Writing & Content Quality Suite
Four adversarial quality gates for anyone who writes with AI. Strip the machine-generated tells, fix unclear or off-tone messages before you send, audit articles for on-page SEO before you publish, and stress-test research for unsupported claims and weak sources. Judge-only, read-only, and model-agnostic — works with any SKILL.md-compatible agent.
Works with every agent that reads SKILL.md — Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, and more.
One payment, lifetime access. 4 skills unlock instantly in your library.
30-day refund guarantee
Instant unlock in your library
Free updates from the creator
What's included
4 skills
An adversarial gate that audits a research brief or AI-generated answer for unsupported claims, weak or outdated sources, missing citations, and one-sided framing — returning a structured TRUST/VERIFY/REJECT verdict with the exact passage quoted and what to verify for each.
An adversarial editing gate that scans any AI-assisted draft and flags the exact tells that make it sound machine-written — filler phrases, formulaic structure, robotic cadence, punctuation tics — returning a structured PASS/REVISE/FAIL verdict with specific fixes.
An adversarial pre-send gate that reviews any email or chat message and returns a structured SEND/REVISE/HOLD verdict — flagging unclear asks, unintended tone, buried action items, and missing context, with the exact text quoted and a fix for each.
An adversarial pre-publish gate that audits any article or web page draft for on-page SEO — title and meta, heading structure, keyword use without stuffing, internal links, readability, and search intent — returning a structured PASS/REVISE/FAIL verdict with a fix for each issue.
See it in action
You say
Audit this research before I rely on it:
"Our analysis shows the global widget market will reach exactly 4.7 billion dollars by 2027, growing at 23 percent annually. Studies confirm widgets are the fastest-growing sector. Everyone agrees this is the best time to invest."
Your agent does
VERDICT: REJECT CONFIDENCE: 12 LOAD-BEARING CLAIMS:
- "market will reach exactly 4.7 billion dollars by 2027" -> unsupported -> find the named report, date, and methodology behind this figure
- "fastest-growing sector" -> unsupported -> identify which study, its scope, and its comparison set WEAKNESSES:
- [claim-support] "growing at 23 percent annually" -> precise figure with no cited source -> trace to a primary market report or remove
- [fabrication-risk] "Studies confirm" -> vague appeal to unnamed studies -> name the specific studies or treat as unverified
- [bias-and-completeness] "Everyone agrees this is the best time to invest" -> one-sided framing with no counterview or risk -> add downside scenarios and conflicts of interest MUST-VERIFY BEFORE ACTING:
- The source and methodology for the 4.7 billion figure and 23 percent growth rate
- Whether any independent source supports the "fastest-growing" claim ONE-LINE SUMMARY: Do not use: the key figures are unsourced and the framing is one-sided.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.