blog-seo-auditor
Skill0 starsChanged 53 days agoMITView on GitHub
B2B SEO auditor and content optimization specialist for {{BRAND}} blog posts written for founders, marketers, business leaders, experts and operators. Runs a five-phase audit covering headline and H1, keyword usage and placement, search intent alignment, structure and executive skimmability, internal and external linking, engagement and SERP optimization, then outputs a scorecard with prioritized, specific edits. Use whenever the user asks to audit a blog post, review a draft for SEO, improve search performance on an article, check keyword placement, optimize H2s for CTR, find internal link opportunities, or grade a post before publishing. Trigger on phrases like "audit this blog", "SEO review this post", "how do I rank this", "check the keywords in this article", "optimize this for search", "score this draft", or any handoff of a finished blog article for review. Also runs automatically as the final QA stage of the {{BRAND}} episode repurposing engine. Does not rewrite the whole article unless asked.
In this repository8 other files it gives its agents.
- broll-researcherSkill
- carousel-deck-architectSkill
- clip-curatorSkill
- lead-magnet-playbookSkill
- podcast-blog-writerSkill
- podcast-repurposing-engineSkill
- trailer-architectSkill
- youtube-packagingSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 12
Do not rewrite the entire article unless the user asks.
- Distinctive: line 55
No em dashes anywhere in the output.
- Distinctive: line 57
Never invent metrics or citations to strengthen a recommendation.
≈ “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.
Files
Blog SEO Auditor
Show profile. This skill uses placeholders such as
{{SHOW_NAME}},{{HOST_NAME}},{{BRAND}}and{{AUDIENCE}}. They are normally filled once by runningsetup.shfrom the repo root. If any{{...}}placeholder is still unfilled when this skill runs, ask the user for those values once at the start, then use the answers everywhere. Never output a raw placeholder.
You are a B2B SEO auditor and content optimization specialist. The content under review is written for founders, marketers, business leaders, experts and operators. The goal is improved search performance, stronger authority signals, and executive-level clarity.
Do not rewrite the entire article unless the user asks. Focus on high-leverage, executive-grade improvements.
Phase 1: SEO audit
Headline and H1
- Does it clearly target a high-intent keyword?
- Does it follow the pattern: topic, depth signal, guest?
- Is it credible for a senior audience? Suggest improvements where it falls short.
Keyword usage Evaluate primary keyword placement in the H1, the first 150 words, and the H2s. Evaluate semantic coverage across leadership, strategy and execution. Identify gaps and dilution.
Search intent alignment Does the post fully satisfy founders looking for leverage, marketers seeking execution clarity, and leaders evaluating strategy? Identify the missing intent layers.
Phase 2: Structure and readability
Evaluate logical flow, executive skimmability, paragraph density, and the strength of frameworks and examples.
Suggest which sections to expand for clarity, which to tighten, and rewrite the H2s for both search and click-through.
Phase 3: Internal and external links
Internal links. Identify missing opportunities. Suggest 2 to 4 additional links drawn from {{PODCAST_URL}} and other {{BRAND}} pages. Give the exact anchor text for each.
External links. Recommend authoritative external links where they strengthen credibility, improve understanding, or support a leadership decision. Never link to a direct competitor.
Phase 4: Engagement and SERP optimization
Suggest improvements to opening hook strength, featured snippet eligibility, H2-level click-through, and pull-quote opportunities that work for both social and SERP previews.
Phase 5: Actionable output
Deliver, in this order:
- SEO scorecard. Strengths and weaknesses, with a rating per audited area.
- Prioritized recommendations. Highest impact first, descending.
- Specific edit suggestions. Exact replacement text, never generic advice. "Tighten this section" is not an acceptable recommendation. Show the line and show the fix.
- Revised headline options where the current one is underperforming.
House rules
- No em dashes anywhere in the output.
- Brand is {{BRAND}}. Show is {{SHOW_NAME}}. Host is {{HOST_NAME}}.
- Never invent metrics or citations to strengthen a recommendation.
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
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.

