Skip to main content
ClaudeWave
Skill693 repo starsupdated 12d ago

seo-audit

The seo-audit skill performs comprehensive website SEO analysis including keyword research, on-page optimization assessment, content gap identification, technical SEO evaluation, and competitor benchmarking. Use it when evaluating a site's overall search engine health, discovering untapped keyword opportunities that competitors rank for, identifying technical issues affecting crawlability or performance, or generating a prioritized action plan distinguishing quick wins from long-term strategic improvements.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/openyak/openyak /tmp/seo-audit && cp -r /tmp/seo-audit/backend/app/data/plugins/marketing/skills/seo-audit ~/.claude/skills/seo-audit
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# /seo-audit

> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).

Audit a website's SEO health, research keyword opportunities, identify content gaps, and benchmark against competitors. Produces a prioritized action plan a marketer can execute immediately.

## Trigger

User runs `/seo-audit` or asks for an SEO audit, keyword research, content gap analysis, technical SEO check, or competitor SEO comparison.

## Inputs

Gather the following from the user. If not provided, ask before proceeding:

1. **URL or domain** — the site to audit, or a topic/keyword if running in keyword research mode

2. **Audit type** — one of:
   - **Full site audit** — end-to-end SEO review covering all sections below
   - **Keyword research** — identify keyword opportunities for a topic or domain
   - **Content gap analysis** — find topics competitors rank for that you don't
   - **Technical SEO check** — crawlability, speed, structured data, and infrastructure issues
   - **Competitor SEO comparison** — head-to-head SEO benchmarking against specific competitors

   If not specified, default to **full site audit**.

3. **Target keywords or topics** (optional) — specific keywords the user is already targeting or wants to rank for

4. **Competitors** (optional) — domains or companies to compare against. If not provided and the audit type requires competitor data, use web search to identify 2-3 likely competitors based on the user's domain and keyword space.

## Process

### 1. Keyword Research

Research keywords related to the user's domain, topic, or target keywords.

**If ~~SEO tools are connected:**
- Pull keyword data, search volume, keyword difficulty scores, and ranking positions automatically
- Identify keywords the site currently ranks for and where it's gaining or losing ground

**If ~~product analytics are connected:**
- Cross-reference keyword targets with actual organic traffic data to validate which keywords are driving visits and conversions

**If tools are not connected:**
- Use web search to research the keyword landscape
- Note: "For more precise volume and difficulty data, connect an SEO tool like Ahrefs or Semrush via MCP. The audit will auto-populate with ranking data."

For each keyword opportunity, assess:
- **Primary keywords** — high-intent terms directly tied to the user's product or service
- **Secondary keywords** — supporting terms and variations
- **Search volume signals** — relative demand (high, medium, low) based on available data
- **Keyword difficulty** — how competitive the term is (easy, moderate, hard)
- **Long-tail opportunities** — specific, lower-competition phrases with clear intent
- **Question-based keywords** — "how to", "what is", "why does" queries that mirror People Also Ask results
- **Intent classification** — informational, navigational, commercial, or transactional

### 2. On-Page SEO Audit

For each key page (homepage, top landing pages, recent blog posts), evaluate:

- **Title tags** — present, unique, within 50-60 characters, includes target keyword
- **Meta descriptions** — present, compelling, within 150-160 characters, includes a call to action
- **H1 tags** — exactly one per page, includes primary keyword
- **H2/H3 structure** — logical hierarchy, uses secondary keywords where natural
- **Keyword usage** — primary keyword appears in the first 100 words, used naturally throughout, not over-stuffed
- **Internal linking** — pages link to related content, orphan pages identified, anchor text is descriptive
- **Image alt text** — all images have descriptive alt attributes, keywords included where relevant
- **URL structure** — clean, readable, includes keywords, no excessive parameters or depth

### 3. Content Gap Analysis

Identify what's missing from the user's content strategy:

- **Competitor topic coverage** — topics and keywords competitors rank for that the user's site does not cover
- **Content freshness** — pages that haven't been updated in 12+ months and may be losing rankings
- **Thin content** — pages with insufficient depth to rank (under 300 words for informational queries, lacking substance)
- **Missing content types** — formats competitors use that the user doesn't (guides, comparison pages, glossaries, tools, templates)
- **Funnel gaps** — missing content at specific buyer journey stages (awareness, consideration, decision)
- **Topic clusters** — opportunities to build pillar pages with supporting content

### 4. Technical SEO Checklist

Evaluate technical foundations that affect crawlability and rankings:

- **Page speed** — identify slow-loading pages and likely causes (large images, render-blocking scripts, excessive redirects)
- **Mobile-friendliness** — responsive design, tap targets, font sizes, viewport configuration
- **Structured data** — opportunities for schema markup (FAQ, HowTo, Product, Article, Organization, Breadcrumb)
- **Crawlability** — robots.txt configuration, XML sitemap presence and accuracy, canonical tags, noindex/nofollow usage
- **Broken links** — internal and external 404s, redirect chains
- **HTTPS** — secure connection, mixed content issues
- **Core Web Vitals signals** — LCP, FID/INP, CLS indicators based on observable page behavior
- **Indexation** — pages that should be indexed but may not be, duplicate content risks

### 5. Competitor SEO Comparison

For each competitor, compare:

- **Keyword overlap** — keywords both sites rank for, and where each site ranks higher
- **Keyword gaps** — terms the competitor ranks for that the user does not
- **Domain authority signals** — relative site strength based on backlink profiles, referring domains, and content depth
- **Content depth** — average content length, topic coverage breadth, publishing frequency
- **Backlink profile observations** — types of sites linking to competitors, link-worthy content they've produced
- **SERP feature ownership** — which competitor appears in featured snippets, Peo
instrument-data-to-allotropeSkill

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full ASM JSON, flattened CSV for easy import, and exportable Python code for data engineers. Common triggers include converting instrument files, standardizing lab data, preparing data for upload to LIMS/ELN systems, or generating parser code for production pipelines.

nextflow-developmentSkill

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.

scientific-problem-selectionSkill

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".

scvi-toolsSkill

Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics deconvolution with DestVI, (6) label transfer and reference mapping with scANVI/scArches, (7) RNA velocity with veloVI, or (8) any deep learning-based single-cell method. Triggers include mentions of scVI, scANVI, totalVI, PeakVI, MultiVI, DestVI, veloVI, sysVI, scArches, variational autoencoder, VAE, batch correction, data integration, multi-modal, CITE-seq, multiome, reference mapping, latent space.

single-cell-rna-qcSkill

Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or following scverse/scanpy best practices for single-cell analysis.

startSkill

Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

cowork-plugin-customizerSkill

>

create-cowork-pluginSkill

>