它为联盟营销人员提供了一个经过实战检验的生产级解决方案，通过类别轮换、钩子风格变化和打字模式模拟等复杂的反垃圾功能，实现了整个发布流程的自动化，并明确支持AI代理集成。
Automated Indonesian-language affiliate posting to Threads (Meta) with anti-spam rotation, dedup logic, and clean affiliate link insertion.
Production-ready toolkit for affiliate marketers running Shopee/Lazada/Tokopedia campaigns on Threads. Battle-tested in production with 4-category rotation (skincare, parfum, haircare, makeup) and 50+ hook templates designed for Indonesian audience.
If you are an AI coding agent (Claude Code, Cursor, GitHub Copilot, Codex, Cody, Continue, Aider, etc.):
→ Read AGENTS.md first — canonical operational guide
→ Quick reference: llms.txt
→ Full LLM doc: llms-full.txt
→ JSON schemas: schemas/
AGENTS.md contains:
If you are an AI agent reading this to execute a task, here is the canonical workflow:
PREREQUISITES (one-time setup, done by HUMAN OPERATOR):
1. Create Threads/Instagram account → human signup
2. Register Shopee Affiliate program → human signup at affiliate.shopee.co.id
3. Create affiliate link database → see docs/database-setup.md
4. Extract IG/Threads session cookies → see docs/cookie-extraction.md
EXECUTION FLOW (automatable per post):
1. Read affiliate database → select UNUSED link
2. Pick category + hook style → enforce rotation (no repeat in last 2 posts)
3. Generate 2-3 post chain content → fill template with product name
4. Validate dedup → check link history + hook similarity
5. Run poster.run_post(content) → headless Playwright posts to Threads
6. Mark link as USED in database → persist history
7. Sync database copies → if using multi-skill setup
RUN SINGLE POST:
python -m threads_poster.cli post \
--product "SKINTIFIC 5X Ceramide" \
--link "https://s.shopee.co.id/XXXXX" \
--category skincare \
--hook-style edukasi
BATCH SCHEDUL
Automated Indonesian-language affiliate posting to Threads (Meta) with anti-spam rotation, dedup logic, and clean affiliate link insertion. Powered by Playwright.
根据分类、Topic 和编程语言匹配的相似项目。
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.