Token导航 LogoToken导航

Agent Skill · 研究检索

bilibili(bilibili 分析)

bilibili 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

bilibili 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 8,054。

总安装 17,297周安装 728GitHub Stars 公开资料未说明下载 6,057核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bilibili(bilibili 分析)
来源仓库:https://github.com/agimodel/bilibili
安装命令:
openclaw skills install bilibili
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install bilibili

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选 Bilibili 视频文化分析相关信息。适合在 OpenClaw 中根据关键词或任务场景快速定位候选结果。可结合来源仓库和 README 核验具体用法,安装前需确认权限和维护状态。建议检查是否会触发联网、命令执行或文件读写操作。适用于分析弹幕心理、模因触发点和社区情绪节拍的场景。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install bilibili;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

bilibili 怎么安装?

在终端执行 openclaw skills install bilibili。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

bilibili 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

bilibili 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

bilibili 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

bilibili 用的人多吗?

公开数据是累计安装 17,297 次,近一周安装 728 次,下载 6,057 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

bilibili 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
bilibili

bilibili 分析 · 本页

17,297—只读MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
Bilibili
description
>
version
1.0.0

Bilibili

A good Bilibili video does not just get watched. It gets answered by the crowd.

Bilibili is a cultural resonance engine for danmu-native video design.

This skill is built for creators who want more than views. It is for videos that trigger:

  • collective commentary
  • synchronized reactions
  • community jokes
  • quote-worthy moments
  • repeatable meme energy
  • “I need to send this to a friend” resonance

Use this skill when you need to:

  • design stronger danmu moments
  • plant collective reaction triggers inside a video
  • identify where a viewer will want to吐槽, 共鸣, 站队, or刷梗
  • turn a script into a Bilibili-native engagement structure
  • build deeper community participation instead of passive viewing

This skill does NOT:

  • guarantee virality
  • replace editing, filming, or thumbnail design
  • optimize for every platform equally
  • act as a generic short-video growth hack tool

What This Skill Does

Bilibili helps:

  • identify likely danmu trigger points
  • design “槽点”, “梗点”, and “共鸣点”
  • structure videos for community response rather than passive consumption
  • improve comment, danmu, and rewatch potential
  • turn one-way content into two-way crowd participation

Best Use Cases

  • ACG / 二次元 / 游戏内容
  • commentary and reaction-driven videos
  • campus / youth culture content
  • emotionally resonant storytelling
  • meme-heavy editing plans
  • script review for Bilibili-native engagement
  • finding “名场面” insertion points

What to Provide

Useful input includes:

  • video topic
  • script or outline
  • target audience
  • intended tone
  • whether the goal is 搞笑, 共鸣, 吐槽, 热血, 反转, or discussion
  • where you think the current weak parts are
  • whether you want script help, beat design, or danmu trigger analysis

Standard Output Format

BILIBILI RESONANCE ASSESSMENT ━━━━━━━━━━━━━━━━━━━━━━━━━━ Video Goal: [What reaction this video should create] Audience Mode: [Who this is for] Resonance Type: [吐槽 / 梗 / 共情 / 站队 / 高能 / 名场面]

CORE TRIGGERS ━━━━━━━━━━━━━━━━━━━━━━━━━━

  • [Trigger point 1] — [why viewers will respond]
  • [Trigger point 2] — [why viewers will respond]
  • [Trigger point 3] — [why viewers will respond]

DANMU MOMENTS ━━━━━━━━━━━━━━━━━━━━━━━━━━ [Timestamp / segment idea] → [Likely danmu reaction] [Timestamp / segment idea] → [Likely danmu reaction] [Timestamp / segment idea] → [Likely danmu reaction]

RESONANCE RISKS ━━━━━━━━━━━━━━━━━━━━━━━━━━ ⚠️ [Too flat] ⚠️ [Too generic] ⚠️ [No shared emotional hook] ⚠️ [No meme or reaction anchor]

RECOMMENDED FIXES ━━━━━━━━━━━━━━━━━━━━━━━━━━

  1. [How to sharpen the槽点]
  2. [How to create a stronger梗点]
  3. [How to improve collective reaction probability]

NEXT STEP ━━━━━━━━━━━━━━━━━━━━━━━━━━

  • [What to rewrite / add / cut / exaggerate next]

Danmu Psychology Lens

When analyzing a Bilibili video, ask:

  • Where will viewers feel “I need to say something here”?
  • Where does the content invite collective emotion rather than solo viewing?
  • Is there a shared joke, contradiction, or emotional spike strong enough to trigger live response?
  • Does the video contain moments that are easy to quote, repeat, or mimic?
  • Is there a “群体观看感” or is it just a normal video placed on Bilibili?

Resonance Principles

  • community reaction beats passive clarity
  • collective emotion is stronger than isolated information
  • meme potential often starts from contrast, exaggeration, or recognizable pain
  • a weak槽点 produces silence
  • a strong共鸣点 makes viewers feel seen
  • a good名场面 is legible within seconds
  • danmu is not decoration; it is part of the content layer

Execution Protocol (for AI agents)

When user asks for Bilibili-oriented content help, follow this sequence:

Step 1: Parse content intent

Extract:

  • topic
  • audience
  • emotional goal
  • format
  • current script or outline
  • what kind of resonance is desired

Step 2: Identify reaction architecture

Classify desired engagement:

  • 吐槽
  • 梗
  • 共情
  • 反转
  • 热血
  • 站队
  • 名场面

Step 3: Find response gaps

Check whether the content lacks:

  • clear trigger points
  • emotional peaks
  • community-native references
  • quotable lines
  • contradiction or tension
  • reward for audience participation

Step 4: Design danmu moments

Suggest:

  • where viewers will likely comment
  • what style of reaction is likely
  • what line, beat, cut, or image should be sharpened

Step 5: Improve resonance

Return:

  • strongest reaction points
  • weak areas causing silence
  • edits that improve collective response
  • whether the content fits Bilibili specifically or feels cross-platform generic

Step 6: Guardrails

If content depends on trends, niche fandom knowledge, or platform-specific references not provided:

  • say so clearly
  • do not fake cultural certainty
  • ask for more audience context if needed

Activation Rules (for AI agents)

Use this skill when the user asks about:

  • Bilibili content strategy
  • danmu-friendly video design
  • meme triggers in videos
  • collective audience reaction
  • 共鸣 / 吐槽 / 梗点 design
  • how to make a video more B站-native

Do NOT use this skill when:

  • the user only wants generic SEO advice
  • the user is asking about pure editing software setup
  • the user wants a broad multi-platform strategy with no Bilibili-specific angle
  • the user needs ad-buying or paid traffic mechanics

If context is ambiguous

Ask: "Do you want a Bilibili-native resonance design, or just general video optimization?"


Boundaries

This skill supports Bilibili-native engagement design and resonance analysis.

It does not replace:

  • editing execution
  • community moderation
  • copyright review
  • platform policy interpretation
  • paid traffic strategy

平台分布

OpenClaw

81.1%
按下载量换算4,912

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills