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 Gingiris-1031/gingiris-skills --skill gingiris-aso-growthgit clone --depth 1 https://github.com/Gingiris-1031/gingiris-skillsWrote 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/gingiris-1031/gingiris-skills/gingiris-aso-growth)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gingiris-aso-growth"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gingiris-aso-growth/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/gingiris-1031/gingiris-skills/gingiris-aso-growth"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gingiris-aso-growth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00320 | $0.02530 |
| Opus 5 | $0.00160 | $0.01265 |
| Sonnet 5 | $0.00064 | $0.00506 |
| Haiku 4.5 | $0.00032 | $0.00253 |
Grade A, and why
gingiris-aso-growth 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASO 增长与 App 冷启动权威指南
中文版
整理自：王恒加老师 ASO 学习会议纪要（2026年3月） 补充资料：行业公开研究与最佳实践
核心框架
本指南覆盖 App 增长的完整周期：
| 模块 | 核心内容 |
|---|---|
| ASO 基础 | 商店页面优化、关键词研究、评分优化、排行榜规则 |
| 冷启动策略 | Organic First 原则、渠道矩阵、App vs Web 差异 |
| UGC 运营 | 创作者寻找与筛选、定价与激励、管理架构 |
| 多平台内容 | TikTok/Instagram/YouTube Shorts 差异与策略 |
| AI 辅助内容创作 | AI 视频制作、账号健康维护、多版本测试策略（需遵守应用商店政策） |
| 平台对比 | App Store vs Google Play 算法规则差异 |
ASO 核心工具
| 工具 | 定价 | 特点 |
|---|---|---|
| Astro | ~$80-90/年 | 界面友好，适合独立开发者 |
| 点点数据 | 按需 | 国内工具，全球数据，功能强大 |
| AppTweak | 按需 | AI 智能洞察，专业级 |
| AppFollow | 按需 | 评论管理 + 关键词研究 |
先建立取证基线
执行任何 ASO 改版前，按国家/地区和流量来源导出最近 28 天数据：曝光、产品页浏览、首次下载、转化率、收入，以及 D1/D7/D30 留存。建立变更日志，记录商店版本、发布时间、关键词排名、素材版本和同期付费投放。
一次有效的 ASO 复盘至少要回答四个问题：
- 关键词排名或搜索曝光是否变化？
- 曝光 → 产品页浏览率是否变化？
- 产品页浏览 → 首次下载率是否变化？
- D7/D30 留存、评分质量或收入是否恶化？
只看到下载上涨，不能归因于 ASO；还需排除付费投放、被推荐、版本发布和季节性。当前 Gingiris 素材库尚无包含上述完整口径的 App Store 前后对照案例，因此本 skill 提供执行框架，不承诺固定提升幅度。
Apple Notes 原始学习记录补充
2026-03-07 的《ASO 学习 0307》支持以下执行顺序：从用户搜索意图出发，比较搜索需求、难度、竞品覆盖和地区差异；有足够流量后再对商店素材做 A/B 测试；冷启动先由创始人亲自验证 Organic Winning Format，再交给 UGC 创作者复制，最后放大已验证素材。
原笔记是学习记录，不是受控增长实验。完整的证据与合规边界见 references/apple-notes-field-evidence.md。
合规红线
- 不购买评分、评论、搜索量、下载或榜单位置；
- 不使用设备农场、批量账号或网络伪装规避平台审核；
- 不使用马甲包绕过下架或执法；
- 评分只向真实用户请求，不筛选或诱导正面评价；
- 使用官方 PPO / Store Listing Experiments 和透明投放进行测试。
冷启动核心原则：Organic First
第一步：创始人亲自下场
- 自己运营社交媒体账号
- 亲自测试各种内容形式
- 找到能持续产生爆款的"Winning Format"
第二步：复制成功模板
- 将 Winning Format 交给 UGC 创作者
- 建立管理流程（合同、付款、数据看板）
第三步：付费投流放大
- 将表现最好的有机内容作为广告素材
- Meta 广告（Facebook + Instagram）是首选
三大短视频平台对比
| 平台 | 用户年龄 | 付费转化率 | 核心指标 |
|---|---|---|---|
| TikTok | 13-18岁 | 最低 | 完播率、分享率 |
| 18-25岁 | 中等 | Share Rate、Like Rate | |
| YouTube Shorts | 25-35岁 | 最高 | 前3秒停留率、完播率 |
What ships with it
13 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.
- .gitattributes 2.4 KB
- .github/FUNDING.yml 60 B
- .github/star_milestone.txt 1 B
- assets/logo-wall.jpg 131 B
- assets/logo.png 130 B
- assets/star.png 130 B
- LICENSE 1.0 KB
- README.md 18 KB
- references/apple-notes-field-evidence.md 2.1 KB
- references/aso-tools.md 2.6 KB
- references/full-guide-zh.md 5.5 KB
- references/platform-algorithms.md 3.3 KB
- references/ugc-management.md 3.1 KB
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 · 215 lines · 320 tokens per session scan A 0d7c13b97daa
gingiris-aso-growth is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (79 stars, last pushed 6d ago), licensed MIT. It adds 320 tokens to every session and 2,530 once invoked, about $0.0016 per session on Opus 5. 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
aso-asc
Apple App Store Connect API integration. Fetch iOS app metadata, reviews, ratings, and version info directly from App Store Connect. Requires API key. Triggers on: "app store connect", "asc".
aso-atlas
App Store Optimization with ASO Atlas. Use for App Store keyword research (popularity, difficulty, who ranks), tracking an iOS app's keyword rankings per storefront, competitor keyword gaps, metadata (title, subtitle, keyword field) drafts, and questions like "how is my app doing" answered from App Store Connect data.…
gingiris-aso-growth
A guide to app-store optimization, or improving an app's App Store and Google Play listing so more people can find and install it.
appshot-images
Generate App Store and Google Play screenshot designs. Use when the user wants to create store listing images, screenshot mockups, or promotional graphics for a mobile app. Builds on appshot-core foundation.
appshot-videos
Generate App Store / Google Play preview videos using Remotion. Scans the target app's codebase, proposes custom scenes, and writes bespoke .tsx scene files using shared animation primitives. Mobile apps only (iOS/Android). Use when the user wants to create a demo video, app preview, promo video, or marketing video…
ipaship-audit
Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.