deslop
Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Use after completing changes and before committing.
89
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%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 description that clearly communicates a specific purpose (cleaning AI-generated code issues) with explicit timing guidance (after changes, before committing). The main weakness is trigger term coverage - users might describe this need using terms like 'clean up', 'simplify', or 'refactor' that aren't present.
Suggestions
Add common user phrases like 'clean up code', 'simplify', 'remove boilerplate', or 'code cleanup' to improve trigger term coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Remove AI-generated code slop', 'unnecessary comments', and 'over-engineering'. These are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff') and when ('Use after completing changes and before committing') with explicit timing guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code slop', 'comments', 'over-engineering', 'branch diff', and 'committing', but missing common variations users might say like 'clean up code', 'refactor', 'simplify', or 'code review'. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused specifically on cleaning AI-generated code artifacts from git diffs before commits. The combination of 'AI-generated code slop', 'branch diff', and pre-commit timing creates distinct triggers unlikely to conflict with general code review or refactoring skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%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-crafted, concise skill that provides actionable guidance for removing AI code slop. The focus areas are specific and concrete, and the guardrails appropriately constrain behavior. The main weakness is the implicit workflow—adding explicit steps with a verification checkpoint before committing would improve reliability for this potentially destructive operation.
Suggestions
Add explicit numbered workflow steps: 1) Run diff commands, 2) Identify slop patterns, 3) Apply edits, 4) Re-run diff to verify only slop was removed, 5) Summarize
Add a validation checkpoint before output: 'Run tests or type-check to confirm behavior unchanged before summarizing'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No explanations of what slop is or why it's bad—assumes Claude understands. Bullet points are terse and actionable. | 3 / 3 |
Actionability | Provides exact bash commands to run, specific patterns to look for with concrete examples (try/catch blocks, casts to any, _vars), and clear output format. Copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow is implicit (fetch, diff, identify, edit, summarize) but lacks explicit sequencing and validation checkpoints. No feedback loop for verifying changes don't break behavior before committing. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized with clear sections (Trigger, Commands, Focus Areas, Guardrails, Output). No need for external references. | 3 / 3 |
Total | 11 / 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.
- 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.