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.
80
83%
Does it follow best practices?
Impact
56%
1.03xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels in completeness and distinctiveness. It clearly defines when to use and when not to use the skill, includes an explicit command trigger (/plan-interview), and provides enough context to distinguish it from general planning skills. The main area for improvement is listing more specific concrete actions beyond 'runs an interview.'
Suggestions
Consider listing 2-3 specific concrete actions the interview produces (e.g., 'generates a requirements document, produces scope boundaries checklist, outputs implementation plan') to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (feature/spec planning) and describes the core action (structured interview to gather requirements), mentioning specific areas like 'technical constraints, scope boundaries, risk tolerance, and success criteria.' However, it doesn't list multiple concrete discrete actions—it's mostly one action (running an interview) with some detail about what it covers. | 2 / 3 |
Completeness | Clearly answers both 'what' (structured interview process to gather requirements across technical constraints, scope, risk, success criteria) and 'when' (when user invokes /plan-interview before implementing a new feature, refactoring, or non-trivial implementation). Also includes explicit 'Do NOT use' guidance, which strengthens the 'when' clause. | 3 / 3 |
Trigger Term Quality | Includes the explicit trigger '/plan-interview' and natural terms like 'new feature', 'refactoring', 'implementation task', 'requirements', 'spec planning'. Also includes negative triggers (bug fixes, research/exploration) which help with disambiguation. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The explicit '/plan-interview' command trigger and the specific 'structured interview process' framing make this highly distinctive. The 'Do NOT use' section further reduces conflict risk by excluding standard planning, bug fixes, and research tasks. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent workflow clarity — the four-phase process with explicit checkpoints, edge case handling, and the Knowledge Audit are standout features. The main weakness is length: at ~300+ lines, the skill could benefit from splitting detailed reference material (refinement prompts, interoperability details) into separate files, and trimming some philosophical/explanatory prose that doesn't directly guide behavior.
Suggestions
Move the 'Interoperability with Other Skills' section and the 'Multi-Plan Synthesis' subsection into separate reference files to reduce the main skill's token footprint.
Trim the 'Philosophy' section to 1-2 sentences — the core insight ('propose preparatory refactors as distinct first steps') can be stated without the extended motivation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with some sections that could be tightened — the philosophy section, some explanatory prose around anti-patterns, and the interoperability section add tokens without proportional value. However, most content is genuinely instructive and not redundant with Claude's base knowledge. | 2 / 3 |
Actionability | The skill provides highly concrete guidance: specific question domains with examples, a clear table for edge cases, exact file naming conventions (docs/plans/plan-NNN-<slug>.md), a complete plan template with markdown structure, tool-specific instructions (AskUserQuestion vs chat fallback), and a realistic end-to-end example showing the interview flow. | 3 / 3 |
Workflow Clarity | The four-phase workflow (Interview → Exploration → Plan Generation → Post-Approval) is clearly sequenced with explicit validation checkpoints: the Knowledge Audit between exploration and planning, the fresh-eyes refinement loop with clear stopping criteria, and the planning depth calibration. Edge cases (contradictions, pivots, interruptions) are handled with a decision table, and the refinement loop includes explicit feedback/retry logic. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/iterative-plan-refinement-prompts.md, context-surfing handoff files) and has a clear pipeline position section, but the main SKILL.md itself is quite long and monolithic. Some sections like the detailed refinement loop prompts, the multi-plan synthesis workflow, and the interoperability details could be split into referenced files to keep the primary skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- pskoett/pskoett-ai-skills
- Commit
d6c68fa
- Reviewed
Table of Contents
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.