Agent skill

activation-analysis

Analyze user activation using Setup → Aha → Habit framework. Identifies activation bottlenecks.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill activation-analysis --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 19 KB
Bundled scripts: none
Path: skills/analysis/activation-analysis/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

The skill guides a user to analyze activation by applying the Setup → Aha → Habit framework to diagnose onboarding problems and identify bottlenecks. It prompts the user for their product, onboarding flow, and metrics, then performs a structured activation diagnostic across three stages (Setup, Aha, Habit) and provides metrics to track (e.g., Setup completion, Time to Aha, D7 retention). It outputs an activation analysis saved to a dated Markdown file and references related context, metrics, and research to inform improvements.

How it works

  • Start with a Quick Start that asks the user for core product details, current onboarding flow, and available metrics.
  • Run through Step 0 to gather internal intelligence from context sources (business info, metrics, user research, meetings, PRDs) and propose gaps.
  • Use Step 1 to pose diagnostic questions aimed at identifying leaks, evidence for the Aha moment, onboarding goals, success signals, and current metrics.
  • Provide an Overview of the three stages and the Framework, including stages definitions and sample metrics.
  • In Step 2, outline how to measure each stage with formulas for Setup Rate, Aha Rate, Habit Rate, and Overall Activation, plus example calculations.
  • Step 3 offers diagnostic drop-off guidance for each stage and Step 4 suggests improvement priorities and tactics for Setup, Aha, and Habit.
  • Include Time-to-Value discussions, cohort analysis, and an Activation Metrics Dashboard with weekly KPIs.
  • Provide a worksheet template to define the three stages and a structured Output Integration plan showing where to save reports and how to link to related artifacts in the context library.
  • The framework emphasizes data-driven Aha moments (based on retained vs churned behavior) and cautions against optimizing without addressing Setup bottlenecks.

When to use it

  • When diagnosing activation problems, improving onboarding, or measuring early product engagement
  • When you need a structured method to define stages, measure progression, and identify bottlenecks in activation

What it can touch

  • Uses references to internal context (business-info-template.md, metrics, research, meetings, PRDs) and external analytics tools (Amplitude/Mixpanel) when connected to provide funnel and retention context.
  • Instructions include saving outputs to outputs/analyses/activation-analysis-[date].md and updating context-library and PRDs as integration points

Caveats

  • The skill requires user-provided data for the three stages and metrics; results depend on the quality and completeness of input data
  • It prescribes explicit definitions and calculations but does not guarantee specific outcomes; recommendations are conditional on data
  • Licensing and tool usage are stated as MIT and claude-code, but concrete tool usage is constrained to what the skill explicitly prescribes
From the SKILL.md

# Activation Analysis: Setup → Aha → Habit Framework ## Quick Start ``` /activation-analysis ``` Then provide: 1. **Your product** and core value proposition (or I'll pull from business-info) 2. **Current onboarding flow** (what steps do new users take?) 3. **Any metrics you have** (setup completion %, D7 retention, time-to-value) I'll diagnose your activation funnel using Setup -> Aha -> Habit, identify the biggest bottleneck, and recommend specific fixes. **Output:** Saved to `outputs/analyses/activation-analysis-[date].md` **Time:** ~15 min with data, ~25 min if defining stages from scratch **When to use:** When diagnosing activation problems, improving onboarding, or measuring early product engagement **Framework source:** Aakash Gupta's "Ultimate Guide to Activation" and "How to Measure Onboarding" ## Context Routing Logic (Internal - for Claude) **Automatic Context Checks:** When this skill is invoked, immediately check: | Source | Files/Folders | Search Terms | What to Extract | |--------|---------------|--------------|-----------------| | Metrics/Analytics | `context-library/metrics/*.md` | "onboarding", "setup", "activation", D7, D30, "time to value", TTV | Current activat

What's inside
Steps it walks through
  1. Quick Start
  2. Context Routing Logic (Internal - for Claude)
  3. Step 0: Understanding Your Current Activation Landscape
  4. Internal Intelligence Summary
  5. Gaps in Knowledge
  6. Step 1: Activation Diagnostic Questions
  7. Question 1: The Biggest Leak
  8. Question 2: Aha Moment Evidence
  9. Question 3: Onboarding Goals
  10. Question 4: Success Signal
  11. Question 5: Current Metrics
  12. Overview
  13. The Framework
  14. Stage 1: Setup
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the activation-analysis skill do?

Analyze user activation using Setup → Aha → Habit framework. Identifies activation bottlenecks.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill activation-analysis --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going