Hooked ux
Diagnose retention and engagement issues by mapping product behavior to the Hook Model (trigger, action, reward, investment). Use when users are not coming back, engagement drops, or the team wants to improve habit loops.From its SKILL.md
npx -y skills add talgacapri/pm-os --skill hooked-uxAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.7 KB, 328 tokens by cl100k_base, as published. Nobody here has run it
Hooked UX
Use this skill when users sign up but do not return consistently.
What this skill does
This skill maps an experience to the Hook Model:
- Trigger
- Action
- Reward
- Investment
It identifies where the habit loop is breaking and how to strengthen it.
Best triggers
Activate for requests like:
- "users aren't coming back"
- "improve retention"
- "habit loop"
- "engagement is dropping"
Diagnosis workflow
- Define the user segment and key repeat behavior.
- Map current journey to the 4 Hook Model stages.
- Score each stage (strong, weak, missing).
- Identify the weakest link in the loop.
- Propose focused interventions by stage:
- Trigger: better timing, channel, relevance
- Action: fewer steps, lower friction, clearer CTA
- Reward: immediate and variable value, clear payoff
- Investment: save preferences, build history, personalize
- Estimate expected effect on retention (low, medium, high confidence).
- Recommend what to ship first.
Output format
Return:
- Current loop map
- Breakpoint analysis (where users drop)
- Top 3 interventions
- Success metrics to track (activation, repeat rate, D7/D30, session depth)
- Fast experiment plan (if needed)
Guardrails
- Focus on real user value, not manipulative mechanics.
- Keep interventions ethical and transparent.
- Avoid adding reminders if core reward is weak.
- Fix product value and friction before notification volume.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.