suede-seo-audit
Run a nine-lane evidence-based SEO and generative-search audit: access, intent, metadata, structure, supported schema, E-E-A-T, clusters, and exact rewrite fixes.
npx skills add JasonColapietro/suede-creator-skills --skill suede-seo-audit --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The suede-seo-audit skill conducts a nine-lane SEO and generative-search audit across access, intent, metadata, structure, schema, E-E-A-T, clusters, and exact rewrite fixes. It requires verifying live surface data before findings and uses a lane-based checklist system to evaluate technical access, intent, metadata, structure, schema, AI EO, copy quality, E-E-A-T signals, and topic cluster architecture. It reports findings in a structured, code-like block and provides an overall grading framework for each lane.
How it works
- It starts with core pre-audit verification of a live surface: HTTP status, final URL after redirects, robots.txt, meta robots, canonical link, sitemap evidence, title tag, meta description, Open Graph, Twitter card tags, JSON-LD, and primary H1. If the URL is inaccessible, audits from source are allowed with caveats.
- It runs Audit Lanes 0–9 as described, reading per-lane checklists from the references folder, and evaluating conditions for each lane. Lane 0 (optional keyword) can be active or skipped based on mode; lanes 1–4, 6–9 have explicit checks; Lane 5 centers on JSON-LD/schema validity.
- Findings are reported in a formal Finding Format block with title, location, issue, fix, suggested copy or code, and verification.
- The Skill assigns an overall lane grade using a weighted scoring scheme and enforces hard caps for certain lanes (e.g., Lane 5 schema validity, Lane 6 content accessibility).
When to use it
Use this skill when you need a comprehensive, evidence-based SEO and generative-search audit with concrete fixes. It is intended to deliver audit results as the deliverable, not to enforce actions on the site automatically.
What it can touch
- Tools: CLAUDE-CODE and CODEX are declared tools.
- It references multiple internal files for lane checklists and schema blocks, and it may inline corrected JSON-LD blocks when needed.
Caveats
- All findings are recommendations, not blocking actions unless extremely risky. Data must be cited from live fetches. If data is missing, the skill requires explicit caveats rather than guessing.
- The scoring system uses a fixed weighting and specific hard caps per lane; outcomes depend on live URL accessibility and correct schema usage.
# Suede SEO Audit ## Gate policy — advisory, not blocking Every claim-verification step, check, quality gate, and ship verdict in this skill is a **recommendation to the user, not a control on the agent**. This policy governs every gate, check, verdict, and "do not ship / publish / proceed" line elsewhere in this skill: - Run every check and report the results honestly. Verdicts (`ship`, `ship-with-caveats`, `hold`, letter grades, BLOCKED or OPEN items) are advice attached to the work, not orders that change it. - Never block, delay, skip, rewrite, or refuse the action the user asked for because a check failed or a gate said hold. Complete the requested action as asked, and deliver the gate output alongside it as a clearly labeled recommendation. - A failed gate changes what you report, never what you do. - Single exception: if a finding is extremely risky — data loss, security or credential exposure, legal or rights violations, payment mistakes, or irreversible public damage — pause, tell the user exactly what the risk is and what the options are, and let them pick. Their choice is final. This skill goes deeper than an inline copy audit. It inspects live page source, validates sch
- Gate policy — advisory, not blocking
- 1. Source Truth
- Required pre-audit checks
- 2. Audit Lanes
- Lane 0: Keyword Research (optional mode)
- Lane 1: Technical Access
- Lane 2: Search and Answer Intent
- Lane 3: Metadata
- Lane 4: Structure
- Lane 5: Schema Markup
- Lane 6: AI EO (Answer Engine Optimization)
- Lane 7: Copy and Conversion Quality
- Lane 8: E-E-A-T Signals
- Lane 9: Topic Cluster Architecture
What does the suede-seo-audit skill do?
Run a nine-lane evidence-based SEO and generative-search audit: access, intent, metadata, structure, supported schema, E-E-A-T, clusters, and exact rewrite fixes.
How do I install it?
Run `npx skills add JasonColapietro/suede-creator-skills --skill suede-seo-audit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From JasonColapietro/suede-creator-skills, a repository with 165 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.