FLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow applies stage prompts to a user-supplied URL or topic, which requires the agent to fetch arbitrary web pages (and SERP/backlink data) that outsiders can publish to but cannot force into the workflow, so this is low; the bundled prompt files and the sync from the FLOW repo are first-party or maintainer-authored and not outsider free text.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The `/seo flow sync` path runs `sync_flow.py` to pull prompt files from github.com/AgriciDaniel/flow at HEAD, and the agent then applies those prompts as instructions, so it is an operational inbound dependency; the publisher is an individual author's repository, which is unofficial, with no warning signs establishing it as weak, so the tier is medium.
AgriciDaniel/claude-seo
468ed5b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.