simplify
Simplify and refine recently modified code for clarity and consistency. Use after writing code to improve readability without changing functionality.
62
43%
Does it follow best practices?
Impact
91%
1.68xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/simplify/SKILL.mdQuality
Discovery
67%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 has a clear structure with both a 'what' and 'when' clause, which is good for completeness. However, it lacks specific concrete actions (what kinds of simplifications?) and misses common trigger terms users would naturally use like 'refactor', 'clean up code', or 'code review'. The scope is somewhat generic and could overlap with other code-quality-related skills.
Suggestions
Add specific concrete actions like 'remove redundant logic, simplify conditionals, improve variable naming, reduce nesting depth' to increase specificity.
Include natural trigger terms users would say, such as 'refactor', 'clean up', 'code cleanup', 'make code cleaner', 'DRY up code', or 'code review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (code) and some actions ('simplify', 'refine', 'improve readability'), but these are fairly general and don't list multiple concrete specific actions like 'remove dead code, rename variables, extract functions, simplify conditionals'. | 2 / 3 |
Completeness | Clearly answers both 'what' (simplify and refine recently modified code for clarity and consistency) and 'when' (use after writing code to improve readability without changing functionality), with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code', 'clarity', 'readability', 'consistency', but misses common natural trigger terms users would say such as 'refactor', 'clean up', 'simplify code', 'code review', 'make code cleaner', or 'DRY'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is somewhat specific to post-writing code cleanup, but 'simplify and refine code' could overlap with general code review skills, linting skills, or refactoring skills. The 'recently modified code' qualifier helps but the scope is still broad. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a persona description or system prompt than an actionable skill document. It is verbose, explains concepts Claude already knows, and provides no concrete examples, code snippets, or specific patterns to follow. The guidance is almost entirely abstract ('enhance clarity', 'reduce complexity') without demonstrating what good simplification looks like in practice.
Suggestions
Add concrete before/after code examples showing specific simplification patterns (e.g., replacing nested ternaries with switch statements, consolidating redundant logic)
Remove explanations of general software engineering principles Claude already knows (e.g., what readability means, why maintainability matters) and focus only on project-specific standards and non-obvious patterns
Add a verification step with concrete actions, such as running tests or diffing output to confirm functionality is preserved after refactoring
Fix the 'CLAUDE.md' reference (currently shown as http://CLAUDE.md) and either inline the essential standards or properly link to the project file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and explains concepts Claude already knows well (what code simplification means, what readability is, basic refactoring principles). Phrases like 'This is a balance that you have mastered as a result your years as an expert software engineer' and extensive explanations of obvious principles waste tokens. The 'Maintain Balance' section describes general software engineering wisdom that Claude inherently understands. | 1 / 3 |
Actionability | The skill provides no concrete code examples, no executable commands, no before/after demonstrations, and no specific patterns to apply. It reads as abstract guidance ('Reduce unnecessary complexity', 'Improving readability') rather than actionable instructions. The project standards reference 'CLAUDE.md' via a URL (http://CLAUDE.md) which is likely incorrect and not a real reference. | 1 / 3 |
Workflow Clarity | There is a numbered refinement process (identify, analyze, apply, ensure, verify, document) which provides some sequence, but it lacks concrete validation checkpoints. Steps like 'Verify the refined code is simpler' give no guidance on how to verify, and there's no feedback loop for when refinements inadvertently change behavior. | 2 / 3 |
Progressive Disclosure | The content is a monolithic block with some structure via numbered sections and bold headers, but everything is inline with no references to external files for detailed standards or examples. The reference to 'CLAUDE.md' suggests awareness of external resources but doesn't properly link or organize content across files. | 2 / 3 |
Total | 6 / 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
- brianlovin/claude-config
- Commit
1a9819e
- 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.