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.
npx skills add nataliacorrea03/claude-code-skills --skill ai-writing-qagit clone --depth 1 https://github.com/nataliacorrea03/claude-code-skillsWrote 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.
[](https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/ai-writing-qa)<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/ai-writing-qa"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/ai-writing-qa/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.
<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/ai-writing-qa"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/ai-writing-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00178 | $0.02204 |
| Opus 5 | $0.00089 | $0.01102 |
| Sonnet 5 | $0.00036 | $0.00441 |
| Haiku 4.5 | $0.00018 | $0.00220 |
Grade A, and why
ai-writing-qa 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 11d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Writing QA
Purpose
Catch AI giveaways in scripts and copy before they ship, so nothing you put out reads like a bot wrote it. Paste anything. This scans it against a fixed catalog of tells, rewrites every line that trips one, and hands back a clean version in your voice. Output is a draft. It never sends and never saves.
Execution logic
Step 1 - Detect the register. Read the copy and decide which voice applies:
- Client-facing (email or anything a customer reads): strict. Gratitude first, one clear call to action, no slang, no abbreviations, no em dashes, warm but contained. Hyperlink with anchor text, never raw URLs.
- Internal (teammates, DMs, notes): casual and fast. Abbreviations fine, bullet points fine. Still no em dashes, still no slop.
- Creative (scripts, captions, social, marketing): hook fast, spoken and human, take a position. Still no em dashes, still no slop.
If register is ambiguous, default to creative. If it looks like a client email, say so before rewriting.
Step 2 - Scan every line against all six buckets below plus the two fast tests.
Step 3 - Rewrite each tripped line. Swap blacklisted words for a concrete noun or active verb. Kill the structural tells. Apply the register's voice. Run the pub test and the first-10% test on the result.
Step 4 - Output the clean version only. Lead with one line: the tell count (e.g. 9 tells caught). Then the full rewritten copy. No per-line breakdown unless asked. If nothing trips, say so and return the text unchanged. Never send. Never save.
Bucket 1 - Core rules (non-negotiable)
- No em dashes. Ever. Single biggest Claude/ChatGPT tell. Use periods, commas, or rewrite.
- No AI slop: filler, buzzwords, hollow sentences that sound professional but say nothing.
- No LinkedIn-energy prose: inspirational throat-clearing, fake profundity, "thought leader" voice.
- No warmup: "great question," restating the prompt, "let's dive in," "in this video we'll explore."
- No hedging / disclaimers: "it's worth noting," "it's important to consider," "that said," watered-down both-sides takes.
- Client comms only: no slang, no abbreviations, no em dashes, gratitude first, single call to action.
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.
- 11d ago First seen · 139 lines · 178 tokens per session scan A 7fdbd5dcfe05
ai-writing-qa is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 178 tokens to every session and 2,204 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.