Skip to content
SkillModel-led418 tokens in use

seo-profound

Read Profound citation rates for your brand across ChatGPT, Perplexity and other LLMs, with top prompts, competitors and spike or drop alerts.

31,134 stars on the repository MIT LicenseAgriciDaniel/claude-seo · extensions/profound/skills/seo-profound
/plugin marketplace add AgriciDaniel/claude-seo /plugin install claude-seo@agricidaniel-claude-seo
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing seo-profound costs

46tokens idle
418tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure9/25
  • Examples0/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community72
  • Maturity32
  • Momentum40

seo-profound is the Profound extension of Claude SEO. Profound polls AI models continuously and publishes time series, so week-over-week and month-over-month changes in brand citation rate are available directly.

The skill routes four commands to Profound and labels each metric with its source and a confidence value. It defers Gemini, AI Overviews and AI Mode coverage to the seo-seranking skill.

What You Get

  • Current citation rate per LLM with a 30-day trend
  • The top prompts that surface or miss the brand
  • Brands cited alongside yours for the same prompts
  • Spike and drop alerts against a seven-day baseline
  • A source and confidence label on each metric

Common Use Cases

  • Track whether ChatGPT and Perplexity cite your brand more over time
  • Find prompts where competitors appear and you do not
  • Watch for sudden drops after a site change
  • Triangulate AI visibility with SE Ranking data

What Makes It Unique

It focuses on trends: Profound publishes polled time series, so the skill reports week-over-week deltas and alerts for every metric. It also sends related work to neighbours: seo-seranking for other platforms, seo-geo for end-to-end audits and seo-content for prompt design.

Under The Hood

The skill is one instruction file with no scripts. Before any call it checks that the settings file holds the Profound API key, which the extension install script writes. It then queries the Profound service with that key. Fetched data is treated as untrusted data and never as instructions.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers