Growth Lab is an open-source growth system that uses coding agents to understand a product, research markets, execute growth activities, and learn from the results. It is designed for teams that want to manage growth work across channels such as SEO and Xiaohongshu through natural-language collaboration, persistent product context, and recorded outcomes. Catalogue add-ons define parts of its product models, research methods, execution workflows, and agent operation.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tsingyuai/growth-labnpx agentmods add skills/tsingyuai/growth-lab/review-seo-performanceWrote 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/tsingyuai/growth-lab/review-seo-performance)<a href="https://agentmods.dev/skills/tsingyuai/growth-lab/review-seo-performance"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/review-seo-performance/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/tsingyuai/growth-lab/review-seo-performance"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/review-seo-performance.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 | $0.00085 | $0.01203 |
| Opus 5 | $0.00043 | $0.00602 |
| Sonnet 5 | $0.00017 | $0.00241 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
review-seo-performance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
复盘 SEO 与 AI 可见性
用可比较周期和页面原始目标复盘已发布页面。考虑上线日期、季节性、抓取与收录延迟，把证据与解释分开。
收集传统搜索证据
node collectors/bing-webmaster/bing-webmaster.mjs page-stats \
--site "$SITE_URL" --out <page-stats-file>
node collectors/bing-webmaster/bing-webmaster.mjs page-query-stats \
--site "$SITE_URL" --page "$PAGE_URL" --out <query-stats-file>
node collectors/bing-webmaster/bing-webmaster.mjs url-info \
--site "$SITE_URL" --url "$PAGE_URL"
读取：
- 抓取与索引状态；
- 展现、查询、点击和点击率；
- 平均展现位置与点击位置；
- 页面或摘要更新前后的变化；
- 产品动作、激活、收入或当前产品真正关心的结果；
- 相关 Memory 中的基线和历史行动。
收集 Bing AI Performance
Bing Webmaster Tools 的 AI Performance 主要通过网页界面提供。使用已登录浏览器读取：
| 指标 | 含义 |
|---|---|
| Total Citations | 页面内容在 AI 答案中作为来源出现的总次数 |
| Cited Pages | 被 AI 当作来源的页面数量与时间变化 |
| Page-level citations | 具体 URL 的被引用次数 |
| Grounding Queries | AI 为寻找引用材料实际运行的检索短语 |
Grounding queries 与传统人类关键词不同。用户的一句话会被模型拆成多个查询，这就是 query fan-out。程序化查询常出现比较、评估、监控、标准、优缺点等结构，它们可以揭示传统关键词工具看不到的内容需求。
AI Performance 的产品状态和字段可能变化，grounding queries 没有稳定 API 时以 Bing Webmaster Tools 当前网页界面为准。只报告界面实际提供的数据，不把推测的合作方覆盖范围写成官方承诺。
用 Grounding queries 反推内容
- 聚合重复出现的概念、对象、比较维度和任务。
- 区分自然查询与程序化查询。
- 找出频繁触发检索但当前页面引用弱或没有覆盖的概念。
- 判断它应成为现有页面的新段落、比较表、FAQ、独立页面还是不值得处理的旁支。
- 回到实时 SERP 和产品能力验证，不因 AI 查询出现就自动创建页面。
检查可提取性
- 高频 grounding 术语是否出现在对应 H2 与前一到两段；
- 结论是否前置，段落能否独立理解；
- 表格、FAQ、步骤和定义是否便于准确抽取；
- 数据、示例和来源是否足以支撑引用；
- 页面是否有作者、更新时间和相邻主题覆盖；
- schema.org、canonical、robots、sitemap 与 IndexNow 是否正确。
- 站点需要面向 LLM 提供内容导航时，检查
llms.txt是否准确、可访问并只声明真实公开内容；不要把它当成收录或引用保证。
三层验证
- 服务器日志：区分 BingBot、OAI-SearchBot 等机器访问和真实用户访问。
- 查询模式：比较传统搜索查询与 AI Performance 的程序化 grounding queries。
- 产品结果：把引用和搜索可见性与分析工具中的来源、访问和产品动作对照。
引用多、点击少不等于失败，也不等于成功。它表示内容被 AI 使用但没有形成等量访问，需要结合品牌呈现、用户后续动作和产品目标判断。
诊断主要约束
- 发现：目标 canonical 尚未被抓取或收录。
- 需求：目标词族没有足够可观察需求。
- 排名：有展现但位置弱。
- 摘要：位置有竞争力但点击率弱。
- 意图：实际到达查询与页面任务偏离。
- 内容：竞品提供更强证据、工具、信息增益、新鲜度或清晰度。
- 转化：页面满足搜索意图但没有带来相应产品行动。
- 有引用无访问：AI 系统使用内容，但用户很少继续访问或识别品牌。
输出复盘
需要视觉比较时，在当前 Model 的 Memory 生成独立 HTML，包含适合当前证据的周期比较、查询表、位置分布、产品结果、AI 引用、grounding query 分类和标注结论。原始导出放在同一 Memory 下。
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 · 98 lines · 85 tokens per session scan A a61cffc5e74b
review-seo-performance is a skill published in the GitHub repository tsingyuai/growth-lab (2,000 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,203 once invoked, about $0.0004 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
synthesis-explore
Synthesis EXPLORE stage for the Diffmode growth-tactics pipeline (fuses the blind-combination draw + emergent-mechanism derivation — formerly two separate synthesis steps — into ONE structural-check-only stage). Reads the per-run growth-factors.json (LIGHT vector DB) + synthesis-constraints.json + founder-input +…
diagnostics-intake
Fast founder-input capture for the Diffmode growth-tactics pipeline (the diagnostics stage). Produces WS/01-diagnostics/founder-input.md in the exact schema the enrichment + synthesis stages read. Two modes — (A) URL mode researches a product's website (homepage/pricing/about) plus a web-research pass to prefill the…
growth-factors-mining
Builds a per-run LIGHT growth-vector database for the Diffmode growth-tactics pipeline by mining public growth case studies fresh, every run, and distilling each into atomic "growth factors" (transferable mechanisms). Clean-room — NEVER reads the proprietary tacticsDB. Outputs growth-factors.json (20-40 vectors spread…
lite-constraints
Generates synthesis-constraints.json for the Diffmode growth-tactics pipeline by reasoning in-context over the per-run growth-factors.json (LIGHT vector DB) + founder context — the clean-room, no-Python replacement for the proprietary Python constraints generator. Emits the white-space pairs, mandatory…
viral-marketing-playbook
Design viral loops into your product — referral programs, invite systems, and share mechanics that drive exponential growth. Includes K-factor calculations and real examples from Dropbox, Slack, and Notion. By @WeiYipei.
cro-optimization
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze…