CtrlK
BlogDocsLog inGet started
Tessl Logo

deslop

Remove AI-generated code slop and clean up code style

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cursor-team-kit/skills/deslop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 concise and well-structured with concrete, actionable pattern guidance, but its workflow lacks an explicit verification step for ensuring behavior is unchanged across batch edits. Adding a validation checkpoint would raise workflow clarity past its current cap.

Suggestions

Add an explicit validation step in the Guardrails or a short 'Verify' section, e.g. run the test suite or confirm the diff still passes type-checking before summarizing.

Specify how to obtain the diff against main (e.g. `git diff main...HEAD`) so the first action is copy-paste executable.

Optionally add a one-line example of an acceptable vs. removed edit to make the actionability fully concrete.

DimensionReasoningScore

Conciseness

The body is a lean bullet list of patterns and guardrails with no padding and no explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Concrete guidance is given via specific patterns to remove ('defensive checks', 'casts to any', 'deeply nested code') plus a concrete starting action ('Check the diff against main'); it falls just short of fully copy-paste executable instruction, matching the 'mostly executable; minor gaps' anchor.

4 / 5

Workflow Clarity

A rough sequence exists (check diff, remove slop, respect guardrails) but there is no explicit validation checkpoint confirming behavior is unchanged, so workflow clarity is capped at 3 for a batch/destructive operation without validation.

3 / 5

Progressive Disclosure

This is a simple under-50-line skill with no need for external references and well-organized sections (Focus Areas, Guardrails), so progressive disclosure scores 5 per the simple-skill scoring note.

5 / 5

Total

17

/

20

Passed

Description

53%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 concise and names a clear niche, but it omits any explicit 'Use when' trigger guidance, which both caps completeness and weakens trigger discoverability. Adding a usage trigger would lift the two weakest dimensions.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when reviewing a branch for AI-generated code slop or cleaning up code style introduced by an AI assistant.'

Add natural synonym keywords users say in practice ('refactor', 'clean up the code', 'review my diff') to broaden trigger coverage.

Consider listing one or two more concrete actions (e.g. 'remove redundant comments and casts to any') to raise specificity from a domain-plus-two to comprehensive.

DimensionReasoningScore

Specificity

Names the domain ('AI-generated code slop') and two concrete actions ('Remove' and 'clean up code style'), matching the anchor that names a domain plus 1-2 actions without comprehensive coverage.

3 / 5

Completeness

The description states clearly what the skill does but lacks any 'Use when...' or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Phrases like 'AI-generated code slop' and 'code style' are natural terms users would say, but common synonyms such as 'refactor', 'clean up', or 'review my code' are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The 'AI slop removal' niche is mostly distinct from general code-review or refactor skills with only minor overlap risk, fitting the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

13

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cursor/plugins
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.