synthesis-content-quality

synthesis-content-quality is a skill for Claude Code, Codex from synthesisengineering/synthesis-skills. It costs 139 tokens per session (8,832 once invoked), scanned A, original, Apache-2.0.

A method for finding poor writing, including empty or shallow content and patterns often produced by AI language models. It evaluates the writing itself rather than assuming who or what created it.

In plain words
What is it for?
Use it to review articles and other content for substance, depth, misleading confidence, model-related patterns, and recurring quality problems.
Why use it?
It helps distinguish useful, substantive writing from text that sounds polished but says little or relies on recognizable generated-writing patterns.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the synthesis-skills plugin — 63 skills, 4 hooks shipped together

Good fit Use it to review articles and other content for substance, depth, misleading confidence, model-related patterns, and recurring quality problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthesisengineering/synthesis-skills/synthesis-content-quality
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add synthesisengineering/synthesis-skills --skill synthesis-content-quality
Clone the repo
git clone --depth 1 https://github.com/synthesisengineering/synthesis-skills

Made for: Claude Code, Codex.

Or install synthesis-skills, the plugin that ships this one along with the rest of its 63 skills, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for synthesis-content-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-content-quality/github.svg)](https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-content-quality)
Your own site
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-content-quality"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-content-quality/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for synthesis-content-quality

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-content-quality"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-content-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00139 $0.08832
Opus 5 $0.00069 $0.04416
Sonnet 5 $0.00028 $0.01766
Haiku 4.5 $0.00014 $0.00883

Measured 10d ago against content hash 6c0b9a898972, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

synthesis-content-quality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/corpus_repetition.py, tests/generate_no_removals_baseline.py, tests/test_additive_upgrade_contract.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/synthesis-content-quality/SKILL.md · 444 lines

How it starts

The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

When to Use This Skill

  • Reviewing AI-assisted drafts before publication.
  • Editing content that may contain unrevised AI output.
  • Building or calibrating AI content detection tools.
  • Training writers or editors on content quality standards.
  • Performing editorial review of submitted content.
  • Forensic analysis of older published content for AI authorship signals (use Historical and Deprecated era patterns).

Read the full file on GitHub · 444 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 444 lines · 139 tokens per session scan A 6c0b9a898972

Subscribe to this mod's changes

synthesis-content-quality is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 139 tokens to every session and 8,832 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens