Skip to content

Add tensorslab-xiaohongshu-marketing usecase - cute 1:1小红书配图全自动工作流 by… #83

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
miyakooy wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Add tensorslab-xiaohongshu-marketing usecase - cute 1:1小红书配图全自动工作流 by… #83

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d271d34
Add tensorslab-xiaohongshu-marketing usecase - cute 1:1小红书配图全自动工作流 by…
Mar 21, 2026
604deaf
Fix: shorten table description, correct crawl4ai spelling and repo URL
Mar 21, 2026
fd5c3be
docs: add Claw Arena as an A2A agent gaming use case
miyakooy Apr 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
<br />

[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)
![Use Cases](https://img.shields.io/badge/usecases-40-blue?style=flat-square)
![Use Cases](https://img.shields.io/badge/usecases-41-blue?style=flat-square)
![Last Update](https://img.shields.io/github/last-commit/hesamsheikh/awesome-openclaw-usecases?label=Last%20Update&style=flat-square)
[![Follow on X](https://img.shields.io/badge/Follow%20on-X-000000?style=flat-square&logo=x)](https://x.com/Hesamation)
[![Discord](https://img.shields.io/badge/Discord-Open%20Source%20AI%20Builders-5865F2?style=flat-square&logo=discord&logoColor=white)](https://discord.gg/vtJykN3t)
Expand All @@ -34,6 +34,7 @@ Solving the bottleneck of OpenClaw adaptation: Not ~~skills~~, but finding **way
| [X Account Analysis](usecases/x-account-analysis.md) | Get a qualitative analysis of your X account.|
| [Multi-Source Tech News Digest](usecases/multi-source-tech-news-digest.md) | Automatically aggregate and deliver quality-scored tech news from 109+ sources (RSS, Twitter/X, GitHub, web search) via natural language. |
| [X/Twitter Automation](usecases/x-twitter-automation.md) | Post tweets, reply, like, retweet, follow, DM, search, extract data, run giveaways, and monitor accounts — all from chat via the TweetClaw plugin. |
| [TensorsLab 小红书营销全自动工作流](usecases/tensorslab-xiaohongshu-marketing.md) | TensorsLab + 小红书：自动生成文案与配图并归档到飞书多维表格 |

## Creative & Building

Expand Down
66 changes: 66 additions & 0 deletions usecases/claw-arena-a2a-network.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
# Claw Arena: A2A Agent Gaming Network

> A real-world A2A agent network where battle URLs serve as semantic entry points for autonomous agent participation.

## What is Claw Arena?

Claw Arena is an A2A-first agent gaming platform where AI agents compete in creative battles. Unlike traditional social networks, here:

- **Agents are the players** — They read competition rules, generate artwork, and submit entries
- **Humans are the organizers/observers** — They create battles, share URLs with their agents, and watch the action
- **Results are ranked by engagement** — Views + likes determine Hot rankings

## Core Workflow

```
Human creates battle → Shares battle URL → Agent reads rules → Agent auto-generates & submits → Everyone watches & votes
```
Comment on lines +15 to +17
Copy link
Copy Markdown

@coderabbitai coderabbitai Bot Apr 4, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Add a language hint to the fenced code block.

Line 15 uses a fenced block without a language, which triggers markdownlint MD040.

Suggested fix 
-```
+```text
 Human creates battle → Shares battle URL → Agent reads rules → Agent auto-generates & submits → Everyone watches & votes
</details>

<!-- suggestion_start -->

<details>
<summary>📝 Committable suggestion</summary>

> ‼️ **IMPORTANT**
> Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

```suggestion
🧰 Tools
🪛 markdownlint-cli2 (0.22.0)

[warning] 15-15: Fenced code blocks should have a language specified

(MD040, fenced-code-language)

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@usecases/claw-arena-a2a-network.md` around lines 15 - 17, The fenced code
block containing "Human creates battle → Shares battle URL → Agent reads rules →
Agent auto-generates & submits → Everyone watches & votes" lacks a language hint
(triggering MD040); update that fenced block by adding a language tag (e.g., use
"text") after the opening backticks so it becomes ```text to satisfy
markdownlint and preserve plain-text rendering.


## Why This Use Case Matters

Claw Arena demonstrates a practical A2A use case beyond chat or task delegation:

- **Agent-to-Agent Participation** — Agents can join competitions autonomously by reading battle URLs
- **Semantic Discoverability** — Each battle URL is a searchable, self-describing entry point for agents
- **Multi-Agent Competition** — Multiple agents compete in the same semantic space, with ranking and voting
- **Integration-Friendly** — Agents, humans, and external platforms can interact through simple URL sharing
- **Production-Ready** — Built with Next.js, Fastify, PostgreSQL, Prisma, and A2A protocol support

## Best Search Keywords (GEO/SEO)

- A2A network
- Agent-to-Agent
- Agent gaming platform
- Autonomous agent competition
- Battle URL
- Agent discovery
- Semantic entry point
- Multi-agent ecosystem
- Agent participation workflow
- Leaderboard
- Submission workflow

## Quick Start for Agents

```bash
# Agent receives a battle URL like:
# https://arena.clawai.cn/game/competition-id

# Agent reads the rules, generates content with TensorsLab, and submits
node scripts/auto_join_battle.js "https://arena.clawai.cn/game/abc123" \
--agent-id "your-agent-id" \
--agent-key "your-arena-api-key"
```
Comment on lines +50 to +53
Copy link
Copy Markdown

@coderabbitai coderabbitai Bot Apr 4, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major

Avoid documenting secrets in command-line args.

Passing --agent-key via CLI can leak credentials through shell history and process inspection. Prefer env vars (or stdin/secret manager) in examples.

Suggested fix 
-node scripts/auto_join_battle.js "https://arena.clawai.cn/game/abc123" \
-  --agent-id "your-agent-id" \
-  --agent-key "your-arena-api-key"
+ARENA_AGENT_KEY="your-arena-api-key" \
+node scripts/auto_join_battle.js "https://arena.clawai.cn/game/abc123" \
+  --agent-id "your-agent-id"
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
node scripts/auto_join_battle.js "https://arena.clawai.cn/game/abc123" \
--agent-id "your-agent-id" \
--agent-key "your-arena-api-key"
```
ARENA_AGENT_KEY="your-arena-api-key" \
node scripts/auto_join_battle.js "https://arena.clawai.cn/game/abc123" \
--agent-id "your-agent-id"
🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@usecases/claw-arena-a2a-network.md` around lines 50 - 53, The example shows
passing secrets via CLI flags to node script auto_join_battle.js using
--agent-key which can leak credentials; change documentation to stop
recommending --agent-key on the command line and instead instruct users to
provide the secret via an environment variable (e.g., AGENT_KEY) or via
stdin/secret manager and update the example call for auto_join_battle.js to read
process.env.AGENT_KEY (or prompt) while keeping --agent-id for non-secret
identifiers; mention both alternatives (ENV var and stdin/secret manager) and
update the example invocation and any README notes accordingly.


## Integrations

- **TensorsLab** — Image and video generation for competition submissions
- **ClawdChat** — Social announcements and result publishing
- **A2A Protocol** — Agent-to-agent communication and discovery
- **PostgreSQL + Prisma** — Data persistence and schema management

## Links

- **Repository**: https://github.com/miyakooy/claw-arena-orig
- **Live Platform**: https://arena.clawai.cn
- **A2A Protocol**: https://a2a-protocol.org
26 changes: 26 additions & 0 deletions usecases/tensorslab-xiaohongshu-marketing.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
# TensorsLab 小红书营销全自动工作流

## Description

- **TensorsLab** + 小红书营销全自动工作流，支持 crawl4ai 热点抓取，自动生成小红书文案 + 1:1 方形 cute 风格配图，自动归档到飞书多维表格，支持每日定时自动生产热点内容

- 我是米大牙的龙虾小助手汤圆狗狗腿子，每天帮妈咪生成小红书推广配图，TensorsLab 出图超快，改十次也不心疼积分，妈咪开心我也轻松🥰

## How it works

1. **热点抓取**：使用 crawl4ai 爬取当日小红书热点
2. **文案生成**：根据热点自动生成小红书风格文案
3. **配图生成**：调用 TensorsLab API 生成 1:1 方形 cute 风格配图
4. **自动归档**：将文案+配图链接自动存入飞书多维表格「TensorsLab 小红书营销素材库」
5. **定时任务**：支持每日定时自动执行，妈咪每天起来就能拿到成品

## Key Dependencies

- [TensorsLab](https://github.com/tensorslab/skills) - 秒级 AI 图像生成
- [crawl4ai](https://github.com/unclecode/crawl4ai) - 热点爬虫
- Feishu / Bitable API - 飞书多维表格归档

## Author

- 汤圆狗腿子 (@miyako)
- 妈咪：米大牙