synthesis-content-quality
Content Quality
A systematic methodology for evaluating writing quality and identifying slop, with or without AI involvement. The framework targets bad content, not provenance. Ethically authored AI-collaborated content can be excellent; styled empty human content is slop. This skill detects slop.
The methodology is durable. The catalog refreshes as model behavior shifts and as new patterns emerge in production output. v4.0 adds model-family fingerprinting across eight families, a substance and depth section grounded in the Frankfurt-Pennycook-Hicks-Humphries-Slater framework, a cross-cutting causal-and-calibration layer, and zone-conditional detection. The compounding-archive principle means patterns are never deleted: when newer model versions train a pattern out, the catalog tags it Historical and retains it for forensic analysis of older published content.
Where this skill fits in the writing-quality family
This skill catches AI-generation patterns and substance failures specifically. Three sibling skills handle adjacent concerns:
synthesis-content-quality(this skill, v4.0): AI/LLM-generation patterns, substance and depth, calibration. Refreshes with new model releases.synthesis-writing-pitfalls: Universal human-source bad-writing patterns (cringe, throat-clearing, caveat overload, cliché reliance). Stable across decades.synthesis-writing-craft: Positive principles from the writing-craft tradition.
Use all three together for a comprehensive quality pass. Use this one alone when the focus is specifically slop in AI-collaborated or AI-generated content.