Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Humblytics/humblytics-marketing-skills --skill cro-optimizergit clone --depth 1 https://github.com/Humblytics/humblytics-marketing-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/cro-optimizer)<a href="https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/cro-optimizer"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/cro-optimizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/cro-optimizer"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/cro-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.02689 |
| Opus 5 | $0.00038 | $0.01345 |
| Sonnet 5 | $0.00015 | $0.00538 |
| Haiku 4.5 | $0.00008 | $0.00269 |
Grade A, and why
cro-optimizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRO Optimizer
Purpose
Analyze conversion funnels using live Humblytics analytics (via the Humblytics MCP), identify the highest-impact drop-off points, and generate prioritized A/B test hypotheses with expected conversion-rate / volume impact. This skill turns raw analytics into a ranked optimization roadmap.
When to Use
- Diagnosing why a funnel is underperforming
- Identifying the biggest conversion bottleneck across a user journey
- Generating a prioritized list of A/B test ideas
- Preparing a CRO sprint plan or quarterly optimization roadmap
- Analyzing page-level or step-level drop-off rates
- Comparing conversion performance across segments (device, source, geography)
Credentials
Live data comes from the Humblytics MCP (server humblytics). Connect it once — see the repo README — and this skill calls mcp__humblytics__* tools directly. No API keys, base URLs, or .env plumbing live in the skill.
- Never paste API keys into chat — they persist in transcripts and logs. Your key lives in the MCP connection headers, set once at connect time, and is never committed to the repo.
- Property: the MCP auto-resolves your property for a single-property key (the common case). For a multi-property key, call
list_propertiesand pass thepropertyIdyou want to analyze. - Docs: https://docs.humblytics.com/api
Before You Start
- Confirm the property — The MCP auto-resolves the property for a single-property key. If the key covers multiple properties, call
list_propertiesand confirm which one to analyze. - Identify the funnel — Clarify which conversion flow to examine (e.g., homepage > pricing > signup > onboarding)
- Check for context — Look for existing project docs, AGENTS.md, or product briefs that describe the business model, target audience, and current conversion goals
- Establish the time range — Default to last 30 days; ask if the user wants a different window
- Confirm MCP access — Verify the Humblytics MCP (server
humblytics) is connected before pulling data
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 187 lines · 76 tokens per session scan A 4e34de51e7ad
cro-optimizer is a skill published in the GitHub repository Humblytics/humblytics-marketing-skills (83 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 2,689 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ab-test-generator
Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version is better", "optimize conversions"…
authoring-ci-workflows
Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under .github/ — new CI jobs, triggers, matrices, checkout/clone tuning, action pinning, GitHub App token auth, concurrency groups, timeout-minutes, paths filters, caching, or runner choice. Covers PostHog's workflow-authoring…
isolating-product-facade-contracts
Plan and execute product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture. Use when a product still exposes internals (models/logic/views) across boundaries and needs migration toward contracts.py + facade/api.py + presentation separation, with a PR strategy…
debugging-mcp-analytics
Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the @posthog/mcp and posthog.mcp SDKs plus the mcpanalytics product). Use when MCP analytics data looks wrong or missing ("events aren't showing", "intent clusters are empty", "sessions are missing", "per-tool numbers look wrong")…
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code review, PR review…
triaging-merge-queue-failures
Decision procedure for a PR that failed or was removed from the Trunk merge queue: classify the kick (superseded by a newer commit, not mergeable, a gate that failed on a cancelled run, real failure, one-off flake, or repo-wide flaky/infra issue) and take the matching action (wait, hold and fix, requeue once, or…