agentleFS
juanpulagjuanpulag/seo-ops-studio/AGENTS.md

seo-ops-studio

AGENTS.md0 starsChanged 6 days agoMITView on GitHub

For Cursor, Cursor Cloud Agents, Google Antigravity, Gemini CLI, Grok Build, OpenAI Codex CLI, Cline, Aider, and any other agent harness that reads project-root agent instructions. Claude Code users: see CLAUDE.md instead. Every skill in skills/*/SKILL.md is authored to a portable subset of the Claude Code skill spec. Validate compatibility with your harness via: The check confirms each SKILL.md has the minimum frontmatter every harness expects (name, description, optional model, optional tools) and warns on Claude-Code-specific features (maxTurns, multi-line tool…

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every skill in skills/*/SKILL.md is authored to a portable subset of the Claude Code skill spec.

    line 12
  2. Very specific:

    Run bundled tools through seo-ops-studio.

    line 127
  3. Very specific:

    Place the repo in ~/.gemini/antigravity/plugins/seo-ops-studio/ or install via:

    line 133
  4. Very specific:

    Progressive Disclosure: Read SKILL.md for routing, load references on demand

    line 177
  5. Very specific:

    Security: All scripts call validate_url() for SSRF protection

    line 179

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.md 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

SEO Ops Studio: Multi-Platform Agent Instructions

For Cursor, Cursor Cloud Agents, Google Antigravity, Gemini CLI, Grok Build, OpenAI Codex CLI, Cline, Aider, and any other agent harness that reads project-root agent instructions.

Claude Code users: see CLAUDE.md instead.

Cross-platform portability (v2.0.0)

Every skill in skills/*/SKILL.md is authored to a portable subset of the Claude Code skill spec. Validate compatibility with your harness via:

./scripts/seo-ops run portability_check.py

The check confirms each SKILL.md has the minimum frontmatter every harness expects (name, description, optional model, optional tools) and warns on Claude-Code-specific features (maxTurns, multi-line tool list with descriptive comments) that other harnesses may ignore but do not reject.

Per-harness notes

HarnessHow to load seo-ops-studio
CursorSymlink or copy skills/ and agents/ into .cursor/rules/. Commands are invoked as text prompts; the harness reads SKILL.md body as system context.
Cursor Cloud AgentsPush the repo; Cloud Agents read AGENTS.md automatically at session start.
Google AntigravityPoint the workspace at this repo root; Antigravity reads AGENTS.md first, falls back to skills/.
Gemini CLIgemini init in this repo loads AGENTS.md. Skills are activated via activate_skill <name> in conversation.
Grok BuildOpen this repository in Grok Build. It reads AGENTS.md and Claude Code compatible plugins and skills without a separate layout. Use grok inspect to verify discovery. See the official compatibility guide.
OpenAI Codex CLIReads AGENTS.md from project root. Bash tools work as documented; some Claude-specific tool names (Read/Write/Edit) are aliased to Codex equivalents transparently.
ClineLoads AGENTS.md from project root. Skills appear as system messages; subagent delegation falls back to in-context expansion.
AiderReads AGENTS.md if present; otherwise falls back to README. Aider does not support sub-agent dispatch; the seo-* skills run inline.

Tool-name compatibility

Where seo-ops-studio skills mention Claude Code tools (Read, Write, Edit, Bash, Glob, Grep, WebFetch), each harness typically has an equivalent:

Claude CodeCodexClineAiderCursor / Antigravity
Readread_fileread_file(inline)read
Writewrite_filewrite_file/add then editwrite
Editapply_diffreplace_in_file/editedit
Bashbashexecute_command/runshell
Globglobsearch_files(inline)find
Grepgrepsearch_files/grepgrep
WebFetchfetch / browse(browser tool)(n/a)fetch

These mappings are automatic in most harnesses; we list them for transparency in case a recipe needs a specific call.

Overview

SEO Ops Studio is a Tier 4 SEO analysis skill with 28 sub-skills (2 SEO Ops skills + 22 core + 1 orchestrator + 1 framework integration + 2 extension mirrors), 19 sub-agents (16 core + 1 framework integration + 2 extension mirrors), and 62 Python execution scripts.

Quick Reference

CommandWhat it does
/seo-ops-analyze audit <url>Full website audit with parallel subagent delegation
/seo-ops-analyze page <url>Deep single-page analysis
/seo-ops-analyze technical <url>Technical SEO audit (9 categories)
/seo-ops-analyze content <url>E-E-A-T and content quality analysis
/seo-ops-analyze content-brief <topic>Generate a content brief for a topic
/seo-ops-analyze schema <url>Schema.org detection, validation, generation
/seo-ops-analyze sitemap <url>XML sitemap analysis or generation
/seo-ops-analyze images <url>Image SEO: on-page audit, SERP analysis, file optimization
/seo-ops-analyze geo <url>AI Overviews / Generative Engine Optimization
/seo-ops-analyze plan <type>Strategic SEO planning
/seo-ops-analyze cluster <keyword>SERP-based semantic clustering and content architecture
/seo-ops-analyze sxo <url>Search Experience Optimization: page-type analysis, personas
/seo-ops-analyze drift baseline <url>Capture SEO baseline for change monitoring
/seo-ops-analyze drift compare <url>Compare current state to stored baseline
/seo-ops-analyze drift history <url>Show drift history over time
/seo-ops-analyze ecommerce <url>E-commerce SEO: product schema, marketplace intelligence
/seo-ops-analyze programmatic [url]Programmatic SEO at scale
/seo-ops-analyze competitor-pages [url]Competitor comparison pages
/seo-ops-analyze flow [stage]FLOW framework prompts (Find, Leverage, Optimize, Win, Local; prompts/sync utilities.)
/seo-ops-analyze local <url>Local SEO analysis (GBP, citations, reviews)
/seo-ops-analyze maps [cmd] [args]Maps intelligence (geo-grid, GBP audit, competitors)
/seo-ops-analyze hreflang <url>Hreflang/i18n SEO audit, cultural profiles, content parity
/seo-ops-analyze google [cmd] [url]Google SEO APIs (GSC, PageSpeed, CrUX, Indexing, GA4)
/seo-ops-analyze backlinks <url>Backlink profile analysis
/seo-ops-analyze backlinks setupSetup free backlink APIs
/seo-ops-analyze backlinks verify <url>Verify known backlinks still exist
/seo-ops-analyze dataforseo [cmd]Live SEO data via DataForSEO (extension)
/seo-ops-analyze image-gen [use-case]AI image generation for SEO assets (extension)
/seo-ops-analyze firecrawl [cmd] <url>Full-site crawling and site mapping (extension)
/seo-ops-analyze ahrefs [cmd] <target>Ahrefs backlink and keyword data (extension)
/seo-ops-analyze bing [cmd] <url>Bing Webmaster data and IndexNow (extension)
/seo-ops-analyze profound [cmd]LLM brand-citation tracking (extension)
/seo-ops-analyze seranking [cmd]AI share-of-voice tracking (extension)
/seo-ops-analyze matomo [cmd] [args]Matomo Reporting API: GA4 alternative or supplement (extension)
/seo-ops-analyze unlighthouse <url>Multi-page Lighthouse audits (extension)

Using with Cursor / Cursor Cloud

Cursor reads this file automatically. All SKILL.md files contain the full analysis logic as natural language instructions. Python scripts in scripts/ provide execution capabilities.

Running scripts directly (Cursor doesn't have MCP):

# Page fetching with SSRF protection
./scripts/seo-ops run fetch_page.py https://example.com

# HTML parsing for SEO elements
./scripts/seo-ops run parse_html.py https://example.com

# PageSpeed Insights
./scripts/seo-ops run pagespeed_check.py https://example.com --json

# Drift baseline
./scripts/seo-ops run drift_baseline.py https://example.com

# DataForSEO (requires credentials)
DATAFORSEO_USERNAME=user DATAFORSEO_PASSWORD=pass ./scripts/seo-ops run dataforseo_merchant.py search "keyword"

Cursor Cloud gotchas:

  • SSL certificates may not resolve for some domains. Investigate the certificate issue rather than disabling verification.
  • Run bundled tools through seo-ops-studio; never call the venv interpreter directly.
  • Screenshots save to /tmp/ not CWD. Check absolute paths.

Using with Google Antigravity

Antigravity discovers this project via .claude-plugin/plugin.json. Place the repo in ~/.gemini/antigravity/plugins/seo-ops-studio/ or install via:

bash install.sh

Architecture

skills/                    # 28 sub-skills (auto-discovered; includes the 2 SEO Ops skills)
  seo/SKILL.md            # Main orchestrator + routing
  seo-ops-cluster/            # Semantic clustering (v1.9.0)
  seo-ops-sxo/                # Search Experience Optimization (v1.9.0)
  seo-ops-drift/              # SEO drift monitoring (v1.9.0)
  seo-ops-ecommerce/          # E-commerce SEO (v1.9.0)
  seo-ops-audit/              # Full site audit
  seo-ops-page/               # Single-page analysis
  seo-ops-technical/          # Technical SEO
  seo-ops-content/            # E-E-A-T quality
  seo-ops-content-brief/      # Content brief generation
  seo-ops-schema/             # Schema.org markup
  seo-ops-sitemap/            # XML sitemaps
  seo-ops-images/             # Image optimization
  seo-ops-geo/                # AI search / GEO
  seo-ops-agentic/            # Agent readiness (Lighthouse Agentic Browsing, WebMCP)
  seo-ops-local/              # Local SEO
  seo-ops-maps/               # Maps intelligence
  seo-ops-plan/               # Strategic planning
  seo-ops-hreflang/           # International SEO
  seo-ops-google/             # Google APIs
  seo-ops-backlinks/          # Backlink analysis
  seo-ops-programmatic/       # Programmatic SEO
  seo-ops-competitor-pages/   # Competitor pages
  seo-ops-flow/               # FLOW framework integration
  seo-ops-dataforseo/         # DataForSEO (extension)
  seo-ops-image-gen/          # AI images (extension)
agents/                    # 19 subagents
scripts/                   # 62 Python scripts, including the managed runtime
schema/                    # JSON-LD templates
extensions/                # 9 MCP extensions: DataForSEO, Firecrawl, Banana, Ahrefs, SE Ranking, Profound, Bing Webmaster, Matomo, Unlighthouse

Key Principles

  1. Progressive Disclosure: Read SKILL.md for routing, load references on demand
  2. Industry Detection: Auto-detect SaaS, e-commerce, local, publisher, agency
  3. Security: All scripts call validate_url() for SSRF protection
  4. Config location: ~/.config/seo-ops-studio/ for API credentials

Credits

Created by @AgriciDaniel. v1.9.0 community contributions by Lutfiya Miller, Chris Muller, Florian Schmitz, Dan Colta, and Matej Marjanovic. See CONTRIBUTORS.md.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.