agentleFS
45ck45ck/marketing-product-skills/.claude/skills/onboarding-activation-audit/SKILL.md

onboarding-activation-audit

Skill3 starsChanged 8 months agoMITView on GitHub

Audit a signup, onboarding, and activation flow to identify friction, missing value discovery, and concrete product/growth fixes.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants a structured review of first-time user experience, activation, and early value realization.

    line 9
  2. Distinctive:

    Use any combination of:

    line 26
  3. Distinctive:

    If direct assets are missing, perform a heuristic audit from the available description.

    line 36
  4. Distinctive:

    Start from the user’s motivating situation and desired progress.

    line 41
  5. Distinctive:

    Create a step map from arrival to first value.

    line 68
  6. Distinctive:

    Use these severity levels:

    line 166
  7. Distinctive:

    If the product is B2B SaaS:

    line 174
  8. Distinctive:

    check whether onboarding optimizes for team rollout too early or too late

    line 175
  9. Distinctive:

    If screenshots or direct UI assets are absent:

    line 179

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Onboarding Activation Audit

Use this skill when the user wants a structured review of first-time user experience, activation, and early value realization.

What this skill must produce

Always produce:

  1. Flow summary
  2. Target job / switching moment
  3. Activation model
  4. Friction audit
  5. Missing value-discovery audit
  6. Experiment ideas
  7. Instrumentation needs
  8. Prioritized action plan

Inputs to gather

Use any combination of:

  • screenshots / recordings / Figma
  • docs / product copy
  • analytics notes
  • onboarding emails / lifecycle messages
  • signup form and first-session behavior
  • product type (attention / transaction / productivity)
  • whether the product is self-serve, PLG, or sales-assisted

If direct assets are missing, perform a heuristic audit from the available description.

Working rules

  • Evaluate onboarding as behavior change, not just a UI tutorial.
  • Start from the user’s motivating situation and desired progress.
  • Separate onboarding from activation. Activation requires value found and value returned to the business.
  • Focus on the fastest route to meaningful action.
  • Reduce steps that are account-focused but not value-focused.
  • Watch for friction that delays the aha moment.

Step-by-step method

Step 1: define the user’s switch

State:

  • what situation they are trying to get away from
  • what progress they want
  • what they are "hiring" the product to do

Step 2: model activation

Break activation into:

  • trigger / acquisition moment
  • onboarding
  • aha moment
  • first value exchange
  • early repeat use / ladder of engagement

Define a candidate activation event.

Step 3: map the current flow

Create a step map from arrival to first value.

For each step note:

  • user task
  • system response
  • why the step exists
  • risk introduced
  • whether it moves the user toward value or only toward setup

Step 4: audit for friction

Inspect:

  • unnecessary fields
  • permission prompts too early
  • unclear copy
  • dead-end states
  • empty states without guidance
  • delayed feedback
  • missing social proof
  • poor defaults
  • too many decisions before value
  • account setup dominating doing-focused progress

Step 5: audit for missing value discovery

Inspect whether the flow:

  • teaches the right behavior
  • gets users to do something meaningful
  • shows proof of benefit
  • creates momentum toward a second session
  • includes lifecycle reinforcement

Step 6: propose fixes

Provide fixes at three levels:

  • copy / content
  • product flow
  • lifecycle / messaging

Step 7: define experiments

Translate fixes into minimum viable tests.

Step 8: define instrumentation

List the events and properties needed to measure the flow.

Output structure

Flow summary

  • Product:
  • User:
  • Core job:
  • Dominant motion:
  • Current conversion target:

Target job / switching moment

  • Old way:
  • Frustration pushing the switch:
  • Desired progress:
  • What success feels like:

Activation model

  • Candidate aha moment:
  • Candidate first value exchange:
  • Candidate activation event:
  • Early retained behavior:

Current flow map

StepWhat the user doesWhy this existsMoves toward value?Main risk

Friction audit

IssueSeverityWhy it hurtsSuggested fix

Missing value-discovery audit

Missing elementWhy it mattersSuggested intervention

Experiment ideas

ExperimentHypothesisSuccess metricMin viable test

Instrumentation needs

List events, properties, and funnel stages required to measure:

  • signup completion
  • onboarding completion
  • aha moment reached
  • first value exchange
  • second-session return

Prioritized action plan

  • Now: 3 changes with the highest expected impact
  • Next: 3 changes to validate through experiments
  • Later: structural improvements requiring more work

Severity scoring

Use these severity levels:

  • Critical: likely blocking activation at scale
  • High: strong drag on conversion or value discovery
  • Medium: meaningful but not fatal
  • Low: polish issue

Special instructions

If the product is B2B SaaS:

  • check whether onboarding optimizes for team rollout too early or too late
  • inspect whether the user is armed with material to bring coworkers in
  • inspect whether a product-qualified account signal should be defined

If screenshots or direct UI assets are absent:

  • be explicit that this is a heuristic audit
  • focus on logic, sequence, copy, and measurement

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.