/SKILL.md
# Hooked: Building Habit-Forming Products Based on Nir Eyal's "Hooked" framework. Use this when designing features, onboarding flows, engagement loops, gamification, notifications, or any product decision where user retention and repeat engagement matter. ## Core Principle The best product doesn't win. The product that captures the **monopoly of the mind** wins — the thing users turn to first with little or no conscious thought. Engagement is as important, if not MORE important, than growth.
npx skillsauth add saubade32/product-management-skill product-management-skillInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Based on Nir Eyal's "Hooked" framework. Use this when designing features, onboarding flows, engagement loops, gamification, notifications, or any product decision where user retention and repeat engagement matter.
The best product doesn't win. The product that captures the monopoly of the mind wins — the thing users turn to first with little or no conscious thought.
Engagement is as important, if not MORE important, than growth. If you can't retain users and keep them coming back, you've got nothing.
Every habit-forming product embeds a hook — a 4-step cycle that runs repeatedly:
Trigger → Action → Variable Reward → Investment
↑ |
└──────────────────────────────────────┘
Two types:
External Triggers — things in the environment telling the user what to do next:
Internal Triggers — the critical piece most teams miss:
Key question to answer: What is your product's internal trigger? What is the frequently occurring itch your product addresses? If your team can't answer this, you have a problem.
Frequency rule: The habit you want to create MUST occur within a week's time or less. More frequent = better. Products like Facebook, Slack, Instagram are used multiple times daily (people check home screens ~150 times/day). If the behavior doesn't occur at least weekly, it's almost impossible to form a habit.
The action is the simplest behavior done in anticipation of a reward — the easiest thing the user can do to scratch that itch.
BJ Fogg's Behavior Model: For any behavior to occur, you need 3 things simultaneously:
Critical insight: 90% of the time, teams focus on increasing motivation (videos, testimonials, persuasion). This is usually the WRONG approach. The better ROI is to increase ability — make the behavior easier.
6 Factors of Ability (reduce any of these to make behavior more likely):
It's NOT enough to just give people what they want. You must give them what they want AND leave them wanting more. This is done through variable rewards.
Based on BF Skinner's operant conditioning: pigeons pecked at a disc more when rewards came on a variable (unpredictable) schedule vs. fixed schedule. Variability spikes the reward system in the brain and creates a wanting/desirous response.
Three types of variable rewards:
a) Rewards of the Tribe — feel good, come from other people, have uncertainty:
b) Rewards of the Hunt — primal search for resources/information:
c) Rewards of the Self — intrinsically pleasurable, not from others or material:
The most overlooked step. The user puts something into the product in anticipation of a future benefit (not immediate gratification).
Purpose: Increase the likelihood of the next pass through the hook.
Two mechanisms:
a) Loading the next trigger:
b) Storing value:
When building any feature requiring unprompted engagement, answer:
When designing Harbor features, evaluate against the hook model:
| Hook Step | Harbor Application | |---|---| | Internal Trigger | Uncertainty about content strategy, fear of falling behind competitors, pressure to publish consistently | | External Trigger | Lifecycle emails, dashboard notifications, weekly recap emails, getting started tasks | | Action | One-click discovery, generate article, scroll idea feed — keep these as simple as possible | | Variable Reward | Discovery results (hunt — what topics will surface?), article quality (self — mastery of content), community/social proof (tribe) | | Investment | Sites added, presets configured, articles generated, discovery history — all make Harbor more valuable over time and harder to leave |
Before shipping any engagement feature, ask:
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.