Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This repository provides a set of structured skills designed to automate the evaluation of digital marketing performance and the application of corporate visual standards. It enables agents to process multi-channel campaign data to calculate funnel metrics and efficiency ratios while ensuring document styling adheres to specific brand guidelines.
These tools help analysts move from raw performance data to budget reallocation recommendations and assist creators in maintaining a consistent artisanal aesthetic across presentations and documents.
WHO IT'S FOR
Digital Marketing Analysts
calculating funnel metrics and ROAS efficiency
Data Scientists
performing diagnostic analysis on time series data
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Replace `<path-to-campaign.csv>` with a CSV containing date, campaign_name, channel, segment, impressions, clicks, conversions, spend, revenue, and orders.
Make sure analyzing-marketing-campaign is installed in your agent before trying this task.
Use the analyzing-marketing-campaign skill to analyze `<path-to-campaign.csv>`. Check data quality, then calculate CTR, CVR, ROAS, CPA, and net profit by channel using the skill's default benchmarks and cost assumptions. Present the funnel and efficiency tables followed by brief channel-by-channel findings. Do not perform budget reallocation.
Replace `<path-to-data.csv>` with a CSV containing one date or timestamp column and one numeric value column.
Replace `<path-to-results-directory>` with the directory where diagnostic results should be stored.
The documented Python dependencies are pandas, numpy, matplotlib, statsmodels, and scipy.
Make sure analyzing-time-series is installed in your agent before trying this task.
Use the analyzing-time-series skill to diagnose `<path-to-data.csv>` and summarize whether the series is forecastable, stationary, seasonal, trending, or likely to need a transform. Use `<path-to-results-directory>` for the diagnostic outputs. Skip the optional plots for this first result.
Replace `<path-to-command.py>` with the Typer command implementation to review.
Provide the related `commands/__init__.py` registration file if registration cannot be assessed from the command file alone.
Make sure reviewing-cli-command is installed in your agent before trying this task.
Use the reviewing-cli-command skill to review `<path-to-command.py>`. Check its structure, Annotated argument and option syntax, validation and exit codes, display-module usage, destructive-action safeguards where applicable, registration, docstring, and help text. Return the documented review format with a brief summary and suggested fixes; do not modify the file.
Claude