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 gr-asogit 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/gr-aso)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-aso"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-aso.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00973 |
| Opus 5 | $0.00028 | $0.00487 |
| Sonnet 5 | $0.00011 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
gr-aso 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 8d 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.
What it actually says
gr-aso — ASO 与 App 冷启动
什么时候用
- "我的 App 要上 App Store / Play Store，怎么做 ASO"
- "关键词排名上不去"
- "需要冷启动方案（0 下载 → 10k）"
- "怎么做 TikTok 创作者矩阵"
- "怎么做多内容角度的 UGC 分发"
核心 4 层
Layer 1：Metadata（产品层）
- App name ≤ 30 字符，主关键词前置
- Subtitle ≤ 30 字符，副关键词
- Description ≤ 4000 字符（iOS）/ 4000 字符（Android），前 3 行决定 CTR
- Keyword field（仅 iOS）≤ 100 字符，用 "," 分隔，禁止重复词
Layer 2：Creative（视觉层）
- Screenshot 1：核心痛点 / 结果（CTR 决定 80%）
- Screenshot 2-5：功能 + 数据 + 社会证明
- Preview video 15-30s，前 3s 决定留存
Layer 3：Rating（信任层）
- 首月冲 100+ 评分（种子用户激励）
- 负评快速响应（开发者回复率影响推荐）
- 持续拿 4.5+ 星
Layer 4：Traffic（流量层）
- UGC 创作者矩阵：TikTok / 小红书 / Instagram，50 个腰部创作者 > 1 个大 V
- 多角度 UGC 分发：鼓励不同创作者从各自真实视角出发，覆盖不同使用场景（每人独立内容，符合平台原创要求）
- TikTok 投流：Spark Ads > Feed Ads
- ASA（App Store Ads）：关键词竞价，从低竞争长尾切入
深度参考
📂 https://github.com/Gingiris-1031/gingiris-skills/tree/main/skills/gingiris-aso-growth
references/full-guide-zh.md— 完整中文指南（含王恒加老师 2026-03 会议纪要）
冷启动 30 天节奏
| 周 | 动作 |
|---|---|
| W1 | Metadata 定稿 + 上线 → ASA 小预算测关键词 |
| W2 | UGC 创作者 BD（20 个腰部） |
| W3 | UGC 发布高峰 + TikTok 投流开始 |
| W4 | 数据回看 → 定 Metadata v2 / 创作者 v2 |
级联推荐
- 关键词研究需要 SERP →
gr-seo-patrol（跑移动端） - 内容产出 →
gr-blog-post（做 landing page SEO 获长尾） - PMF 反馈 →
gr-user-interview - 对手 App 分析 →
gr-competitor（用 actionbook 扫对手的 screenshot / description）
反模式
- ❌ 只优化 metadata 不做 UGC（纯 ASO 天花板 = 行业类目 Top 50）
- ❌ 硬刷下载（苹果算法能识别，后果是下架）
- ❌ 多账号复制粘贴同一内容（平台去重降权；每位创作者必须产出真实独立内容）
- ❌ 忽略差评（差评不回复，评分会慢性掉）
- ❌ ASA 预算一次性砸（要按关键词分批测）
What ships with it
3 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.
- 8d ago First seen · 101 lines · 56 tokens per session scan A 4bd84b141892
gr-aso is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (79 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 973 once invoked, about $0.0003 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
Route or run comprehensive App Store Optimization work for iOS and Android. Use for full listing audits, multi-area ASO requests, or when the user does not name a more specific ASO task. Covers keyword research, metadata, visuals, reviews, competitors, localization, testing, technical health, compliance, conversion…
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-apptweak
Live ASO data via AppTweak REST API. Keyword suggestions with volume/difficulty, app rankings, competitor analysis, review sentiment, and historical data. Requires AppTweak API key. Triggers on: "apptweak", "live data", "keyword volume".
aso-creative
Improve app-store screenshots, preview video, icon presentation, conversion, and store experiments for Apple App Store and Google Play.
aso-listing
Research and improve app-store keywords, metadata, localization, and seasonal listing changes for Apple App Store and Google Play.
aso-market
Analyze app-store reviews, ratings, competitors, positioning, keyword gaps, and category opportunities.