rmslop

Remove AI code slop

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/rmslop/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized for a simple single-task skill, but it lacks executable commands and a verification step for what is a destructive editing operation, capping actionability and workflow clarity at the mid-level.

Suggestions

Add an executable command for the first step, e.g. `git diff main...HEAD` (or a merge-base equivalent), so Claude knows exactly how to obtain the diff.

Insert a verification checkpoint before reporting, such as "Run the test suite / type-check and confirm it still passes before summarizing," to cover the destructive nature of removing code.

Optionally specify how to scope removal (whole branch vs. per-file) and how to preserve intent, making the actionable guidance more concrete.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no padding or explanation of concepts Claude already knows; the overview, bullet list, and report instruction all earn their place.	3 / 3
Actionability	It gives a concrete first step ("Check the diff against main") and specific slop categories to target, but offers no executable commands (e.g. a git diff invocation) and stays descriptive for the bulk of the guidance.	2 / 3
Workflow Clarity	A check-diff → remove → report sequence is implied, but because the operation is destructive (deleting code) there is no validation or verification checkpoint (e.g. re-run tests/build), which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The skill is well under 50 lines with no need for external references, and content is cleanly organized into an overview, a bulleted criteria list, and a reporting instruction, satisfying the simple-skill guidance for a full score.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 distinctive domain, but it names only one action and omits any explicit "when to use it" trigger guidance, leaving both completeness and trigger coverage at the mid-level.

Suggestions

Add a concrete "Use when..." clause, e.g. "Use when reviewing an AI-authored branch before merge to strip unnecessary AI slop from the diff."

Expand the action list slightly to name multiple concrete actions (e.g. "Remove stray comments, defensive guards, and any-casts introduced by AI tooling").

Include common trigger variations a user would naturally say ("clean up AI code", "de-slop the diff") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The phrase "Remove AI code slop" names a clear domain and one concrete action verb, but it lists only a single action rather than multiple specific concrete actions, so it does not reach score 3.	2 / 3
Completeness	It states what the skill does ("Remove AI code slop") but provides no "Use when..." clause or equivalent explicit trigger for when to use it, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	"AI code slop" is a relevant keyword a user might say, but it lacks common natural variations (e.g. "clean up AI code", "remove AI comments", "refactor AI-generated code"), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	"Remove AI code slop" carves a recognizable niche unlikely to overlap with unrelated skills, but it is brief enough that it could still be confused with general cleanup/refactoring skills, so it is not a clear score 3.	2 / 3
	Total	8 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (19 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: revokslab/ShipFree
Path: .cursor/skills/rmslop/SKILL.md
Commit: 67b7e3a

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

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.