Agent skill

Cohort Analysis

by guia-matthieu in guia-matthieu/clawfu-skills

Analyze user retention by cohort. An agent skill from guia-matthieu/clawfu-skills.

MITAuto-check passedData & Analytics

Install Cohort Analysis

skills CLI
$ npx skills add guia-matthieu/clawfu-skills --skill cohort-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install guia-matthieu/clawfu-skills cohort-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/guia-matthieu/clawfu-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/analytics/cohort-analysis .claude/skills/cohort-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cohort-analysis
GitHub stars
150
Token cost
~864 tokens
SKILL.md length
195 words
Files
3 (incl. scripts)
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Analyze user retention by cohort. An agent skill from guia-matthieu/clawfu-skills.

  • : measuring customer retention
  • SKILL.md covers When to Use This Skill, What Claude Does vs What You…, Dependencies and Commands, plus 5 more sections
  • Runs Python scripts from its folder; calls python and pip
  • Understanding lifecycle patterns

What it does

Cohort Analysis is an agent skill from guia-matthieu/clawfu-skills. Analyze user retention by cohort. Use when: measuring customer retention; understanding lifecycle patterns; comparing acquisition cohorts; tracking engagement over time; identifying churn risks

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/main.py`).

It sits in Data & Analytics, covering Product analytics, Referral and retention marketing and Customer success. The repository describes itself as: 172 expert marketing skills for AI agents — ClawFu MCP Server. The licence is MIT.

When your agent uses it

  • : measuring customer retention
  • Understanding lifecycle patterns
  • Comparing acquisition cohorts
  • Tracking engagement over time

Example prompts

  • “/cohort-analysis”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 4108f5c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cohort Analysis loads about 864 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 195 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~864

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from guia-matthieu/clawfu-skills at commit 4108f5c, republished under its MIT licence (© guia-matthieu). 195 words, ~864 tokens.

Download SKILL.mdSave it as .claude/skills/cohort-analysis/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
cohort-analysis
description
Analyze user retention by cohort. Use when: measuring customer retention; understanding lifecycle patterns; comparing acquisition cohorts; tracking engagement over time; identifying churn risks
license
MIT
metadata.author
ClawFu
metadata.version
1.0.0
metadata.mcp-server
@clawfu/mcp-skills

Cohort Analysis

Analyze retention and behavior patterns by grouping users into cohorts - understand how different customer groups behave over time.

When to Use This Skill

  • Retention tracking - Measure how users stick around over time
  • Acquisition analysis - Compare cohorts from different channels
  • Product changes - Measure impact on user behavior
  • Churn prediction - Identify at-risk cohorts
  • LTV estimation - Project customer lifetime value

What Claude Does vs What You Decide

Claude DoesYou Decide
Structures analysis frameworksMetric definitions
Identifies patterns in dataBusiness interpretation
Creates visualization templatesDashboard design
Suggests optimization areasAction priorities
Calculates statistical measuresDecision thresholds

Dependencies

bash
pip install pandas plotly click

Commands

Retention Analysis
bash
python scripts/main.py retention data.csv --date-col signup --event-col purchase
python scripts/main.py retention data.csv --date-col signup --periods week
Visualize Cohorts
bash
python scripts/main.py visualize cohorts.csv --output retention_chart.html
Export Report
bash
python scripts/main.py report data.csv --date-col signup --event-col active --output report.html

Examples

Example 1: Analyze User Retention
bash
python scripts/main.py retention users.csv --date-col signup_date --event-col last_active

# Output:
# Cohort Retention Analysis
# ──────────────────────────────────
# Cohort     Users    M1     M2     M3     M4
# Jan 2024   1,234    65%    48%    42%    38%
# Feb 2024   1,456    62%    45%    41%    --
# Mar 2024   1,321    68%    52%    --     --
# Apr 2024   1,567    64%    --     --     --
#
# Avg Retention: 65% → 48% → 42% → 38%
# Best Cohort: Mar 2024 (68% M1)
Example 2: Generate Visual Report
bash
python scripts/main.py report transactions.csv \
  --date-col signup \
  --event-col purchase_date \
  --output retention_report.html

# Generates interactive HTML with:
# - Retention heatmap
# - Cohort size chart
# - Trend analysis

Cohort Table Format

CohortSizePeriod 0Period 1Period 2Period 3
2024-011234100%65%48%42%
2024-021456100%62%45%-
2024-031321100%68%--

Skill Boundaries

What This Skill Does Well
  • Structuring data analysis
  • Identifying patterns and trends
  • Creating visualization frameworks
  • Calculating statistical measures
What This Skill Cannot Do
  • Access your actual data
  • Replace statistical expertise
  • Make business decisions
  • Guarantee prediction accuracy

Skill Metadata

  • Mode: centaur
yaml
category: analytics
subcategory: retention
dependencies: [pandas, plotly]
difficulty: intermediate
time_saved: 4+ hours/week

© guia-matthieu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/analytics/cohort-analysis of guia-matthieu/clawfu-skills.

  • SKILL.md
  • scripts/main.py
  • scripts/requirements.txt

Open the folder on GitHubat commit 4108f5c

Compare with similar skills

Cohort Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cohort Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cohort Analysis this skillguia-matthieu/clawfu-skills150—~864Automated safety check: PassMIT
Retention Analysisliangdabiao/claude-data-analysis-ultra-main290—~1.3kAutomated safety check: NotesNone
Almost Paidnestyme/awesome-prompts151—~3.9kAutomated safety check: PassNone
Cohort Analysisindranilbanerjee/digital-marketing-pro8621 repos~2.7kAutomated safety check: PassMIT
Product Adoptionmagnus919/agent-skills115—~1.7kAutomated safety check: PassMIT
PostHog CLI Queriesdebugtheworldbot/keyStats1.5k—~1.2kAutomated safety check: PassMIT

Similar skills

  • Retention Analysis

    liangdabiao/claude-data-analysis-ultra-main

    Analyze user retention and churn using survival analysis, cohort analysis, and machine learning.

    290 GitHub stars~1.3k tokensUpdated 5 mo ago
    Data & AnalyticsAuto-check: notes
  • Almost Paid

    nestyme/awesome-prompts

    Find the users who almost paid — saw the paywall, started checkout, ran out of free credits, let a trial lapse — size what they are worth, and turn them into a one-screen dashboard with a…

    151 GitHub stars~3.9k tokensUpdated 10 days ago
    Data & AnalyticsAuto-check passed
  • Cohort Analysis

    indranilbanerjee/digital-marketing-pro

    Run cohort analysis: retention matrix and LTV by cohort. An agent skill from indranilbanerjee/digital-marketing-pro.

    862 GitHub starsUsed in 1 repo~2.7k tokens
    Data & AnalyticsAuto-check passed
  • Product Adoption

    magnus919/agent-skills

    Diagnose and design product adoption for onboarding, activation, behavior change, feature discovery, rollout, and sustained use after launch.

    115 GitHub stars~1.7k tokensUpdated today
    Sales & SupportAuto-check passed
  • PostHog CLI Queries

    debugtheworldbot/keyStats

    Runs HogQL queries against this project's PostHog data from the terminal using posthog-cli, with bundled scripts for dashboard metadata the CLI itself has no command for.

    1.5k GitHub stars~1.2k tokensUpdated 7 days ago
    Data & AnalyticsAuto-check passed
  • Retentioneering Contributing

    retentioneering/retentioneering-tools

    Help the user turn their Retentioneering ideas, friction reports, bug findings, or feature needs into high-quality upstream contributions: from capturing and validating the idea, through minimal…

    927 GitHub stars~1.8k tokensUpdated 3 days ago
    Data & AnalyticsAuto-check passed

More from guia-matthieu/clawfu-skills

All 31 skills in this repo
  • Ab Test Stats

    guia-matthieu/clawfu-skills

    Calculate A/B test statistical significance. An agent skill from guia-matthieu/clawfu-skills.

    150 GitHub stars~1k tokensUpdated 9 days ago
    Auto-check passed
  • Competitive Analysis

    guia-matthieu/clawfu-skills

    Analyze your competitive landscape using Porter's Five Forces and modern frameworks—understand industry dynamics, identify strategic opportunities, and position your business for sustainable…

    150 GitHub stars~5.2k tokensUpdated 9 days ago
    Auto-check passed
  • Competitor Monitor

    guia-matthieu/clawfu-skills

    Monitor competitor websites for changes. An agent skill from guia-matthieu/clawfu-skills.

    150 GitHub stars~815 tokensUpdated 9 days ago
    Auto-check passed
  • Content Repurposer

    guia-matthieu/clawfu-skills

    Transform long-form content into multiple short-form pieces.

    150 GitHub stars~1.4k tokensUpdated 9 days ago
    Auto-check passed
  • Deliverability Checker

    guia-matthieu/clawfu-skills

    Check email deliverability and DNS configuration. An agent skill from guia-matthieu/clawfu-skills.

    150 GitHub stars~1.1k tokensUpdated 9 days ago
    Auto-check passed
  • Image Batch

    guia-matthieu/clawfu-skills

    Batch process images for marketing. An agent skill from guia-matthieu/clawfu-skills.

    150 GitHub stars~1.3k tokensUpdated 9 days ago
    Auto-check passed

Questions about Cohort Analysis

What does Cohort Analysis do?

Analyze user retention by cohort. An agent skill from guia-matthieu/clawfu-skills. Cohort Analysis is an agent skill from guia-matthieu/clawfu-skills. Analyze user retention by cohort.

When should I use Cohort Analysis?

Cohort Analysis fits situations like: : measuring customer retention; understanding lifecycle patterns; comparing acquisition cohorts; tracking engagement over time.

How do I install Cohort Analysis in Claude Code?

Run `npx skills add guia-matthieu/clawfu-skills --skill cohort-analysis -a claude-code`. Or copy the skill folder (skills/analytics/cohort-analysis in guia-matthieu/clawfu-skills) into .claude/skills/cohort-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Cohort Analysis in Codex?

Run `npx skills add guia-matthieu/clawfu-skills --skill cohort-analysis -a codex`. Or copy the skill folder (skills/analytics/cohort-analysis in guia-matthieu/clawfu-skills) into .agents/skills/cohort-analysis in your project. Codex loads it when a task matches its description.

Can I use Cohort Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add guia-matthieu/clawfu-skills --skill cohort-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cohort-analysis, .gemini/skills/cohort-analysis, .github/skills/cohort-analysis and .opencode/skills/cohort-analysis in your project.

What does Cohort Analysis need to run?

Going by SKILL.md and its folder, Cohort Analysis needs Python for the scripts in its folder and the command-line tools its instructions call (python and pip). Our summary lists: Python 3.

Does Cohort Analysis access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Cohort Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cohort Analysis use?

Cohort Analysis is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cohort Analysis use?

About 864 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cohort Analysis?

Skills that share tags, products or a category with Cohort Analysis: Retention Analysis (liangdabiao/claude-data-analysis-ultra-main, 290 stars), Almost Paid (nestyme/awesome-prompts, 151 stars), Cohort Analysis (indranilbanerjee/digital-marketing-pro, 862 stars) and Product Adoption (magnus919/agent-skills, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cohort Analysis?

guia-matthieu (a GitHub user) maintains it in guia-matthieu/clawfu-skills, which has 150 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 1, 2026.

Source: guia-matthieu/clawfu-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.