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 S3YED/appie-kit --skill seo-keyword-strategiegit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/seo-keyword-strategie)<a href="https://agentmods.dev/skills/s3yed/appie-kit/seo-keyword-strategie"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/seo-keyword-strategie/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/s3yed/appie-kit/seo-keyword-strategie"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/seo-keyword-strategie.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 | $0.00029 | $0.00978 |
| Opus 5 | $0.00015 | $0.00489 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
seo-keyword-strategie 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Keyword Strategie Skill
Purpose
Select, validate, and place the right keywords for any Weblyfe site or blog post. Use this before writing any content, when auditing an existing page that is not ranking, or when planning a new site's content architecture. Codifies the long-tail focus and keyword placement rules from Seyed's course.
Source
"Scoren op zoekwoorden" PDF from Seyed's Weblyfe University SEO course (downloaded from Drive 2026-05-03).
Quick reference
| Task | Action |
|---|---|
| Find keyword ideas | Ubersuggest (ubersuggest.com) - primary tool named in PDF |
| Monitor current rankings | Google Search Console > Performance > Queries |
| Track competitor keywords | SEMrush |
| Find long-tail suggestions | Google's "Zoekopdrachten gerelateerd aan..." at bottom of SERP |
| Place keyword in content | H1, first paragraph, H2/H3, URL, title tag, meta description, alt tags |
Core principles
- "Hoe verder naar voren een woord staat, hoe meer waarde het van Google krijgt." - keyword position in a sentence matters.
- Long-tail keywords (specific phrases) make up 70% of all searches. Short head terms make up only 30% and carry far more competition.
- Avoid keyword stuffing. The example in the PDF ("SEO blog SEO tips SEO trucs SEO...") is explicitly mocked as spam that Google penalises.
- One primary keyword per page. Supporting keywords can appear but one term should dominate each URL.
- Moving from position 2 to 1 = +28.4% CTR gain. Every position matters; target the top 5.
- Monsterartikelen (monster articles) are the highest-value content format: long, with images, video, outgoing links, interactie, backlinks, and internal links combined.
- Use tools to validate search volume before writing. Intuition alone is not enough.
- "Lekker specifiek" - the more specific the query, the less competition and the higher the buyer intent.
How to apply (for any new Weblyfe site)
- Open Ubersuggest, enter the main topic of the page/site, collect 10-20 candidate keywords.
- Filter for long-tail variants (3+ words). Favour specificity over volume.
- Check Google's "gerelateerde zoekopdrachten" at the bottom of the SERP to find buyer-intent variants.
- Assign one primary keyword per page/post. Map keywords to URLs in a spreadsheet before writing.
- Place the primary keyword: title tag, H1, first 100 words of body, at least one H2 or H3, URL slug, meta description, featured image filename and alt tag.
- Validate with Google Search Console after 4-8 weeks: check impressions and average position for the target query.
- Use SEMrush to identify which keywords competitors rank for that you do not yet cover.
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.
- 9d ago First seen · 70 lines · 29 tokens per session scan A 2216abf6aba3
seo-keyword-strategie is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 17d ago), licensed MIT. It adds 29 tokens to every session and 978 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
content-distribution
Content distribution as a discipline. Owned channels (newsletter, blog, social), earned channels (PR, syndication, mentions), paid channels (boosted posts, syndication networks), and the channel-fit decisions that distinguish strategic distribution from spam-everywhere. Audience-channel matching, content-channel…
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
agents-md-protocol
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.
python-memory-safe-scripts
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU…