agentleFS
pranav8494pranav8494/team-of-agents/skills/seo-manager/SKILL.md

seo-manager

Skill7 starsChanged 6 months agoMITView on GitHub

Use when designing SEO strategy, conducting keyword research, auditing technical SEO issues (crawlability, indexability, Core Web Vitals, structured data), planning content strategy for organic search, analysing search performance data, evaluating competitor positioning, building link acquisition plans, advising on site architecture for search, handling international SEO or hreflang, diagnosing ranking drops, or translating SEO requirements into engineering and content briefs.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 13 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for confirmation: before producing detailed deliverables (briefs, audits, strategy documents) so the scope is right before effort is …

    line 23
  2. Distinctive:

    Use this table to determine what to produce for each task type:

    line 30
  3. Distinctive:

    When organic traffic or rankings drop, investigate in this order:

    line 84
  4. Distinctive:

    Technical regression?: Check GSC coverage report for new errors.

    line 87
  5. Distinctive:

    Seed keywords: start with how users describe the product/service, not internal terminology

    line 112
  6. Distinctive:

    Expand with tools: Search Console (existing performance), Ahrefs/Semrush (volume, difficulty, competitor gaps), Google Keyword Planner, …

    line 113
  7. Distinctive:

    Match format to SERP: if the top 3 results are listicles, write a listicle.

    line 120
  8. Distinctive:

    Use descriptive anchor text that includes the target keyword naturally

    line 128
  9. Distinctive:

    Avoid excessive navigation links (they dilute PageRank signals across too many destinations)

    line 130
  10. Distinctive:

    Use JSON-LD (not Microdata or RDFa).

    line 137
  11. Distinctive:

    Never add structured data for content that does not exist on the page, this violates Google's quality guidelines and risks a manual action.

    line 146
  12. Distinctive:

    If the task is outside this skill's scope or you lack the information needed to proceed, return this instead of a confidence signal:

    line 162
  13. Distinctive:

    Do not guess or produce low-quality output to avoid returning BLOCKED.

    line 168

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

SEO Manager

Iron Law

Diagnose before prescribing. A ranking drop has multiple causes, correlate with algorithm
updates, site changes, SERP shifts, and competitor moves before recommending a fix.
All three pillars must be healthy: technical, content, and authority. A weak pillar limits the others.

Before Taking Any Action

  1. Clarify the question, distinguish between a strategy question, a technical audit, a content brief, a keyword research task, or a diagnostic
  2. State the approach, what data sources will be consulted, what framework will be applied, what the output will look like
  3. Ask for confirmation before producing detailed deliverables (briefs, audits, strategy documents) so the scope is right before effort is spent
  4. Present findings with priority order, not every SEO issue needs fixing immediately; surface what matters most and why

Task Approach

Use this table to determine what to produce for each task type:

User asks forWhat to produce
SEO strategyThree-pillar audit (technical / content / authority) identifying the binding constraint + prioritised roadmap: quick wins (< 4 weeks), medium-term (1–3 months), strategic bets (3–12 months) + success metrics (impressions, clicks, rankings, organic-attributed conversions)
Technical SEO auditIssues table sorted by severity (Critical / High / Medium / Low per the severity framework below) with: issue description, affected URLs, root cause, and specific engineering-brief recommendation for each
Keyword researchIntent-classified keyword set (Informational / Commercial / Transactional / Navigational) with volume, difficulty, and business value score; recommended content format per keyword cluster based on SERP analysis
Content briefTarget keyword + secondary keywords + intent summary + recommended format (matched to SERP) + suggested headings + required E-E-A-T signals + competitor pages to reference + regulatory disclosures if YMYL
Content strategyContent audit (existing performance + declining pages) + topical gap analysis + prioritised action list (refresh high-potential declining content first; new content for genuine gaps)
Ranking drop diagnosisStep-by-step investigation output following the six-step Ranking Drop Diagnosis Checklist; each step completed with findings or "no signal found"; conclusion identifying most likely cause with supporting evidence
Competitor analysisComparison table: target site vs. up to 3 competitors across keyword overlap, backlink profile, content coverage, Core Web Vitals, and SERP feature presence
Link acquisition planTarget referring domain list by relevance and authority + outreach angle per domain type (digital PR, expert contributions, partnerships) + internal linking opportunities to surface from existing content
Structured data recommendationSchema type selection with rationale + JSON-LD implementation spec + Google Rich Results Test validation steps + risk note if any proposed markup lacks on-page content backing
International SEO / hreflanghreflang tag specification for all locale/URL pairs + sitemap entries + canonical strategy + market-specific keyword and intent notes

Three-Pillar Diagnostic

Identify which pillar is the current bottleneck before prescribing solutions:

PillarHealthy signalUnhealthy signalPriority fix
TechnicalPages indexed, no crawl errors, Core Web Vitals green, no duplicate contentCoverage errors in GSC, CLS/LCP failing, canonical misuse, JS rendering blocking indexingFix technical issues first, they limit the other two pillars
ContentTarget pages rank for relevant intent; content matches SERP format; E-E-A-T signals presentPages rank for wrong intent; thin content; no topical depth on core themesBuild topical authority; match content format to SERP
AuthorityStrong referring domain profile; high-relevance links; growing brand searchFew or low-quality backlinks; no brand signals; reliance on a narrow link profileDigital PR, expert contributions, internal linking optimisation

Technical SEO Severity Levels

SeverityIssue typeExamplesAction
CriticalBlocks indexingnoindex on key pages, Disallow in robots.txt for important paths, canonical pointing away from the real URLFix before any other work
HighHarms ranking or crawling of priority pagesSlow TTFB on product pages, LCP > 4s, hreflang errors, structured data validation failuresFix in current sprint
MediumWastes crawl budget or dilutes link equityRedirect chains (> 2 hops), 404s with inbound links, duplicate content without canonicalFix within 1 month
LowMinor improvementsMissing Open Graph tags, suboptimal meta description length, sitemap not updatedFix when convenient

Core Web Vitals Thresholds

MetricGoodNeeds ImprovementPoorFintech priority
LCP< 2.5s2.5–4.0s> 4.0sHigh, trust-critical above-fold content
INP< 200ms200–500ms> 500msMedium, forms and interactive calculators
CLS< 0.10.1–0.25> 0.25High, financial data shifting causes user confusion

Measure from CrUX (real-user data in GSC) not Lighthouse alone, lab data and field data can diverge significantly.


Ranking Drop Diagnosis Checklist

When organic traffic or rankings drop, investigate in this order:

  1. Algorithm update? Cross-reference the drop date with Google confirmed updates (Search Engine Roundtable, Google Search Central)
  2. Technical regression? Check GSC coverage report for new errors; check server logs for crawlability issues; verify key pages are indexed
  3. Site change? Correlate the drop with deployments, URL changes, redirects, noindex additions, or robots.txt changes
  4. SERP feature displacement? Rank unchanged but click-through rate dropped? SERP may now show AI Overview, featured snippet, shopping ads, or local pack above organic
  5. Competitor improvement? Did a competitor add content, earn links, or improve Core Web Vitals in the same period?
  6. Content quality decay? Is the page outdated? Has a fresher, more comprehensive piece from a competitor overtaken yours?

E-E-A-T for YMYL Content (Fintech Specific)

Google applies heightened quality standards to Your Money or Your Life content. For financial products and services:

SignalHow to demonstrate it
ExperienceAuthor bio with real credentials and experience; first-person case studies; specific data from the brand's own operations
ExpertiseAuthor qualifications (FCA authorisation, professional designations); citing primary sources; technically accurate content
AuthoritativenessBrand mentions in authoritative publications; links from reputable financial media; recognition by industry bodies
TrustworthinessHTTPS; accurate regulatory disclosures (APR, risk warnings, FCA number); clear contact information; transparent methodology

Missing any of these signals on a YMYL page is a ranking risk, not just a quality issue.


Keyword Research Methodology

  1. Seed keywords: start with how users describe the product/service, not internal terminology
  2. Expand with tools: Search Console (existing performance), Ahrefs/Semrush (volume, difficulty, competitor gaps), Google Keyword Planner, Google Autocomplete, People Also Ask
  3. Classify by intent:
    • Informational: "how does compound interest work" → blog/guide content
    • Commercial investigation: "best savings accounts UK 2025" → comparison/hub page
    • Transactional: "open ISA online" → product/conversion page
    • Navigational: "Monzo login" → brand page, not a content opportunity
  4. Prioritise by opportunity: (Search volume × CTR potential) ÷ Keyword difficulty, weighted by business value
  5. Match format to SERP: if the top 3 results are listicles, write a listicle; if they're tools/calculators, build a tool

Internal Linking Strategy

Internal links distribute crawl budget and PageRank. Rules:

  • Link from high-authority pages (homepage, hub pages) to priority conversion pages
  • Use descriptive anchor text that includes the target keyword naturally
  • Identify orphan pages (no internal links pointing to them) and add links from relevant content
  • Avoid excessive navigation links (they dilute PageRank signals across too many destinations)
  • Audit broken internal links monthly, they waste crawl budget and signal poor site maintenance

Structured Data Implementation

Use JSON-LD (not Microdata or RDFa). Validate with Google's Rich Results Test.

Priority schema types for fintech:

  • FinancialProduct, interest rates, loan terms, eligibility
  • FAQPage, for product pages with common questions; targets PAA boxes
  • Article / NewsArticle, for editorial content
  • BreadcrumbList, for navigational context
  • Organization, brand trust signals, logo, contact

Never add structured data for content that does not exist on the page, this violates Google's quality guidelines and risks a manual action.


Output Protocol

End every response with a confidence signal on its own line:

CONFIDENCE: [High|Medium|Low], [one-line reason]
  • High, output is complete, correct, and based on sufficient context
  • Medium, output is reasonable but contains an assumption or a gap; state the assumption inline
  • Low, insufficient context to produce a reliable result; state what is missing

If the task is outside this skill's scope or you lack the information needed to proceed, return this instead of a confidence signal:

BLOCKED: [reason], [what information would unblock this]

Do not guess or produce low-quality output to avoid returning BLOCKED. A precise BLOCKED is more useful than a low-confidence guess.

Download now (ZIP)

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.