Skip to content
SkillModel-led980 tokens in use

cohort-analysis

Analyze user engagement by cohort: retention curves, feature adoption trends and churn patterns, with charts, Python scripts and follow-up research ideas.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-data-analytics/skills/cohort-analysis
claude plugin install pm-data-analytics@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing cohort-analysis costs

47tokens idle
980tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure23/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

cohort-analysis guides an agent through reading cohort data from CSV, Excel or JSON, checking its quality, and calculating retention rates and engagement trends. It builds retention heatmaps and cohort charts, picks out the significant patterns, and recommends qualitative and quantitative follow-ups such as churn interviews and A/B tests.

What You Get

  • A data summary covering cohort sizes, date ranges and quality issues
  • Retention rates, drop-off points and period-over-period changes
  • Retention heatmaps and cohort progression charts
  • Two or three significant patterns, such as early churn in one cohort
  • Specific follow-up research such as churn interviews and win/loss analysis
  • Reusable Python analysis scripts using pandas and numpy on request

Common Use Cases

  • Finding out why a recent signup cohort retains worse than an earlier one
  • Comparing how fast cohorts adopt a new feature
  • Choosing which retention metrics to track for a subscription app

What Makes It Unique

It pairs the numbers with a research plan. After the retention analysis it names interviews, surveys, session replays and experiments that would explain what the data shows, so the output leads to the next piece of work.

Under The Hood

The skill is one SKILL.md of instructions with no bundled scripts. The agent reads the files you provide and, when you ask for it, writes Python scripts with pandas and numpy to compute retention and draw charts. It shows example prompts and an output format. It reaches no outside service.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers