tsingyuai/growth-lab

An open-source end-to-end growth tool that understands the product, connects to information sources, researches the market, executes growth actions, and improves itself based on real data.

About the project

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.

This repository also configures its own agents. See what growth-lab tells them →

2.0kStars on the repository
23Mods indexed here, across every type
22d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

tsingyuai/growth-lab

Skill Codex

Collect Bilibili video and creator evidence with MediaCrawler through search, exact BV detail, comments, dynamics, contacts, and optional media. Use for topic, format, title, creator, or audience research with explicit time-range and quality controls.

not rated 2.0k +3 22d ago A SkillSpector: pass 56 tokens original Apache-2.0

tsingyuai/growth-lab

Skill Codex

Collect Douyin competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, hook, format, audience-language, or creator research that needs reproducible raw evidence and a documented selection method.

not rated 2.0k +3 22d ago A SkillSpector: pass 57 tokens original Apache-2.0

tsingyuai/growth-lab

Skill Codex

Collect Kuaishou competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, format, audience-language, or creator research requiring reproducible source records and explicit collection limits.

not rated 2.0k +3 22d ago A SkillSpector: pass 56 tokens original Apache-2.0

media-crawler-tieba

04

tsingyuai/growth-lab

Skill Codex

Collect Baidu Tieba thread and user evidence with MediaCrawler using keyword or bar discovery, exact thread detail, replies, and creator pages. Use for community pain-point, vocabulary, objection, topic, or user research with thread-context preservation.

not rated 2.0k +3 22d ago A SkillSpector: pass 55 tokens original Apache-2.0

media-crawler-weibo

05

tsingyuai/growth-lab

Skill Codex

Collect Weibo posts and creator evidence with MediaCrawler using search, exact post IDs, comments, optional media, and creator IDs. Use for discourse, trend, messaging, audience-language, or account research requiring preserved provenance and risk-aware detail enrichment.

not rated 2.0k +3 22d ago A SkillSpector: pass 55 tokens original Apache-2.0

media-crawler-zhihu

06

tsingyuai/growth-lab

Skill Codex

Collect Zhihu answers, articles, videos, comments, and creator evidence with MediaCrawler through search and exact URLs. Use for expert discourse, problem framing, objections, terminology, topic, or creator research where content type and question context must remain explicit.

not rated 2.0k +3 22d ago A SkillSpector: pass 57 tokens original Apache-2.0

media-crawler

07

tsingyuai/growth-lab

Skill Codex

Install, authenticate, configure, operate, and troubleshoot the external MediaCrawler client shared by Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu collectors. Xiaohongshu uses the separate browser-first xiaohongshu-mcp Collector. Use when auditing this client, onboarding a supported platform account, selecting…

not rated 2.0k +3 22d ago A SkillSpector: pass 94 tokens original Apache-2.0

research-product

08

tsingyuai/growth-lab

Skill Codex

A research workflow for gradually learning what a product is, based on code, documentation, real pages, data, and user statements. It records confirmed facts separately from interpretations, assumptions, and unknowns.

not rated 2.0k +3 22d ago A SkillSpector: pass 100 tokens original Apache-2.0

research-seo-demand

09

tsingyuai/growth-lab

Skill Codex needs its repo

A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.

not rated 2.0k +3 22d ago A SkillSpector: pass 102 tokens original Apache-2.0

xiaohongshu-mcp

10

tsingyuai/growth-lab

Skill Codex

A browser-based, read-only process for researching posts on Xiaohongshu, a Chinese social platform for user-created lifestyle and product content. It can collect search results, candidate cover images, selected post details, and sanitized evidence.

not rated 2.0k +3 22d ago A SkillSpector: pass 78 tokens original Apache-2.0

create-seo-page

11

tsingyuai/growth-lab

Skill Codex

A Chinese-language workflow for creating and implementing search-focused pages in an existing product repository. SEO means improving a page so it can be found and understood through search engines.

not rated 2.0k +3 22d ago A SkillSpector: pass 93 tokens original Apache-2.0

generate-image

12

tsingyuai/growth-lab

Skill Codex

Generate, edit, or batch-create SEO, marketing, social, and document images with Gemini or OpenAI through the repository-owned Growth Lab image client. Use when a page or content loop needs illustrations, diagrams, covers, reference-image edits, multiple candidates, or verified image text and composition. This is the…

not rated 2.0k +3 changed 22d ago A SkillSpector: warn 73 tokens original Apache-2.0

review-seo-page

13

tsingyuai/growth-lab

Skill Codex

A Chinese-language review process for checking and revising search-engine-optimized pages. SEO means improving a page so it matches what people search for and can be understood by search engines.

not rated 2.0k +3 22d ago A SkillSpector: pass 104 tokens original Apache-2.0

tsingyuai/growth-lab

Skill Codex needs its repo

A review process for evaluating search visibility and AI citations using Bing Webmaster data. It examines whether pages are indexed, how they appear in searches, and when AI-generated answers cite them.

not rated 2.0k +3 22d ago A SkillSpector: pass 85 tokens original Apache-2.0

screenshot-assets

15

tsingyuai/growth-lab

Skill Codex

Capture authenticated product screenshots through the repository-owned Playwright CDP script and archive them in the invoking loop's Memory. Use when content needs truthful UI evidence, reusable product screenshots, a selected component, or a full-page browser capture. Requires only user-installed uv and Chrome…

not rated 2.0k +3 22d ago A SkillSpector: pass 77 tokens original Apache-2.0

xhs-render-cards

16

tsingyuai/growth-lab

Skill Codex

A production guide for turning approved Xiaohongshu drafts into reviewable image cards. Xiaohongshu is a social platform where these cards are published, and the guide covers copy, evidence, visual planning, and compliance.

not rated 2.0k +3 22d ago A SkillSpector: pass 89 tokens original Apache-2.0

onboard-growth-lab

17

tsingyuai/growth-lab

Skill Claude CodeCodex

A setup guide for Growth Lab, a system that combines several capabilities and external tools. It checks required keys, command-line tools, browsers, and sign-ins.

not rated 2.0k +3 22d ago A SkillSpector: pass 102 tokens original Apache-2.0

run-seo-page-loop

18

tsingyuai/growth-lab

Skill Codex

Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review. Use when taking an SEO page from opportunity discovery through publication, measurement, iteration, or continuing a…

not rated 2.0k +3 22d ago A SkillSpector: pass 65 tokens original Apache-2.0

xhs-replicate

19

tsingyuai/growth-lab

Skill Codex

A Xiaohongshu content workflow for researching ideas, adapting the structure of popular posts, adding verified product information, creating images, checking compliance, and reviewing results after publishing. Xiaohongshu is a social platform where people share lifestyle and product content.

not rated 2.0k +3 22d ago A SkillSpector: pass 82 tokens original Apache-2.0

tsingyuai/growth-lab

Skill Codex needs its repo

A writing workflow for producing long articles for WeChat Official Accounts, a Chinese article-publishing platform. It prepares the topic and outline, creates the article files and metadata, and performs content and compliance checks, but does not publish the article.

not rated 2.0k +3 22d ago A 81 tokens original Apache-2.0

wechat-mp-publish

21

tsingyuai/growth-lab

Skill Codex

A tool for turning a prepared article into WeChat-formatted HTML, previewing it, uploading its images, and creating or publishing a WeChat Official Account draft through the official API. The API is the standard interface programs use to communicate with a service.

not rated 2.0k +3 22d ago A 91 tokens original Apache-2.0

tsingyuai/growth-lab

Skill Codex

A workflow for creating, checking, publishing, and reviewing long articles for WeChat Official Accounts, a Chinese platform for publishing articles to subscribers. It covers topic selection, drafting, previewing, compliance checks, draft syncing, controlled release, and performance review.

not rated 2.0k +3 22d ago A 93 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: