Weibo Hub

What it does

When your agent uses it

• Tasks that involve Browser automation
• Tasks that involve Web scraping
• Tasks that involve Authentication

Example prompts

• “weibo-hub”
• “Weibo trending searches”
• “scraping Weibo”
• “/weibo-hub”

Requirements

• Python 3

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1Use browser_use to Extract Cookies
2. 2Read and Save Credentials from the env File

What it can do on your machine

Read from SKILL.md and the folder at commit ae8c5db. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 5 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • weibo.com

  Also links to:

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Weibo Hub loads about 1.8k tokens when it runs. Until then it costs about 165 tokens; SKILL.md has 367 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~165

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 367 words, ~1,762 tokens.

name

weibo-hub

description

A skill for reading and writing Weibo data with Python + UV. It depends only on httpx and uses `browser_use get_cookies` to automatically retrieve cookies and complete authentication, with no manual copying required. It supports trending searches, popular feeds, following feeds, keyword search, Weibo post details/comments/reposts, user profiles/posts/following/follower lists, and more. This skill must be triggered whenever the user mentions "Weibo", "weibo", "weibo-hub", "Weibo trending searches", "scraping Weibo", "searching Weibo", "Weibo comments", "Weibo users", or any scenario that requires programmatic reading or writing of Weibo data.

/var/minis/skills/weibo-hub/
├── SKILL.md
├── pyproject.toml          # httpx only
└── scripts/
    ├── __init__.py
    ├── constants.py        # API endpoints, headers, and path constants
    ├── exceptions.py       # WeiboError exception hierarchy
    ├── auth.py             # Credential persistence (no browser-cookie3)
    └── client.py           # WeiboClient core class (all APIs)

# Call in the agent:
browser_use(action="navigate", url="https://weibo.com")
# After confirming you are logged in:
browser_use(action="get_cookies", url="https://weibo.com")
# Record the returned offload env file path

import sys, os, subprocess, json

# Load Cookie environment variables (the path comes from the offload file returned by get_cookies)
env_file = "/var/minis/offloads/env_cookies_xxx.sh"   # Replace with the actual path
result = subprocess.run(
    f". {env_file} && python3 -c \"import os,json; print(json.dumps(dict(os.environ)))\"",
    shell=True, capture_output=True, text=True
)
env = json.loads(result.stdout)

# Parse the Cookie dictionary (variables with the COOKIE_ prefix)
cookies = {
    k[len("COOKIE_"):]: v
    for k, v in env.items()
    if k.startswith("COOKIE_")
}

# Save credentials
sys.path.insert(0, "/var/minis/skills/weibo-hub")
from scripts.client import WeiboClient
WeiboClient.setup_credential(cookies)

cd /var/minis/skills/weibo-hub
uv sync

import sys
sys.path.insert(0, "/var/minis/skills/weibo-hub")
from scripts.client import WeiboClient

with WeiboClient() as client:

    # ── Trending searches / trends (no login required)──────────────────────────────
    topics = client.hot_search()          # Trending search list (~52 entries)
    for t in topics[:10]:
        print(f"#{t.get('realtime_hot_show_label','')} {t.get('word','')}")

    band = client.hot_band()              # Full trending search list
    trends = client.trending()            # Real-time search suggestions

    # ── Feeds (popular requires no login; following requires login)─────────────────────
    hot = client.hot_feed(count=10)       # Popular timeline
    home = client.home_feed(count=20)     # Following timeline

    # ── Search (mobile API)────────────────────────────────────
    results = client.search("Artificial Intelligence", page=1)
    for w in results[:5]:
        print(w.get("text", "")[:80])

    # ── Weibo post details / comments / reposts (login required)──────────────────
    wb = client.detail("Qw06Kd98p")
    cmt = client.comments("WeiboID", count=20)
    rep = client.reposts("WeiboID", count=10)

    # ── Users (login required)─────────────────────────────────────
    me = client.me()                      # Currently logged-in user
    user = client.profile("1699432410")   # Specified user profile
    weibos = client.user_weibos("1699432410", page=1)
    following = client.following("1699432410", page=1)
    followers = client.followers("1699432410", page=1)

© OpenMinis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts) in weibo-hub of OpenMinis/MinisSkills.

• SKILL.md
• pyproject.toml
• scripts/__init__.py
• scripts/auth.py
• scripts/client.py
• scripts/constants.py
• scripts/exceptions.py
• uv.lock

Open the folder on GitHubat commit ae8c5db