Writing Standards Knowledge Modules

A writing quality gate that detects and eliminates AI-generated writing patterns. Merges 29 detection patterns from humanizer with 5-dimension scoring from stop-slop. Use this module as the final quality check before publishing any content. See ATTRIBUTION.md for licensing details. Scan the content for AI writing patterns across 6 categories. Each detected pattern is a signal that the text sounds machine-generated. Full pattern catalog with before/after examples: references/banned-patterns.md Rate the content 1-10 on five dimensions. The scoring system measures how human the writing sounds, not whether it's "good" writing in general. Threshold: 35/50 to pass. Any single dimension below 5 = automatic revision, regardless of total score. Full rubric with scoring examples: references/scoring.md These 8 rules from stop-slop are the active editing directives. Apply them when rewriting flagged content:

Decides what to write, when to publish it, and why it matters. This module sits upstream of copywriting and social-content: it produces the plan they execute against. Without a strategy, you produce content that nobody searches for, nobody shares, and nobody remembers. Every piece of content falls into one of two modes. Confusing them is the most common strategy mistake. Captures existing demand. People already have questions; you answer them better than anyone else. Driven by keyword research, not inspirationStructured for SEO: clear headings, answer-first format, internal linksCompounds over time (evergreen traffic curve)Examples: "how to set up CI/CD", "best project management tools 2025", "React vs Vue comparison"Success metric: organic search traffic, ranking position Creates new demand. Nobody was searching for your insight because it didn't exist until you published it. Driven by original thinking: novel data, contrarian takes, proprietary research, lived experienceStructured for engagement: strong hooks, narrative tension, quotable linesSpikes on publish, decays unless redistributedExamples: "We analyzed 10,000 deploys and here's what broke", "Why we stopped doing sprint planning", "The hidden cost of microservices nobody talks about"Success metric: social shares, backlinks, email signups, brand recall New sites: searchable first. You need a baseline of organic traffic before shareable content has distribution. A brilliant essay with zero audience stays invisible. Established sites: shift toward shareable. Once organic traffic covers your base, shareable content builds brand and differentiation. The 60/40 split (searchable/shareable) works for most teams. Adjust based on your distribution channels.

Conversion copywriting for marketing websites. Covers homepage heroes, landing pages, pricing pages, feature pages, comparison pages, and all supporting sections (social proof, FAQ, objection handling, CTAs). Produces draft copy ready for the copy-editing module to review and the writing-quality module to score. Read brand-context.md before writing any copy. Every brand decision depends on it. If no brand context file exists, ask for these before drafting: Without brand context, copy defaults to clear and competent but personality-less. That is not good enough for production. Six principles, ranked by priority. When they conflict, the higher-ranked principle wins.

Creates platform-specific social media content that builds audience, drives traffic, and establishes authority. This module handles the last mile: taking ideas, blog posts, and brand positioning and turning them into posts that work on each platform's algorithm and audience expectations. Allocate content across pillars to avoid becoming a one-note account. The exact percentages depend on your brand and goals, but this distribution works as a starting point: The 5% promotional rule matters. Accounts that promote more than they teach get unfollowed. You earn the right to promote by consistently providing value in the other 95%. When a brand-context.md is provided: Map brand voice rules to social tone (formal brands stay professional; casual brands can use humor and slang)Align pillar topics with the brand's content themesAdjust promotional allocation based on product launch cycles (temporarily bump to 10-15% during launches, then return to 5%) The first line determines whether anyone reads the rest. On most platforms, only the first 1-2 lines are visible before the "see more" fold. Every post needs a hook that earns the click. Creates an information gap the reader needs to close. Formula: "Most [audience] don't know that [surprising fact]..." Examples: "Most marketers don't know that 73% of blog traffic comes from posts older than 6 months.""Most founders don't know that their pricing page is the second-most visited page on their site.""Most engineers don't know that the CI pipeline is their biggest deployment bottleneck." When to use: Data-backed insights, counterintuitive findings, industry statistics. Opens with a specific moment that creates narrative tension.

A structured editing methodology for reviewing and polishing existing marketing copy. Uses the Nine Sweeps framework to systematically improve clarity, persuasion, credibility, and readability in separate focused passes. Each sweep targets one dimension so nothing gets missed and nothing gets over-edited. Read brand-context.md before editing any content. You need to understand the intended voice so you preserve it. Editing that strips brand personality is worse than leaving rough copy alone. Key things to absorb from brand context before you start: Tone and formality — is this brand casual, professional, technical, playful?Approved language — terms the brand uses deliberately, even if they seem unusualBanned language — words or phrases the brand avoids for strategic reasonsAudience — who reads this? What do they already know? What do they care about? If no brand context is available, ask for one. Without it, you risk editing toward generic corporate voice. The core methodology. Each sweep is a single focused pass through the content targeting one specific dimension. Do not combine sweeps. Do not skip sweeps. The order matters: structural issues first, polish last. Focus: Can the reader understand this on first read? What to check: Sentences that require re-reading to parseUnclear pronoun references ("it", "this", "they" without obvious antecedent)Jargon or acronyms used without explanationAmbiguous modifiers (does the adjective apply to the first noun or the second?)Sentences trying to say two things at once Common issues: Stacking multiple clauses in one sentenceUsing "this" to refer to an entire preceding paragraphAssuming the reader shares context they don't haveLeading with qualifications before the main point Process: