cohort-analysis

An agent skill by phuryn, from phuryn/pm-skills. Tags: automation, spreadsheets, trend-analysis, web.

What it does

Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over time, investigating churn patterns, or identifying engagement trends.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add phuryn/pm-skills --skill cohort-analysis

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/phuryn/pm-skills
cp -r pm-skills/pm-data-analytics/skills/cohort-analysis ~/.claude/skills/cohort-analysis

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a markdown-only analytics skill that reads user-provided cohort datasets, computes retention/adoption metrics, and suggests follow-up research. It does not ship executable code or automation, so the main consideration is ordinary handling of whatever user engagement data you upload, which may be sensitive.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code execution are shipped; `SKILL.md` is descriptive only.
Network access	0 (none)	The only outbound references are static `Further Reading` links; there is no download/upload or remote-host interaction code.
Filesystem reach	0 (none)	The skill only describes analyzing uploaded files and generating outputs; it does not read, write, or delete local paths.
Secrets & credentials	0 (none)	It mentions cohort and engagement data, but nothing about tokens, passwords, keychains, `.env` files, or other credential stores.
Privilege & persistence	0 (none)	There is no sudo, install, service registration, shell startup editing, or other privilege-changing behavior.
Instruction hijack surface	0 (none)	The file contains no instructions to ignore policies, hide actions, or follow remote instructions; it is straightforward documentation.
Irreversible actions	0 (none)	It recommends analysis and research follow-ups only; it does not send messages, publish, pay, book, deploy, or delete anything.
Transparency	0 (none)	There are no binaries, minified blobs, base64 payloads, or unpinned installers; the repository content is fully readable markdown.

Before installing

Confirm you are comfortable uploading cohort data to the agent, since the skill is designed to ingest CSV, Excel, or JSON files.
If you plan to use the optional Python output, review the generated script before running it locally.
Treat any cohort tables with user-level activity as potentially sensitive and only analyze data you are allowed to share.

Rated 2026-10-19 by an automated review of 1 file from the skill's repository.

Source

Repository: phuryn/pm-skills (all skills from this repository)
Path: pm-data-analytics/skills/cohort-analysis/SKILL.md
Branch: main
Updated: 2026-09-19

ab-test-analysis — Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations.
sentiment-analysis — Analyze user feedback data to identify segments with sentiment scores, JTBD, and product satisfaction insights.
growth-loops — Identify growth loops (flywheels) for sustainable traction. Evaluates 5 loop types: Viral, Usage, Collaboration, User-Generated, and Referral.
user-segmentation — Segment users from feedback data based on behavior, JTBD, and needs. Identifies at least 3 distinct user segments.
aws-blocks — Guides building full-stack applications with AWS Blocks — an Infrastructure-from-Code framework.
chrome-mcp-troubleshooting — Diagnose and fix Claude in Chrome MCP extension connectivity issues.