Skills Explorer Add Skills

seo-profound

An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: analysis, multi-agent, seo, tracking, trend-analysis.

What it does

Profound LLM citation tracker (extension). Time-series brand citation rates across ChatGPT, Perplexity, and other LLMs. Pairs with seo-seranking for triangulated AI visibility coverage.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add AgriciDaniel/claude-seo --skill seo-profound

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/AgriciDaniel/claude-seo
cp -r claude-seo/extensions/profound/skills/seo-profound ~/.claude/skills/seo-profound

Safety box score

Grade B, low risk: 25 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a documentation-only wrapper around Profound’s LLM citation tracking features, but it depends on an API key and tells the agent to read the user’s Claude settings file. The main risks are external network requests to Profound/LLM services and exposure of credentials or account configuration via `PROFOUND_API_KEY` and `~/.claude/settings.json`.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)No shell commands, scripts, or code execution are present in `SKILL.md`; it only describes commands and outputs.
Network access2 (moderate)The skill is inherently an online API client: it says Profound is a "citation tracker" and requires a "Profound API key," so using it will send prompts/brand data to external services.
Filesystem reach2 (moderate)It explicitly instructs the agent to check the home dotfile `~/.claude/settings.json`, which reaches outside the project workspace into the user's home directory.
Secrets & credentials2 (moderate)It depends on a secret-like credential, `PROFOUND_API_KEY`, and tells the agent to verify it in `~/.claude/settings.json`, which can expose account configuration.
Privilege & persistence0 (none)No sudo, service registration, global installs, or OS/shell settings changes are described in the reviewed file.
Instruction hijack surface0 (none)No instructions to ignore safeguards, hide actions, or follow remote instructions appear in the reviewed file.
Irreversible actions0 (none)The skill describes reporting and cross-skill delegation only; it does not send messages, deploy, pay, book, or otherwise act on its own.
Transparency0 (none)The reviewed file is plain markdown only; there are no binaries, generated blobs, or unreadable assets in the provided inventory.

Before installing

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository
AgriciDaniel/claude-seo (all skills from this repository)
Path
extensions/profound/skills/seo-profound/SKILL.md
Branch
main
Collection
claude-seo
Updated
2026-09-21