Bilibili Hub

What it does

When your agent uses it

• Tasks that involve Transcription
• Tasks that involve Browser automation
• Tasks that involve Video and podcast notes

Example prompts

• “Bilibili,”
• “bilibili,”
• “Bilibili videos,”
• “/bilibili-hub”

Requirements

• Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Use browser_use navigate to open https://www.bilibili.com and confirm that you are logged in.
2. 2Use browser_use get_cookies to retrieve cookies (raw values do not appear in the conversation).
3. 3Load the offload 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 4 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • uv
  • ffmpeg

  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:

  • bilibili.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

Bilibili Hub loads about 2.2k tokens when it runs. Until then it costs about 204 tokens; SKILL.md has 599 words of instructions outside code blocks.

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

~204

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

~2.2k

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). 599 words, ~2,208 tokens.

name

bilibili-hub

description

A skill for reading and writing Bilibili data with Python + UV, using bilibili-api-python + aiohttp. It automatically obtains cookies through `browser_use get_cookies` for authentication, so no manual copying is required. Supports video details, subtitles, AI summaries, comments, user profiles, search, popular videos/rankings, following dynamics feed, favorites, Watch Later, viewing history, interactions (likes, coins, triple action), publishing and deleting dynamics, and more. When a user mentions "Bilibili," "bilibili," "Bilibili videos," "Bilibili popular," "bilibili-hub," "get Bilibili data," "Bilibili subtitles," "Bilibili comments," "Bilibili favorites," "Bilibili dynamics," or any scenario that requires programmatically reading or writing Bilibili content, this skill must be triggered.

/var/minis/skills/bilibili-hub/
├── SKILL.md
├── pyproject.toml          # bilibili-api-python + aiohttp
└── scripts/
    ├── __init__.py
    ├── exceptions.py       # 6 structured exception types
    ├── payloads.py         # Data structure normalization (normalize_* functions)
    └── client.py           # BiliClient core class (all API methods)

. /var/minis/offloads/env_cookies_www_bilibili_com_xxx.sh
export BILI_SESSDATA="$COOKIE_SESSDATA"
export BILI_JCT="$COOKIE_BILI_JCT"
export BILI_USERID="$COOKIE_DEDEUSERID"
export BILI_BUVID3="$COOKIE_BUVID3"

# Method 1: From environment variables (recommended)
client = BiliClient.from_env()

# Method 2: Pass a dict directly
client = BiliClient({
    "SESSDATA":   os.environ["BILI_SESSDATA"],
    "bili_jct":   os.environ["BILI_JCT"],
    "DedeUserID": os.environ["BILI_USERID"],
})

# Method 3: Read-only operations (no write permissions required)
client = BiliClient({"SESSDATA": os.environ["BILI_SESSDATA"]})

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

import os, json, sys
sys.path.insert(0, "/var/minis/skills/bilibili-hub")
from scripts.client import BiliClient

client = BiliClient.from_env()

# Current user information
me = client.whoami()
print("User:", me.get("name"), "UID:", me.get("mid"))

# Search videos
videos = client.search_videos("Python Tutorial", count=5)
for v in videos:
    print(f"  {v['bvid']} {v['title']} ({v['duration']})")

# Get video details (including subtitles)
detail = client.get_video("BV1xx411c7mD", subtitle=True)
print(detail["video"]["title"])
print(detail["subtitle"]["text"][:200])

# Popular videos
hot = client.get_hot(count=10)
for v in hot:
    print(f"  {v['bvid']} {v['title']} 👁{v['stats']['view']}")

from scripts.exceptions import (
    AuthenticationError,  # Cookie missing or expired
    RateLimitError,       # Triggered risk control (412)
    NotFoundError,        # Video/user does not exist
    NetworkError,         # Network/timeout error
    InvalidBvidError,     # Invalid BV number format
    BiliError,            # Other API error (base class)
)

try:
    detail = client.get_video("BV1xx411c7mD")
except AuthenticationError:
    print("Cookie has expired. Please retrieve it again.")
except RateLimitError:
    print("Risk control triggered. Try again later.")
except NotFoundError:
    print("Video does not exist.")
except BiliError as e:
    print(f"API error: {e}")

© 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 5 other files (scripts) in bilibili-hub of OpenMinis/MinisSkills.

• SKILL.md
• pyproject.toml
• scripts/__init__.py
• scripts/client.py
• scripts/exceptions.py
• scripts/payloads.py

Open the folder on GitHubat commit ae8c5db