performance-benchmarking
Compares your key metrics against industry benchmarks for your specific vertical, campaign type, and platform. Tells you where you're ahead, where you're behind, and where there's room to improve — adjusted for your account size and spend level, because a $10K/month account and a $500K/month account…
Install / Use
npx skills add irinabuht12-oss/marketing-skills --skill performance-benchmarkingInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of performance-benchmarking
performance-benchmarking scores 83/100 on our quality scale, 3015th of 4,698 Development & Engineering skills we index.
Its SKILL.md is 2.9 KB long, split into 7 sections and no code examples: a solid amount of guidance for an agent.
With 7,761 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 20 days ago, so performance-benchmarking is actively maintained.
- Our last check on 2026-11-06 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
ReviewOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs the agent to add a custom third-party MCP connector at https://connector.get-ryze.ai/mcp so Claude can read Google Ads, Meta Ads, GA4 and Search Console data, routing sensitive account data through an unofficial intermed.
AI review: risky
- The skill instructs the agent to add a custom third-party MCP connector at https://connector.get-ryze.ai/mcp so Claude can read Google Ads, Meta Ads, GA4 and Search Console data, routing sensitive account data through an unofficial intermed
- It frames this connector setup as a normal prerequisite for benchmarking, which could lead users to grant broad read access to advertising and analytics accounts without scrutinizing the third-party service.
- It does not instruct credential theft, destructive commands, or disabling permission prompts, so it is not malicious, but the requested integration meaningfully increases data exposure.
AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
performance-benchmarking compared with similar skills
All 4 of these similar skills score higher than performance-benchmarking; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| performance-benchmarking (this skill)by irinabuht12-oss | 83 | 7.8k | 20d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install performance-benchmarking?
- Run
npx skills add irinabuht12-oss/marketing-skills --skill performance-benchmarking. The install tabs above show the steps for each supported agent. - Which AI agents does performance-benchmarking work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is performance-benchmarking safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs the agent to add a custom third-party MCP connector at https://connector.get-ryze.ai/mcp so Claude can read Google Ads, Meta Ads, GA4 and Search Console data, routing sensitive account data through an unofficial intermed. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is performance-benchmarking still maintained?
- The repository was last updated 20 days ago, so performance-benchmarking is actively maintained.
Skill content
View source on GitHubname: performance-benchmarking description: Compares your key metrics against industry benchmarks for your specific vertical, campaign type, and platform. Tells you where you're ahead, where you're behind, and where there's room to improve — adjusted for your account size and spend level, because a $10K/month account and a $500K/month account have different benchmark realities. Platform: Google and Meta. metadata: platform: Google and Meta
29/ Performance Benchmarking — Google + Meta
What it does
Compares your key metrics against industry benchmarks for your specific vertical, campaign type, and platform. Tells you where you're ahead, where you're behind, and where there's room to improve — adjusted for your account size and spend level, because a $10K/month account and a $500K/month account have different benchmark realities.
How it works
Claude takes your core metrics (CPC, CTR, CVR, CPA, ROAS, CPM) and compares them against available benchmark data for your industry and campaign type. It adjusts for factors that affect comparison — account maturity, geo, budget level, and funnel stage — so you're not comparing your prospecting CPA against someone else's retargeting CPA.
Practical example
Your SaaS client's Google Search campaigns show a 3.2% CTR and $52 CPA. Claude benchmarks this against B2B SaaS averages: CTR is 18% above benchmark (strong ad relevance), but CPA is 30% above benchmark, with the gap primarily in CVR (2.1% vs benchmark 3.4%). This points to a landing page issue rather than an ad issue — your ads attract clicks at a good rate, but the landing page isn't converting them. For Meta, your CPM of $18 is right at benchmark, but your hook rate on video ads (22%) is well below the 35% benchmark, suggesting the first 3 seconds of your videos need work.
What you get back
- Metric-by-metric comparison against industry benchmarks with variance percentages
- Where you're outperforming with context on why
- Where you're underperforming with likely root causes
- Prioritized improvement opportunities ranked by potential impact
- Benchmark context: what "good" looks like for your specific situation, not just industry averages
When to use it
- When pitching new clients to identify quick wins in their accounts
- QBRs and annual reviews to show performance in context
- When clients ask "is our CPA good?" and need a data-backed answer
- For internal team benchmarking across multiple client accounts in the same vertical
Data access (Ryze MCP)
This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:
- claude.ai / Claude Desktop: Settings → Connectors → Add custom connector →
https://connector.get-ryze.ai/mcp - Claude Code:
claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp - Cursor: Settings → MCP → add the same URL
Setup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
