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 Search-Foundry/sf-ai-skills --skill sf-google-quality-contentgit clone --depth 1 https://github.com/Search-Foundry/sf-ai-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/search-foundry/sf-ai-skills/sf-google-quality-content)<a href="https://agentmods.dev/skills/search-foundry/sf-ai-skills/sf-google-quality-content"><img src="https://agentmods.dev/badge/skills/search-foundry/sf-ai-skills/sf-google-quality-content/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/search-foundry/sf-ai-skills/sf-google-quality-content"><img src="https://agentmods.dev/badge/skills/search-foundry/sf-ai-skills/sf-google-quality-content.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 | $0.00113 | $0.01666 |
| Opus 5 | $0.00056 | $0.00833 |
| Sonnet 5 | $0.00023 | $0.00333 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
sf-google-quality-content 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 12d 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.
SF Google Quality Content
Use this skill to produce or audit SEO/editorial content that is genuinely helpful, trustworthy, and aligned with Google QRG.
Language mode
- Default to Italian if the user writes in Italian.
- Default to English if the user writes in English.
- If the target market is specified, adapt language, examples, and terminology to that market.
- Preserve the same quality controls in both languages.
Workflow (EN)
1) Frame the task before writing
- Define audience, locale, funnel stage, and business goal.
- Define the query intent cluster: informational, transactional, navigational, local, mixed.
- State the page purpose in one sentence.
- Classify YMYL risk (
none,moderate,high) and required trust threshold.
2) Build the evidence base
- Collect source facts, first-hand signals, and brand-owned proof points.
- Mark each key claim with a source type: first-party data, expert statement, primary source, secondary source.
- If claims are sensitive (health, finance, legal, civic), require high-confidence sourcing and clear attribution.
3) Define E-E-A-T strategy (explicitly)
- Experience: add direct use, lived context, tests, real cases, or operational details.
- Expertise: show qualified knowledge level needed for topic risk.
- Authoritativeness: connect to recognized entities, references, or track record.
- Trust: prioritize accuracy, transparency, edit quality, and absence of deception.
- For YMYL content, trust and correctness are mandatory gates, not optional enhancements.
4) Produce the content
- Write for the dominant intent first; cover secondary intents only if they help users.
- Use clear information hierarchy: answer first, then depth, then supporting detail.
- Prefer concrete examples, comparisons, and practical steps over generic prose.
- Separate facts, interpretation, and opinion.
- Declare uncertainties and limits when present.
5) Run the quality gate (required)
- Reject content if it appears mass-produced, derivative, or with little added value.
- Reject content with sensational, misleading, or manipulative framing.
- Reject content missing who-is-responsible signals when needed (author/site accountability).
- Reject YMYL content with mild inaccuracies or weak trust signals.
- Check ads/monetization and UX do not obstruct main content comprehension.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 139 lines · 113 tokens per session scan A 1225117e304f
sf-google-quality-content is a skill published in the GitHub repository Search-Foundry/sf-ai-skills (5 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 1,666 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…