stop-slop

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Quality

92%

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

Quality

Content

100%

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

An exemplar concise, actionable instruction-only skill: every rule is a concrete instruction, quick checks form a pre-delivery checklist with a scoring rubric and revise threshold, and detailed material is properly offloaded to real reference files.

Dimension	Reasoning	Score
Conciseness	The body is lean, imperative, and assumes Claude's competence; no concepts Claude already knows are explained and nearly every token earns its place.	3 / 3
Actionability	Concrete, executable guidance throughout ('Any adverbs? Kill them', 'Find the actor, make them the subject'); per the code-vs-instruction note, absence of code is not penalized for this actionable instruction-only skill.	3 / 3
Workflow Clarity	A simple single-purpose skill under 50 lines, so the simple-skill allowance applies; the Quick Checks checklist plus a scored rubric with a 'Below 35/50: revise' threshold provide an explicit validate-and-revise feedback loop.	3 / 3
Progressive Disclosure	Well-organized overview with three clearly signaled one-level-deep references (phrases.md, structures.md, examples.md), all of which exist as real bundle files; content is appropriately split.	3 / 3
	Total	12 / 12 Passed

Description

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.

A clear, third-person description that states what the skill does and when to use it with concrete trigger terms. It loses a point only on trigger-term coverage, which could include more colloquial variations users actually say.

Suggestions

Broaden trigger terms to include colloquial phrasings users say, e.g. 'make text less robotic' or 'fix AI-sounding writing'.

Consider naming the deliverable context (e.g. emails, essays, blog posts) so Claude matches it to more specific writing tasks.

Dimension	Reasoning	Score
Specificity	Names the domain ('AI writing patterns from prose') and lists concrete actions ('Remove', 'eliminate predictable AI tells'), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Remove AI writing patterns from prose') and when ('Use when drafting, editing, or reviewing text'), the clearest anchor match.	3 / 3
Trigger Term Quality	Includes natural terms users would say ('drafting, editing, or reviewing text'), but coverage is moderate and omits common variations like 'make this less robotic' or 'fix AI-sounding text'.	2 / 3
Distinctiveness Conflict Risk	The 'AI writing patterns' niche is distinct and unlikely to trigger for unrelated skills; the trigger terms are narrowly scoped.	3 / 3
	Total	11 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: holaboss-ai/holaOS
Path: runtime/harnesses/src/embedded-skills/stop-slop/SKILL.md
Commit: 74c7b6f

Reviewed: 6 days 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.