In short:
ak-gamification-marketinghelps you pick game mechanics such as points, badges, leaderboards, streaks or challenges based on one useful behavior and evidence about that exact group of users. Then it builds the campaign, the implementation and the measurement. It always puts a no-game option next to it for comparison. It does not promise more revenue or better retention.
Disclosure: I maintain AgentKit and have an affiliate relationship with it: the AgentKit link in this post is an affiliate link; buying through it gets you 30% off.
Summary
Use it when you want customers to come back, refer friends or finish onboarding, and you need to choose game mechanics for a reason, along with the campaign, the implementation or the measurement. You do not need it if all you want is a promised number for revenue or retention: the skill does not make that promise.
flowchart LR
A["Marketing goal"] --> B["ak-gamification-marketing"]
B --> C["Chosen mechanics + guardrails"]
C --> D["Campaign: emails, weekly schedule"]
C --> E["Implementation: API, schema, rules"]
D --> F["Measure value and side effects"]
E --> F
F --> G["Analysis report"]Four things to get right:
| Concept | Question | Example |
|---|---|---|
| Useful behavior | What do users do that truly has value, and why is it hard for them? | Customers come back for a second purchase. It is hard because they forget the store after the first one. |
| Mechanics | Of the 10 core mechanics, which fits this behavior and these users? | The 10 mechanics are points, badges, leaderboards, levels, streaks, challenges, quests, unlockables, rewards and progress bars. Onboarding often uses progress bars, small badges, feature unlocks and drip emails. |
| Guardrails | What do you track to know the campaign does no harm? | Churn, fatigue and email unsubscribes, reward cost, fraud. Plus an opt-out and privacy requirements. |
| Falsifiable hypothesis | Which result shows this mechanic is not worth it? | The streak group does not buy again more than the group that only gets reminder emails. Then the simple no-game option wins. |
A goal alone is not enough reason to use streaks, public leaderboards, time pressure or random rewards. Octalysis, Self-Determination Theory, the Fogg model and player types are only lenses for design, not causal evidence.
Sample prompt for a loyalty program:
/ak-gamification-marketing Design a loyalty program for <online store name>.
Useful behavior: customers come back for a second purchase.
Why it is hard: <reason, for example customers forget the store after the first purchase>.
Evidence: <data or survey about these customers>.
Constraints: reward cost at most <budget>, customers can opt out.
Done when: there is a chosen mechanic, a no-game option to compare, and a way to measure.This skill has no flags. What you write after the command is free input: a mechanic (for example "streaks") or a campaign (for example "a refer-a-friend program").
Below is the detailed version: the run flow, 5 situations with prompts (loyalty program, refer-a-friend by email, new user onboarding, implementation design, measuring campaign results), how to write the input, the change history by ak release, and common pitfalls. The detailed version and the interactive page are for subscribers. Your agent can also search them through the portal's MCP.
Opens when your account has subscriber access
This guide is for subscribers
Once your account has access, the full piece, the interactive visual and the agent call all open.
- Sign in or create a modernEngineer accountReading access belongs to your account email.
- Choose a plan on the pricing page1, 3 or 12 months, paid by VietQR bank transfer. Access opens about a minute after the money arrives.
- Or redeem a Facebook subscriber codePeople supporting the page on Facebook get an activation code by message each month.
Already a subscriber? Sign in to read.
Use this piece in your agent
Get an API keyCopy the text below and paste it into Claude Code, Codex or whichever agent you use. The agent reads the piece and checks it against the repo you have open.
Read "ak-gamification-marketing: design gamification around a useful behavior" on modernEngineer and apply it to this repo.
1. Call the content_get tool of the modernengineer MCP server with locale "en", slug "ak-gamification-marketing". If the modernengineer MCP server is not connected, stop and walk me through connecting it from https://modernengineer.dev/en/mcp.
2. Summarize the main steps of the piece and point out which apply to this repo.
3. Propose concrete changes and ask me before editing any file.Connect MCP in Claude Code (once)
claude mcp add --transport http modernengineer \
https://api.modernengineer.dev/mcp \
--header "Authorization: Bearer <API key>"Reading the full piece over MCP needs an API key from a subscriber account or one that bought this guide. Without access, the agent only gets the opening.
- Version
- v1.0.0
- Updated
- 22/10/2026
- Licence
- All rights reserved
- Slug
- ak-gamification-marketing
