is moderate verbosity in rationale/philosophy passages that assume less of Claude than necessary.

Suggestions

Trim the Philosophy section's explanatory rationale ("Agents default to plowing straight through implementation...") down to the operative instruction, since Claude already understands this failure mode.

Move the worked OAuth Example and/or the full required-elements markdown template into a reference file, keeping only a pointer inline to reduce SKILL.md length.

Cut closing justification sentences like "This audit prevents the most common agent failure..." since the preceding imperative steps already carry the guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient process guidance, but several passages explain concepts Claude already knows (the Philosophy rationale about agents "plowing straight through implementation", the closing rationale sentences in Knowledge Audit) that could be trimmed without losing actionability.	3 / 5
Actionability	Provides fully executable guidance: four required question domains with sub-bullets, 2-3 questions per batch, the plan file path format `docs/plans/plan-NNN-<slug>.md`, a required-elements markdown template, and a concrete worked OAuth example covering the common case.	5 / 5
Workflow Clarity	The four-phase process is clearly sequenced with explicit checkpoints: the refinement stop-conditions, the Knowledge Audit "stop and surface it" rule, the edge-case handling table, and the fresh-eyes restart loop provide strong validation and feedback structure.	5 / 5
Progressive Disclosure	Good structure with a single well-signaled one-level-deep reference (`references/iterative-plan-refinement-prompts.md`) referenced inline, but the body is fairly long with inline template/example content that a cleaner split could offload, keeping it just below the 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

87%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 strong: it clearly states what the skill does and when to use it, with concrete trigger phrases and explicit exclusion guidance. It is slightly held back by action phrasing that leans abstract rather than enumerating multiple discrete concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ("runs an upfront interview to gather requirements across technical constraints, scope boundaries, risk tolerance, and success criteria"), but the actions are somewhat abstract rather than a comprehensive list of distinct concrete operations, so it sits below the 5 anchor.	4 / 5
Completeness	Explicitly answers both "what" (ensures alignment via a structured requirements interview across four named domains) and "when" ("Use this skill when the user invokes /plan-interview before implementing a new feature, refactoring...") with concrete trigger phrases, plus negative triggers.	5 / 5
Trigger Term Quality	Includes natural trigger terms users would say ("/plan-interview", "new feature", "refactoring", "non-trivial implementation task") with good coverage, though a few common synonyms (e.g. "spec", "planning") are only weakly present.	4 / 5
Distinctiveness Conflict Risk	Tied to a distinct command invocation (/plan-interview) with explicit non-trigger guidance, giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	18 / 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: skills/plan-interview/SKILL.md
Commit: 8a71d70

Reviewed: 11 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.