AI Agent Hub
Back to plugins
⚙️

dsh-ctr-split

Workflow Updated 2026.08.20

Run the following command in DeepSeek Harness:

dsh plugin install uckkk/dsh-ctr-split

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install uckkk/dsh-ctr-split in DeepSeek Harness to install this plugin; source code is available at https://github.com/uckkk/dsh-ctr-split

About this plugin

When running ad campaigns, landing-page iterations, or A/B tests, an overall click-through rate rarely tells you which parameter is actually driving the shift. dsh-ctr-split tackles exactly that decomposition problem: it breaks a single CTR figure down by individual parameters so you can pinpoint each one's contribution.

At its core, the plugin exposes a ctr_split tool that takes your parameters, applies the exact formula, and returns a structured set of detailed results. The whole implementation is pure Node with zero network calls, so every computation runs locally with predictable latency and reproducible output, making it a natural fit as a deterministic calculation step inside an agent workflow.

If you are on a growth team, a data analyst, or simply anyone who needs to decompose CTR by parameter inside a conversation without relying on an external SaaS or database, this plugin is ready to drop in and turn your attribution logic into an orchestratable workflow step.

Use Cases

  • Decompose an overall CTR by individual ad parameters after an A/B test
  • Invoke the CTR split tool directly inside an agent session
  • Compute CTR breakdowns locally without any external database

Best For

  • Growth and ad-optimization teams
  • Data analysts and product analysts
  • Developers adding deterministic calculation steps to agent workflows