agentleFS
jwuthri-cloudjwuthri-cloud/Tracely-ai/.claude/skills/seo-audit/SKILL.md

seo-audit

Skill1.2k starsChanged 21 days agoMITView on GitHub

Audit a website and deliver a one-page, plain-language SEO report anyone can act on, centered on a single do-this-week action.

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 165 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this when asked for an SEO audit or review of a domain, especially when the output is a shareable report for a non-expert.

    line 12
  2. Distinctive:

    Keep total spend modest: one audit, one backlinks overview, at most one domain overview, and at most one keyword-research call.

    line 28
  3. Very specific:

    When the crawl finishes, read get_audit_issues (and get_domain_overview if the site is alive).

    line 34
  4. Distinctive:

    Verify every finding you plan to report against the live page HTML by fetching pages yourself.

    line 36
  5. Very specific:

    Write the report using template.html in this skill directory (see Output format).

    line 43
  6. Very specific:

    Use template.html next to this file.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 165 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

OpenSEO SEO Audit

Goal

Audit a domain and produce a one-page HTML report that anyone, including a complete SEO beginner, can read once and act on. The whole report exists to support ONE action the owner can take this week; everything else is supporting detail.

Use this when asked for an SEO audit or review of a domain, especially when the output is a shareable report for a non-expert. For expert-facing analysis of a competitor or market, use competitor-analysis or competitive-landscape instead.

Required inputs

  • Domain to audit
  • projectId (use list_projects; if no project matches the domain, create one with create_project)

OpenSEO MCP tools

  • whoami: confirm connection and remaining credits before spending anything. If OpenSEO is not connected, stop and ask the user to connect it.
  • list_projects / create_project: resolve the projectId.
  • run_site_audit: start the crawl (default page budget), then poll get_audit_status and read get_audit_issues. Use get_audit_pages when per-page evidence helps.
  • get_backlinks_overview: backlink and referring-domain picture; usually the deciding data for the "one thing".
  • get_domain_overview: estimated organic traffic and organic keyword count. Skip when the site is clearly dead.
  • research_keywords: keyword ideas with volume and difficulty, used to propose a starting focus area. One call with 1-3 seeds taken from what the site is actually about. Skip when the site is down.

Keep total spend modest: one audit, one backlinks overview, at most one domain overview, and at most one keyword-research call. Only the overview and keyword lookups spend credits.

Workflow

  1. whoami, then resolve the projectId.
  2. run_site_audit for the domain. While it crawls, fetch get_backlinks_overview.
  3. When the crawl finishes, read get_audit_issues (and get_domain_overview if the site is alive).
  4. If the audit comes back broken or nearly empty (certificate errors, 5xx, one page crawled): investigate before writing. Check the certificate and redirect variants yourself, and search the web for the business. A dead domain often has a live successor site, which flips the whole recommendation to "redirect the old domain".
  5. Verify every finding you plan to report against the live page HTML by fetching pages yourself. Report nothing you have not seen evidence for.
  6. Decide the one thing. Derive it from the data, never from generic advice. Common patterns:
    • Clean site, no backlinks: outreach to guests, partners, or directories, with a ready-to-send message.
    • Dead domain, live successor site: permanent redirect via hosting support, with the exact sentence to send them.
    • Blocked or noindexed pages: remove the block. It must be doable this week by a non-technical person, with copy-paste-ready mechanics included.
  7. When the site is healthy, propose a starting focus area: run one research_keywords call seeded from the site's actual topic, then pick one theme and 3 to 5 specific, low-difficulty keywords the site can realistically rank for, each with the page or post to make. This is a starting direction, not a keyword strategy; point the user at the keyword-research skill for the full workflow. Skip this step entirely when the site is down — the one thing is all that matters there.
  8. Write the report using template.html in this skill directory (see Output format).
  9. Review before delivering: run an adversarial pass with a second agent or model if your environment has one, otherwise do a fresh self-review. Give the reviewer the verified facts and have it attack four things: claims beyond the facts, unglossed jargon, anything overwhelming for a beginner, and dramatic language. The reviewer may also flag true facts it was not given; check those against your evidence instead of "fixing" them.
  10. Deliver the report: if your environment can publish or preview HTML (for example as an artifact), do that; otherwise save the HTML file and tell the user to open it in their browser.

Output format

Use template.html next to this file. Fill in content; keep the CSS and structure as they are (light palette only, no dark mode).

  • Header: domain as the title, the review date on its own line under it, then a 2-3 sentence summary of the whole report (overall state; the main gap and the one thing; what the report covers).
  • Section order: verdict, the one thing, small fixes (5 to 10 max, ordered by impact), where to focus first (healthy sites only), already working, method footer.
  • Each fix row shows the exact evidence (a quoted tag or number) and concrete steps a non-technical person can follow.
  • "Where to focus first" names one topic area and 3 to 5 keywords, each with its search volume in plain words and the page or post to make. Omit the section when the site is down.

Guardrails

  • Tone: calm and plain. No exclamation points, no drama words, no em dashes, no "Not X. Y." contrasts, no filler. Severity words only where literally true (a down site is critical; a long title is not).
  • Gloss every term of art in plain English on first use: canonical, meta description, alt text, crawler, 301, structured data.
  • Skip nitpicks that do not matter for the specific site. A beginner report with twenty findings has failed.
  • Missing backlink or ranking data means "no recorded data", not a penalty; say so rather than dramatizing it.
  • Favor keywords the site can win now: specific intent, low difficulty. Do not list head terms a new site cannot rank for yet.
  • Separate what the tools reported from what you verified yourself, and note both in the method footer.

Download now (ZIP)

Trending

More talk lately.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 1 mentionNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the jwuthri-cloud/Tracely-ai repository that our weekly crawl found: only 1 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Who's talking about jwuthri-cloud/Tracely-ai

The biggest 1 of 1 mention linking to the repository that our crawl found. Each line is their own headline.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.