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 02-segment-analysisgit 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/02-segment-analysis)<a href="https://agentmods.dev/skills/thaolst/ai-growth-prompts/02-segment-analysis"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-prompts/02-segment-analysis/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/02-segment-analysis"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-prompts/02-segment-analysis.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 | $0.03032 |
| Opus 5 | $0.00000 | $0.01516 |
| Sonnet 5 | $0.00000 | $0.00606 |
| Haiku 4.5 | $0.00000 | $0.00303 |
Grade A, and why
02-segment-analysis 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 10d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
02 · Phân tích segment
Hiểu ai cần target và target thế nào - trong phạm vi kênh cho phép ở mỗi cấp độ campaign.
| Cấp độ | Dữ liệu có sẵn | Phân tích được |
|---|---|---|
| S | Cohort, RFM cơ bản | Phân khúc hành vi, chọn 1 nhóm |
| M | Thêm dữ liệu kênh paid | Multi-segment, phân bổ budget |
| L | Full data + research | Nghiên cứu định tính + định lượng |
Prompt 04 · Phân tích cohort drop để tìm điểm can thiệp
Khi nào dùng: Dữ liệu retention cho thấy drop-off nhưng chưa rõ nguyên nhân và cách xử lý.
Dữ liệu retention của một cohort loyalty:
[Paste dữ liệu - CSV, bảng, hoặc số liệu]
Ví dụ:
Tuần 0: 100%
Tuần 1: 68%
Tuần 2: 45%
Tuần 4: 38%
Tuần 8: 29%
Tuần 12: 22%
Cấp độ campaign có thể chạy: [S / M / L / XL]
Phân tích:
1. Điểm rớt mạnh nhất - user đang làm gì ở giai đoạn đó?
2. W0→W1 vs W1→W2 - cái nào đáng lo hơn và tại sao?
3. 3 giả thuyết hành vi cụ thể cho drop
4. Cho mỗi giả thuyết, một thử nghiệm phù hợp [S/M]:
- S: in-app mechanic hoặc owned channel test, 1–2 tuần
- M: có thể thêm kênh paid hoặc comm planning
5. Nếu chỉ can thiệp một việc trong tuần này: làm gì?
Prompt 05 · Phân khúc user để phân bổ ngân sách
Khi nào dùng: Đã có ngân sách (S hoặc M), cần phân bổ vào nhóm nào.
Cần ưu tiên segment nào để target.
Cấp độ: [S / M / L / XL]
Ngân sách: [ước lượng]
Kênh:
- S: in-app + owned out-app
- M: thêm [kênh paid cụ thể]
Dữ liệu mỗi user:
- Số dư điểm
- Ngày từ lần giao dịch cuối
- Số lần redeem voucher 30 ngày qua
- Danh mục voucher ưa thích
- [Khác nếu có]
Mục tiêu: [tăng MAU / kéo user lapsed / tăng tần suất]
Đề xuất:
1. 3–4 segment tối đa - đủ để thực thi với kênh hiện có
2. Mỗi segment: đặc điểm, % ngân sách, loại voucher phù hợp, lý do
3. Segment nào nên bỏ qua ở mức ngân sách này - và tại sao
4. Nếu chỉ target 1 segment: chọn ai và tại sao?
Prompt 06 · Tìm tín hiệu churn sớm để can thiệp
Khi nào dùng: Muốn can thiệp trước khi user ngừng hoạt động - ở cấp S, chỉ dùng owned channels và in-app mechanic.
What ships with it
2 files 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.
- 10d ago First seen · 324 lines · 0 tokens per session scan A c17bce4294bc
02-segment-analysis is a skill published in the GitHub repository thaolst/ai-growth-prompts (11 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,032 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…
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…
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…
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.
fintech-campaign-designer
Design full fintech campaigns from concept to execution — promotion strategy, mechanic, user journey, budget, and risk assessment. Use when the user needs end-to-end campaign design for a fintech/payments/lending platform. Specialized for SEA markets (Vietnam, Indonesia, Philippines, Thailand).
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…