refactor-pass
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build/tests to verify behavior.
85
77%
Does it follow best practices?
Impact
97%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/refactor-pass/SKILL.mdQuality
Discovery
82%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 solid description that clearly communicates both what the skill does and when to use it, with good trigger terms that developers would naturally use. Its main weaknesses are moderate specificity in the concrete actions performed and some potential overlap with other code quality or refactoring skills. Adding more specific actions and distinguishing characteristics would strengthen it further.
Suggestions
Add more specific concrete actions like 'extract helper functions, inline unnecessary abstractions, remove unused imports and variables, consolidate duplicated logic' to improve specificity.
Differentiate more clearly from general refactoring skills by emphasizing the post-change context, e.g., 'after implementing a feature or fixing a bug' to reduce conflict risk with broader code review skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (refactoring) and some actions (simplification, dead-code removal, build/test verification), but doesn't list multiple concrete specific actions like 'extract methods, inline variables, remove unused imports'. The actions remain somewhat high-level. | 2 / 3 |
Completeness | Clearly answers both 'what' (perform a refactor pass focused on simplicity, verify with build/tests) and 'when' (explicit 'Use when' clause covering refactor/cleanup pass, simplification, dead-code removal, and build/test verification expectations). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'refactor', 'cleanup pass', 'simplification', 'dead-code removal'. These are terms developers naturally use when requesting this kind of work. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies refactoring focused on simplicity with build/test verification, it could overlap with general code review or cleanup skills. The 'after recent changes' qualifier and build/test verification add some distinctiveness, but 'refactor' is a broad term that many skills might match. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, well-structured skill that efficiently communicates a refactoring workflow. Its main weakness is the lack of concrete, actionable examples—specific before/after code patterns or commands would make it significantly more useful. The workflow also lacks an explicit feedback loop for handling test failures after refactoring.
Suggestions
Add 1-2 concrete before/after code examples showing specific refactoring patterns (e.g., dead code removal, logic straightening) to improve actionability.
Add an explicit feedback loop: 'If tests fail after refactoring, revert the last change, isolate the issue, and retry with a smaller refactor step.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. Every line serves a purpose, no unnecessary explanations of what refactoring is or why it matters. Assumes Claude's competence. | 3 / 3 |
Actionability | Provides a clear checklist of what to do but lacks concrete examples—no specific code patterns showing before/after refactors, no specific commands for running builds/tests, and no guidance on how to identify dead code or straighten logic flows. | 2 / 3 |
Workflow Clarity | Steps are clearly sequenced and include a build/test verification step, but there's no explicit feedback loop for what to do if tests fail after refactoring, and no validation checkpoint between individual refactor steps to catch regressions early. | 2 / 3 |
Progressive Disclosure | For a simple, short skill under 50 lines with a single-purpose task, the content is well-organized with a clear workflow section. No external references are needed given the scope. | 3 / 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
- pgplex/pgconsole
- Commit
cb70fa0
- 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.