Borrowing it
Nothing to install: this file belongs to umutxyp/Seo-Promt-Master. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/umutxyp/Seo-Promt-Master/main/.claude/skills/seo-audit/SKILL.mdgit clone --depth 1 https://github.com/umutxyp/Seo-Promt-MasterWrote 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/umutxyp/seo-promt-master/seo-audit)<a href="https://agentmods.dev/skills/umutxyp/seo-promt-master/seo-audit"><img src="https://agentmods.dev/badge/skills/umutxyp/seo-promt-master/seo-audit/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/umutxyp/seo-promt-master/seo-audit"><img src="https://agentmods.dev/badge/skills/umutxyp/seo-promt-master/seo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00108 | $0.01208 |
| Opus 5 | $0.00054 | $0.00604 |
| Sonnet 5 | $0.00022 | $0.00242 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
seo-audit scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
and seen the change — `curl` the route, grep the rendered output, or re-run How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO audit and repair
You are running SEO Prompt Master. Bring every public page of the project in the working directory into compliance with Google's documented guidance, and prove it rather than asserting it.
Before anything else
Read docs/README.md for the map, then keep docs/ open as you work. It is the
only source of truth in this skill. If a claim about how Google behaves is
not in docs/01–docs/17, say "not covered by the knowledge base" instead of
recalling it from memory — the SEO web is full of advice that was true in 2021.
Check verticals/README.md for an overlay matching the project's industry. It
adds emphasis; it never replaces the core audit.
Two ways to learn what is wrong, and you need both
Read the code to know what the project intends. Run the tool to know what the server actually does. They disagree more often than anyone expects, and the gap is where the bugs live.
node tools/seo-audit.mjs --url https://the-site.example --max 40 --md seo-report.md
Zero dependencies, Node 18+. It samples across the sitemap rather than the head
of it, then checks robots.txt against RFC 9309, sitemap limits and lastmod
credibility, host consolidation, per-template soft 404s, canonical
self-reference, hreflang reciprocity across pages (a one-way set is
discarded in full), duplicate titles, streamed-metadata visibility, raw-HTML
content volume, structured-data validity, and image dimensions. It exits 1 if
any P1 is open, so it can gate a deploy.
Point it at a local build (--url http://localhost:3000) when there is no live
site yet.
Three things it deliberately cannot see, which stay your job: whether the
content is any good (docs/14), off-page authority (docs/17), and real
field CWV data, which only CrUX has (docs/05).
The workflow
Follow START.md, which holds the full phase-by-phase instructions:
| Phase | File | Output |
|---|---|---|
| 0 — Bootstrap & detect | prompts/00-bootstrap.md |
Stack report |
| 1 — Discover routes | prompts/01-discover-routes.md |
ROUTES-INVENTORY.md |
| 2 — Audit each page | prompts/02-audit-page.md |
SEO-AUDIT-PROGRESS.md |
| 3 — Prioritise | prompts/03-prioritize-fixes.md |
P1/P2/P3 backlog + baseline score |
| 4 — Fix & verify | prompts/04-apply-and-verify.md |
Fixes, each with evidence |
| 5 — Live signals (optional) | prompts/05-live-signals.md |
Field data, if a live URL exists |
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 · 92 lines · 108 tokens per session scan A 3fd7a1fb57bb
seo-audit is a skill published in the GitHub repository umutxyp/Seo-Promt-Master (547 stars, last pushed 27d ago), licensed MIT. It adds 108 tokens to every session and 1,208 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
skill-push
Create and push reusable skills to SkillNote from Codex when repeated instructions are detected or the user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection, and publishing.
skillnote-doctor
A diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file validity, and installed skill health. Use when your setup seems broken, skills aren't loading, or you want to audit your agent's configuration.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
complete-skill
Rate a SkillNote skill after using it in Codex. Called after applying a skill to record a 1-5 rating and outcome.
mcpmu
Install, set up, and manage MCP servers using the mcpmu CLI. Use when the user wants to install mcpmu, register it as an MCP server, add/remove/list MCP servers, manage namespaces, set tool permissions, manage server-level denied tools, or expose servers via serve mode.