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
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 tsingyuai/growth-lab --skill onboard-growth-labgit clone --depth 1 https://github.com/tsingyuai/growth-labWrote 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/onboard-growth-lab)<a href="https://agentmods.dev/skills/tsingyuai/growth-lab/onboard-growth-lab"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/onboard-growth-lab/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/onboard-growth-lab"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/onboard-growth-lab.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 | $0.00102 | $0.02154 |
| Opus 5 | $0.00051 | $0.01077 |
| Sonnet 5 | $0.00020 | $0.00431 |
| Haiku 4.5 | $0.00010 | $0.00215 |
Grade A, and why
onboard-growth-lab scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. 只要启用任一 MediaCrawler 平台，必须先完成不可绕过的 Chrome CDP onboarding：Chrome 版本至少 144；为 MediaCrawler 启动一个使用仓库外持久化 profile 的专用 Chrome 实例，同时显式传入 `--remote-debugging-port=<port>` 和 `--user-data-dir=<profile-dir>`；`curl --noproxy '*' h How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Growth Lab 统一 onboarding
这是整个系统唯一的 onboarding 入口。不要要求各业务 Skill 各自重复审计，也不要创建页面、注册全局 command 或维护配置状态机。
工作方式
- 完整读取 依赖清单。
- 先运行
python models/onboard-growth-lab/scripts/check_configuration.py，再只读检查当前机器、已声明的第三方 Client 和认证 profile。脚本与回复都不得输出 secret、cookie、token 或认证文件内容。 - 向用户给出一张统一状态表：
已就绪、缺失、可选、本轮绕过。 - 用自然语言询问用户要启用哪些缺失能力、哪些本轮绕过。不要替用户安装所有可选项。
- 对用户选择启用的项目逐项处理：
- API key：解释用途、官方获取入口、变量名和
CONFIGURATION.md中的本地配置步骤。默认请用户在.env.local或系统密钥管理器中自行配置；只有用户明确授权写入时才可修改.env.local，且永不回显完整值。 - 第三方 CLI/Client：必须有用户可直接访问的官方来源和安装方式；说明来源、许可证、安装位置与命令，用户确认后安装并检查版本。
- 登录认证：启动上游或业务 Skill 已定义的原生交互流程，让用户本人扫码、OAuth 或输入验证码；认证材料不得进入仓库或 Memory。
- API key：解释用途、官方获取入口、变量名和
- 每完成一项就重新执行对应的只读检查。结束时再次输出统一状态表和本轮绕过项。
小红书 browser-first 就绪门禁
小红书不再经过 MediaCrawler。需要小红书采集时，按 xiaohongshu-mcp 独立检查：
- 告诉用户首次默认采集 25 条，数量可调整，但建议 25 条。
- 检查
XHS_MCP_ENDPOINT、XHS_MCP_BINARY、XHS_MCP_LOGIN_BINARY和仓库外XHS_MCP_COOKIES_PATH，不读取或输出登录态内容。 - 缺少配置时显示
CONFIGURATION.md的准确位置、需要填写的字段及用途，然后停下等待用户配置或选择本轮绕过。 - 服务未运行时先说明将启动本机只读服务；登录缺失时说明授权边界并在用户确认后打开可见二维码登录窗口。
- 只有本机 health check、登录状态和一次低频最小读取全部成功，才报告
已就绪，可立即抓取。遇到风控、验证、超时或空响应立即停止，不自动重试或规避平台控制。
小红书登录只授权读取公开研究证据，不授权点赞、收藏、评论、关注、上传或发布。
MediaCrawler 风险确认与就绪门禁
MediaCrawler 的安装、登录和实际抓取必须在本统一 onboarding 中完成，不得把“已安装”或“有 profile”报告为可用。
- 在启动 Chrome、二维码登录或任何真实抓取前，通过 Agent 对话原意告知：
- 自动化抓取可能触发平台风控，导致限流、验证、登录失效或封号。
- 不要使用正式账号、主账号或承载重要资产的账号；使用者应准备可损失的专用账号。
- 账号被封后，部分公开内容在不需要该账号的路径上仍可能采集，但不保证持续可用，也不得尝试绕过平台风控。
- 请用户明确回复类似“我已了解封号风险，并确认使用非正式、可损失的专用账号”。沉默、模糊回复或仅要求“继续”不构成确认。未取得确认就停在风险门禁，不启动登录和抓取。
- 确认后，让用户选择需要启用的平台：抖音、快手、B 站、微博、贴吧、知乎。小红书使用独立的 browser-first 就绪门禁。未启用的平台必须由用户明确说“本轮绕过”，不得默认忽略。
- 只要启用任一 MediaCrawler 平台，必须先完成不可绕过的 Chrome CDP onboarding：Chrome 版本至少 144；为 MediaCrawler 启动一个使用仓库外持久化 profile 的专用 Chrome 实例，同时显式传入
--remote-debugging-port=<port>和--user-data-dir=<profile-dir>；curl --noproxy '*' http://127.0.0.1:<port>/json/version必须返回可解析的 Chrome DevTools JSON；MediaCrawler 配置为ENABLE_CDP_MODE = True、CDP_CONNECT_EXISTING = True且CDP_DEBUG_PORT = <port>。Chrome 144+ 在chrome://inspect/#remote-debugging中的 GUI auto-connect 服务不提供 MediaCrawler 所需的/json/version，不得把“Server running”字样单独当成通过。任一项失败就报告CDP 未就绪并停止，不得回退到标准 Playwright、临时干净浏览器或 Cookie 注入。CDP 不允许本轮绕过；用户只能绕过整个 MediaCrawler 能力或某个平台。 - 对每个启用平台依次执行 MediaCrawler operations 的登录就绪检查。必须同时满足：CDP 连接已验证、页面显示已登录、最小真实读取成功、产出非空且无登录/风控信号。
- 只有上述四项全部通过才报告该平台为
已就绪，可立即抓取。其他状态使用CDP 未就绪、待登录、验证失败、触发风控或本轮绕过；不维护额外状态文件。
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.
- 13d ago First seen · 79 lines · 102 tokens per session scan A 0ba362a6dd5a
onboard-growth-lab is a skill published in the GitHub repository tsingyuai/growth-lab (1,998 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 102 tokens to every session and 2,154 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…