Skip to content
cccskills
FreePublished on GitHub

bilibili-viral-topic

Find low-follower viral Bilibili videos for account-growth topic selection. Use when the user asks for B站低粉爆款, Bilibili low-fan hits, 起号选题 from B站, niche Bilibili references, or videos ranked by UP主粉丝数, 播放, 点赞, 投币, 收藏, 分享, 评论, 弹幕, and 播放粉丝比.

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (6)

  • SKILL.md3.0 KB
  • agents/openai.yaml226 B
  • references/category_map.md904 B
  • references/rate_limits.md889 B
  • references/scoring.md1.5 KB
  • scripts/search_bilibili_viral_topic.py22.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Bilibili Viral Topic

Use this skill to find B站 videos that significantly outperform the UP主's follower base.

Quick Start

Run the bundled script from this skill directory:

python3 scripts/search_bilibili_viral_topic.py --topic "AI工具,大模型,AI编程" --days 30 --max-followers 100000 --min-play 10000 --limit 50 --format markdown

No API key is required. The script uses public Bilibili JSON endpoints with browser-like headers, conservative rate limits, retries, and a local follower cache.

Optional environment:

export BILIBILI_COOKIE="..."

Only set BILIBILI_COOKIE if public requests are repeatedly rate-limited. Never write cookies into skill files or output artifacts.

Workflow

  1. Convert the user's niche into focused Chinese and product-name keywords.
  2. Search B站 videos through x/web-interface/search/type with order=pubdate and order=click.
  3. Optionally supplement with x/web-interface/ranking/v2 when the user asks for broader platform signals.
  4. Deduplicate by bvid.
  5. Filter to the requested recent window using pubdate.
  6. Enrich each unique mid through x/relation/stat?vmid=<mid> and cache follower counts.
  7. Filter:
    • follower_count <= --max-followers
    • view_count >= --min-play
    • view_count / follower_count >= --min-play-follower-ratio
  8. Rank by breakout_score, then play_follower_ratio, then view_count.
  9. Return JSON for automation or Markdown for topic review.

Output Contract

Each result must preserve source and UP主 evidence:

{
  "platform": "bilibili",
  "content_id": "",
  "url": "",
  "title": "",
  "author_id": "",
  "author_name": "",
  "follower_count": 0,
  "published_at": "",
  "view_count": 0,
  "like_count": 0,
  "comment_count": 0,
  "share_count": 0,
  "save_count": 0,
  "coin_count": 0,
  "danmaku_count": 0,
  "hot_score": 0,
  "breakout_score": 0,
  "evidence": []
}

Read references/scoring.md before changing thresholds or combining B站 results with other platforms. Read references/rate_limits.md before increasing pages, ranking rids, or request speed.

Guardrails

  • Do not scrape B站 HTML pages when the JSON endpoints are enough.
  • Use browser-like headers. Naked script user agents can trigger -352 or HTTP 412.
  • Keep request speed conservative. Default --request-sleep 0.6 is intentional.
  • Cache follower counts for at least 24 hours. Re-querying the same mid repeatedly increases risk and adds little value.
  • Do not call a video confirmed low-fan if follower count is missing unless the user explicitly allows unknown followers.
  • Use videos as topic signals, hook references, title structures, and format references. Do not copy full scripts or captions wholesale.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Generate and download images through APIMart's asynchronous GPT-Image-2 API. Use when Codex needs APIMart image generation, GPT-Image-2 text-to-image, image-to-image with reference URLs or local image files, 1k/2k/4k output, aspect-ratio control, task polling, or saving APIMart image results locally.

The English summary is being prepared. Showing the original description.

kangarooking/kangarooking-skills680Updated Sep 7, 2026

用于处理写书过程中的章节截图与插图工作流。适用于:梳理某一章需要哪些截图、逐步给出 Claude Code 实操提示词、规定截图文件名与图号映射、回填本地 Markdown 中的图片位置、清理作者备注为读者版正文、以及把章节和图片按正确位置同步到 Feishu 文档。用户如果提到“书的截图”“章节配图”“图号对应”“放到原文里”“上传飞书文档”“按刚才那套流程来”,应触发此 skill。

The English summary is being prepared. Showing the original description.

kangarooking/kangarooking-skills680Updated Sep 7, 2026

Use for the owner's personal creator-content thumbnails and covers for short video, Bilibili, Douyin, WeChat, or similar platforms from a title, summary, established real portrait, kangaroo IP, product Logo, screenshot, or app reference. It enforces the owner's visual signature, runs a four-concept selection stage, then five responsive platform ratios. Do not use for generic clients, book or album covers, slide title pages, generic posters or social cards, article body illustrations, document headers, website hero art, or unrelated image edits unless the user explicitly invokes cover-skill and accepts the personal-signature rules.

The English summary is being prepared. Showing the original description.

kangarooking/kangarooking-skills680Updated Sep 7, 2026

Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development.

The English summary is being prepared. Showing the original description.

kangarooking/kangarooking-skills680Updated Sep 7, 2026

输入文字或图片,通过腾讯混元生3D TokenHub/OpenAI 兼容接口或腾讯云 SDK 生成3D模型。支持文生3D、图生3D、多视图生3D、PBR、白模、草图生3D、智能拓扑生3D;当用户要求生成或查询混元3D模型时使用。

The English summary is being prepared. Showing the original description.

kangarooking/kangarooking-skills680Updated Sep 7, 2026

Standalone multi-agent image generation skill for Hermes. Includes an internal design compiler, GPT-Image-2 generation via apimart.ai, case library reuse, interactive reference selection, batch workflows, and style-consistent series generation.

The English summary is being prepared. Showing the original description.

kangarooking/kangarooking-skills680Updated Sep 7, 2026

See all skills by kangarooking

Report a problem with this skill