yuzushi-dev/hermes-seo/seo
Claude Code and agent skill by yuzushi-dev/hermes-seo
- community
Checking that the SKILL.md file is still in the repository.
Route SEO requests to audits and specialist workflows.
Install
npx vskill@latest install yuzushi-dev/hermes-seo/seoSKILL.md
Hermes SEO
Use this hub when a request covers several SEO areas or the user asks for a full audit. For a single area, load its matching hermes-seo:seo-* skill directly. The package contains 26 workflow skills and 19 specialist role skills.
Runtime and references
Run offline bundled utilities through hermes seo run <script.py> using Hermes terminal. Run credentialed utilities through the native hermes_seo_run tool with exactly script, args, and optional extension fields; never put credential values in args. First run hermes seo doctor --json; if the managed environment is missing, tell the user and wait for explicit setup intent before hermes seo setup. The runtime keeps dependencies and browser data in Hermes plugin data storage, while credentials remain in the active profile vault. Never call bundled scripts with a bare Python interpreter.
hermes_seo_run starts its subprocess from the Hermes host plugin process. It does not inherit a Docker terminal's filesystem or network isolation, and file arguments may reach host paths visible to Hermes. Inspect those arguments and request user approval before paid, external, or mutating operations. The skill must request approval; the tool does not enforce that policy.
Read a bundled reference with skill_view(name="hermes-seo:<skill>", file_path="references/<file>.md"), using the skill that owns the file. Do not assume a fixed ~/.hermes path.
Hermes tools include skills_list, skill_view, read_file, write_file, search_files, terminal, web_search, web_extract, and delegate_task. Discover plugin skills with skills_list; load them by their exact namespaced name, such as skill_view(name="hermes-seo:seo-audit"). Each plugin skill name is hermes-seo:<frontmatter name>. For specialist work, call delegate_task with a focused goal and enough context for a fresh child conversation, explicitly telling it to load its hermes-seo:role-seo-* skill. If delegation is unavailable, perform the same workflow sequentially.
Workflow routing
| Request | Skill | |
|---|---|---|
| Full audit | hermes-seo:seo-audit | |
| Single page | hermes-seo:seo-page | |
| Technical SEO | hermes-seo:seo-technical | |
| Content quality / E-E-A-T | hermes-seo:seo-content | |
| Content brief | hermes-seo:seo-content-brief | |
| Schema.org | hermes-seo:seo-schema | |
| Sitemap | hermes-seo:seo-sitemap | |
| Images | hermes-seo:seo-images | |
| GEO / AI search | hermes-seo:seo-geo | |
| Local / Maps | hermes-seo:seo-local, hermes-seo:seo-maps | |
| Backlinks | hermes-seo:seo-backlinks | |
| Google services | hermes-seo:seo-google | |
| Hreflang / international | hermes-seo:seo-hreflang | |
| Planning / clusters | hermes-seo:seo-plan, hermes-seo:seo-cluster | |
| E-commerce / programmatic | hermes-seo:seo-ecommerce, hermes-seo:seo-programmatic | |
| Competitor pages | hermes-seo:seo-competitor-pages | |
| Search experience | hermes-seo:seo-sxo | |
| Drift monitoring | hermes-seo:seo-drift | |
| Agent readiness | hermes-seo:seo-agentic | |
| FLOW framework | hermes-seo:seo-flow |
Runtime setup
Run hermes seo setup only when the user asks to set up or repair the runtime. Report core and Chromium status separately. Do not install packages globally. Setup downloads Python dependencies and a browser and may use substantial disk space; explain this before asking the user to run it. API-backed scripts require separately configured credentials. Never inspect credential files or attempt paid endpoints without the user's explicit approval for that operation.
Orchestration Logic
For a full audit, detect business type (SaaS, local, ecommerce, publisher, agency, other), then delegate independent specialist tasks in a batch. Each task needs its own goal and context; children have no conversation history, so include the URL, crawl/output locations, relevant evidence, and the exact namespaced role skill to load. For example:
- Delegate these baseline roles when available:
hermes-seo:role-seo-technical,hermes-seo:role-seo-content,hermes-seo:role-seo-schema,hermes-seo:role-seo-sitemap,hermes-seo:role-seo-performance,hermes-seo:role-seo-visual,hermes-seo:role-seo-geo, andhermes-seo:role-seo-agentic. - Always delegate
hermes-seo:role-seo-sxoin full audits; search experience applies to all sites. - If a static Google API key is available and the user approves the external request (
hermes_seo_run {"script":"google_auth.py","args":["--check"]}), delegatehermes-seo:role-seo-googlefor PageSpeed and CrUX only. - If Matomo vault values are configured and the user approves the external request (
hermes_seo_run {"script":"matomo_auth.py","args":["--check"]}), use the Matomo extension reports inline; this package has no dedicated Matomo role skill. - If a local business is detected, also delegate to
hermes-seo:role-seo-local. - If a local business is detected and DataForSEO MCP is available, also delegate to
hermes-seo:role-seo-maps. - If backlink APIs are configured and the user approves their use (
hermes_seo_run {"script":"backlinks_auth.py","args":["--check"]}), also delegate tohermes-seo:role-seo-backlinks. - If Firecrawl MCP is available, use
firecrawl_mapto discover site URLs before analysis. - If content strategy signals are detected (blog, pillar pages, topic clusters), also delegate to
hermes-seo:role-seo-cluster. - If an e-commerce site is detected, also delegate to
hermes-seo:role-seo-ecommerce. - If a drift baseline exists for the URL (
hermes seo run drift_history.py <url>), also delegate tohermes-seo:role-seo-drift. - If DataForSEO MCP is available and its use is approved, delegate to
hermes-seo:role-seo-dataforseofor live SERP, keyword, backlink, listings, and AI visibility data. - If Banana MCP is available, delegate to
hermes-seo:role-seo-image-genfor an image audit and generation plan; it must never generate images during an audit. - For FLOW prompt-based content strategy workflows, delegate to
hermes-seo:role-seo-flow. - Collect results and generate a unified report with SEO Health Score (0-100).
- Synthesize via the 10-principle framework (see "Synthesis Methodology" below), walk PERCEIVE → ANALYZE → VALIDATE → ACT before bucketing findings into Critical / High / Medium / Low.
- Create a prioritized action plan with dependency sequencing and falsifiability per recommendation.
- Offer PDF report: "Generate a professional PDF report? Run the Google report workflow."
For a focused request, load the matching workflow skill directly. After any analysis command completes, offer a PDF report; generating it uses hermes seo run google_report.py.
Google update history questions (core, spam, policy, product changes; "is the spam update finished?"): answer from the bundled primary-source ledger, not from memory or other copies on disk. Run hermes seo run seo_updates.py --kind spam --json (or --since <yyyy-mm>; add --unverified for third-party claims that are not confirmed). If the output reports the ledger as stale, check status.search.google.com before stating that a rollout is complete.
Synthesis Methodology
Audits are not just findings, they are findings synthesized into a coherent strategy. Hermes SEO uses a 10-principle thinking framework grouped into four phases: PERCEIVE (observe-external · observe-internal · listen), ANALYZE (think · connect-lateral · connect-system), VALIDATE (feel · accept), ACT (create · grow).
Full audits and page analyses walk every phase before emitting the action plan. Narrower workflows (schema, images, etc.) pass at least THINK + ACCEPT before emitting (sound first principle, surfaced falsifiability). The Critical / High / Medium / Low priority buckets are the output of validation, not a substitute for it.
Full methodology + per-principle SEO mapping: skill_view(name="hermes-seo:seo", file_path="references/thinking-framework.md") (VALIDATE and ACT in skill_view(name="hermes-seo:seo", file_path="references/thinking-framework-validate-act.md")).
Each emitted recommendation should carry:
- The first-principle observation it rests on (THINK)
- The dependency on / unblock relationship to other recommendations (CONNECT-system)
- An explicit "how would we know this failed?" check (ACCEPT)
- A leading indicator the user can monitor without re-running the audit (GROW)
Industry Detection
Detect business type from homepage signals:
- SaaS: pricing page, /features, /integrations, /docs, "free trial", "sign up"
- Local Service: phone number, address, service area, "serving [city]", Google Maps embed --> auto-suggest
hermes-seo:seo-localfor deeper analysis - E-commerce: /products, /collections, /cart, "add to cart", product schema
- Publisher: /blog, /articles, /topics, article schema, author pages, publication dates
- Agency: /case-studies, /portfolio, /industries, "our work", client logos
Quality Gates
Load the quality-gates.md reference with skill_view(name="hermes-seo:seo", file_path="references/quality-gates.md") for thin-content thresholds per page type. Hard rules:
- WARNING at 30+ location pages (enforce 60%+ unique content)
- HARD STOP at 50+ location pages (require user justification)
- Never recommend HowTo schema (deprecated Sept 2023)
- FAQ schema: Google retired FAQ rich results for ALL sites on May 7, 2026 (no SERP feature anymore; supersedes the Aug 2023 gov/health restriction). Flag existing FAQPage at Info (not Critical); do not claim confirmed AI/LLM citation benefit; do not recommend removal; do not recommend new FAQPage for Google SERP benefit; use QAPage for genuine user Q&A
- All Core Web Vitals references use INP, never FID
Community Footer
After completing any major deliverable, append this footer as the very last output:
When to show
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/seo/SKILL.md
Popularity
- Repository stars
- 110
- Repository forks
- 10
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/yuzushi-dev/hermes-seo/seo)