Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add thaolst/ai-growth-prompts --skill 06-retention-strategygit clone --depth 1 https://github.com/thaolst/ai-growth-promptsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thaolst/ai-growth-prompts/06-retention-strategy)<a href="https://agentmods.dev/skills/thaolst/ai-growth-prompts/06-retention-strategy"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-prompts/06-retention-strategy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thaolst/ai-growth-prompts/06-retention-strategy"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-prompts/06-retention-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.04423 |
| Opus 5 | $0.00000 | $0.02211 |
| Sonnet 5 | $0.00000 | $0.00885 |
| Haiku 4.5 | $0.00000 | $0.00442 |
Grade A, and why
06-retention-strategy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
06 · Retention & loyalty strategy
Retention không phải là nhắc user quay lại. Là xây hệ thống để user tự muốn quay lại. Ở cấp S, retention dựa vào timing và ưu đãi đơn giản. Ở cấp M, có thể thêm layer gamification và segment-specific mechanic. Ở cấp L, xây loyalty program riêng.
| Cấp độ | Chiến thuật khả thi | Ràng buộc |
|---|---|---|
| S | Trigger theo hành vi, voucher tái kích hoạt | In-app + owned out-app, không paid |
| M | Loyalty tier, streak mechanic, segment-specific comm | Có paid hỗ trợ kéo về, dev sprint giới hạn |
| L | Full loyalty program, Xu economy, VIP layer | Nhiều tháng dev, research, cross-functional team |
Prompt 11 · Thiết kế retention loop cho campaign
Khi nào dùng: Đang thiết kế campaign và muốn có cơ chế giữ chân user ngay từ đầu, không phải chờ đến lúc họ rời đi mới can thiệp.
Retention loop cần được thiết kế ngay trong campaign,
không phải sau khi user drop off.
Cấp độ: [S / M / L / XL]
Loại campaign: [voucher drop / game / event / loyalty program / khác]
Ngân sách ước lượng: [số tiền hoặc phạm vi]
Bối cảnh:
- Mục tiêu của campaign: [tăng frequency / kích hoạt user mới / cross-sell]
- Kênh chính: [in-app push / SMS / email / paid social / in-app banner]
- User target: [new / active 30 ngày gần / lapsed >60 ngày / vip]
- Độ dài campaign dự kiến: [số ngày hoặc tuần]
Thiết kế retention loop với 3 phase:
**Phase 1 - Kick-off (Ngày 1-3)**
- User thấy gì và làm gì trong 3 ngày đầu?
- Điều gì đưa họ quay lại lần 2?
- KPI phase này: [tỉ lệ quay lại ngày 3]
**Phase 2 - Engagement (Ngày 4-14)**
- Cơ chế nào khiến user tương tác nhiều hơn 1 lần/tuần?
- Cần trigger gì (và trigger tự động được không)?
- Với [S]: chỉ in-app push + timing thông minh
- Với [M]: thêm trigger qua paid kênh nếu chi phí cho phép
- KPI phase này: [số phiên / user / tuần]
**Phase 3 - Sustain (Ngày 15+)**
- Khi nào user tự nhiên quay lại mà không cần nhắc?
- Điểm nào có thể chuyển họ từ "campaign participant" thành "habitual user"?
- Tỉ lệ giữ chân kỳ vọng ở ngày 30: [số % MAU của cohort]
Yêu cầu output:
1. Retention loop diagram (mô tả bằng text, dùng ASCII nếu cần)
2. 3 điểm quyết định quan trọng nhất trong loop
3. Cách đo mỗi phase — metric nào, dashboard nào
4. Risk: nếu loop không hoạt động, điểm fail đầu tiên là gì
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 414 lines · 0 tokens per session scan A 56a7e4c75702
06-retention-strategy is a skill published in the GitHub repository thaolst/ai-growth-prompts (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,423 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
multi-agent-workflow
Run a two-stage research then planning workflow for growth campaigns. Use when the user wants to analyze past campaign data AND create a new plan based on that analysis in one connected workflow. Stage 1: analyze data and extract structured insights. Stage 2: use insights to build a campaign plan. Input: past campaign…
campaign-brief
Write a complete campaign brief for growth marketing campaigns. Use when the user needs to create a campaign brief, plan a promotion, design a voucher campaign, or structure a marketing campaign. Works for fintech, e-commerce, super apps, and mobile payment platforms. Input: target segment, objective, budget, mechanic…
ab-test-analyzer
Analyze A/B test results and recommend next actions. Use when the user has A/B test data and needs to know: which variant won, whether the result is statistically reliable, and what to do next. Works for conversion rate tests, copy tests, mechanic tests, UI tests. Input: user counts and conversions for control and…
agent-pre-deploy-review
Review an AI agent prompt and setup before deploying it in real work. Use when the user has built or customized an agent and wants a thorough review before depending on it for real campaign work. Input: agent description, system prompt, example input, example output. Output: prompt weaknesses, edge cases, improvement…
campaign-planning
Build a monthly or quarterly campaign plan from a growth target. Use when the user has a target (MEU, transactions, revenue, retention) and needs a full campaign plan: how many campaigns, what type, in what order, with what budget. Higher-level than campaign-brief (which covers a single campaign in detail). Input…
churn-intervention
Design churn prevention and winback campaigns for fintech and super apps. Use when the user needs to reduce churn, design save offers, create cancellation flows, plan re-engagement campaigns, or analyze churn reasons. Supports both proactive (predictive) and reactive (post-churn) strategies.