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…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository29 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- seo-ops-agenticSkill
- seo-ops-analyzeSkill
- seo-ops-auditSkill
- seo-ops-backlinksSkill
- seo-ops-clusterSkill
- seo-ops-competitor-pagesSkill
- seo-ops-content-briefSkill
- seo-ops-contentSkill
- seo-ops-dataforseoSkill
- seo-ops-driftSkill
- seo-ops-ecommerceSkill
- seo-ops-flowSkill
- seo-ops-geoSkill
- seo-ops-googleSkill
- seo-ops-hreflangSkill
- seo-ops-image-genSkill
- seo-ops-imagesSkill
- seo-ops-localSkill
- seo-ops-mapsSkill
- seo-ops-pageSkill
- seo-ops-planSkill
- seo-ops-programmaticSkill
- seo-ops-schemaSkill
- seo-ops-setupSkill
- seo-ops-sitemapSkill
- seo-opsSkill
- seo-ops-sxoSkill
- seo-ops-technicalSkill
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
- Very specific: line 12
Every skill in skills/*/SKILL.md is authored to a portable subset of the Claude Code skill spec.
- Very specific: line 127
Run bundled tools through seo-ops-studio.
- Very specific: line 133
Place the repo in ~/.gemini/antigravity/plugins/seo-ops-studio/ or install via:
- Very specific: line 177
Progressive Disclosure: Read SKILL.md for routing, load references on demand
- Very specific: line 179
Security: All scripts call validate_url() for SSRF protection
≈ “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.
Files
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.mdinstead.
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.pyThe 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
| Harness | How to load seo-ops-studio |
| Cursor | Symlink 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 Agents | Push the repo; Cloud Agents read AGENTS.md automatically at session start. |
| Google Antigravity | Point the workspace at this repo root; Antigravity reads AGENTS.md first, falls back to skills/. |
| Gemini CLI | gemini init in this repo loads AGENTS.md. Skills are activated via activate_skill <name> in conversation. |
| Grok Build | Open 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 CLI | Reads AGENTS.md from project root. Bash tools work as documented; some Claude-specific tool names (Read/Write/Edit) are aliased to Codex equivalents transparently. |
| Cline | Loads AGENTS.md from project root. Skills appear as system messages; subagent delegation falls back to in-context expansion. |
| Aider | Reads 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 Code | Codex | Cline | Aider | Cursor / Antigravity |
| Read | read_file | read_file | (inline) | read |
| Write | write_file | write_file | /add then edit | write |
| Edit | apply_diff | replace_in_file | /edit | edit |
| Bash | bash | execute_command | /run | shell |
| Glob | glob | search_files | (inline) | find |
| Grep | grep | search_files | /grep | grep |
| WebFetch | fetch / 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
| Command | What 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 setup | Setup 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.shArchitecture
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, UnlighthouseKey Principles
- Progressive Disclosure: Read SKILL.md for routing, load references on demand
- Industry Detection: Auto-detect SaaS, e-commerce, local, publisher, agency
- Security: All scripts call
validate_url()for SSRF protection - 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.
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.

