technical-seo
Use when diagnosing crawl/index issues, performance regressions, or structured data gaps.
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install gtmagents/gtm-agents/technical-seo skilz install gtmagents/gtm-agents/technical-seo --agent opencode skilz install gtmagents/gtm-agents/technical-seo --agent codex skilz install gtmagents/gtm-agents/technical-seo --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/gtmagents/gtm-agents cp -r gtm-agents/plugins/seo/skills/technical-seo ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
sql-translation
by MicrockGuide for adding SQL function translations to dbplyr backends. Use when implementing new database-specific R-to-SQL translations for functions like st...
component-search
by redpanda-dataThis skill should be used when users need to discover Redpanda Connect components for their streaming pipelines. Trigger when users ask about finding ...
reasoningbank-with-agentdb
by ruvnet"Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distilla...
reasoningbank-with-agentdb
by ruvnet"Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distilla...
Agentic Skill Details
- Repository
- gtm-agents
- Type
- Technical
- Meta-Domain
- data ai
- Primary Domain
- database
- Market Score
- 60.0
Agent Skill Grade
D
Score: 60/100
Click to see breakdown
Score Breakdown
Recommendations
- Focus on improving Pda (currently 12/30)
- Focus on improving Utility (currently 10/20)
- Add trigger phrases to description for discoverability
Graded: 1/19/2026
Developer Feedback
I took a look at your technical-seo skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 60/100, D grade territory — this is based on Anthropic's skill best practices. The good news: your spec compliance is solid (12/15). The tough news: Progressive Disclosure Architecture and Utility are dragging you down hard (12/30 and 10/20 respectively). You've got the foundation right, but the skill needs more depth and structure to really shine.
What's Working Well
- Spec compliance is tight — Your frontmatter is valid YAML with all required fields, name convention is correct hyphen-case. That's the baseline done right.
- Readable structure — The skill has decent navigation signals with clear headers and what looks like a logical TOC, which helps discoverability.
- Concise writing — Your content isn't bloated. You're saying what needs to be said without fluff (that's worth points in the Writing Style category).
The Big One: Reference Files Are Missing
Here's what's holding you back: you have zero reference files supporting your main SKILL.md. The grading report shows "0 reference files with 0 words" — that's a killer for Progressive Disclosure Architecture (which you need for the full 30 points).
Why this matters: A skill with only one 387-word SKILL.md file can't progressively disclose its complexity. Users get dumped the whole thing at once instead of layered discovery. This is a token efficiency problem AND a usability problem.
The fix: Create reference files. Think:
guides/getting-started.md— onboarding stepsexamples/common-audits.md— real-world use casesreference/tools-explained.md— detailed tool explanationstemplates/audit-checklist.md— templates users can reuse
Even 2-3 well-structured reference files would bump your PDA score from 12 to 20+. That alone gets you to 68-70.
Other Things Worth Fixing
Flesh out your description triggers — You're only at 3/4 on description quality. Add 2-3 more trigger phrases beyond what you have. Think: "SEO audit", "search ranking", "crawl errors". This improves discoverability and helps the right people find your skill.
Add examples and templates — You scored 1/3 here. Include at least one code block or template showing how to use this skill in context. A simple JSON schema of expected output or a before/after example would get you the remaining points.
Strengthen feedback loops — You're at 1/4. Add validation sections that help users know if they're using the skill correctly. Something like "If you see X output, it means Y" or "Common mistakes to avoid".
Quick Wins
- Create 2-3 reference files (biggest bang for your buck — +8-10 points PDA)
- Add 2 more trigger phrases to your description (+1 point, easy win)
- Include 1-2 templates or examples (+2 points Utility)
- Add a "How to Know It Worked" section for feedback loops (+2-3 points)
These moves get you from 60 to 72-75, solidly into C territory. The reference files are the key unlock.
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
Browse Category
More data ai Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?