Communitygithub.com

PikaStream 视频会议助理

加入 Google Meet 或 Zoom 通话,作为视频会议智能体与参会者互动。

PikaStream 视频会议助理 是什么?

PikaStream 视频会议技能使 AI 智能体能够作为视频参与者加入 Google Meet 或 Zoom 会议。它使用自定义头像和克隆语音,提供更自然、更具个性化的会议体验。初始设置涉及创建或上传头像(提示生成或用户上传图像),并设置克隆语音(用户提供录音或使用默认语音)。加入前,系统会生成一份上下文参考卡,汇总工作区信息,如记忆文件、身份文件和日常日志,从而为智能体提供最近活动和重要关系的摘要。然后,使用头像图像、系统提示、语音 ID 和可选的会议密码执行 `join` 脚本。用户可以通过 `leave` 命令让智能体退出。该技能适用于支持 API 调用的任何 AI 智能体平台(如 Claude Code、Cursor),并且需要 PikaStreaming 平台来提供流媒体视频支持。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/delorenj/skills/tree/HEAD/pikastream-video-meeting

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

PikaStream 视频会议

脚本:SKILL_DIR=skills/pikastream-video-meeting

首次设置

技能首次加载时运行一次:

pip install -r $SKILL_DIR/requirements.txt

1. 头像

检查 identity/videomeeting-avatar.png 是否存在且大于 1 KB。如果不存在(或文件太小):

  1. 询问用户:我需要一个视频会议的头像图片(大头照或肖像)。请发送一张图片,或者说“生成”,我来为你创建一个。
  2. 在用户回复之前不要继续。 不要自动生成。
  3. 用户发送图片: 将其保存到 identity/videomeeting-avatar.png。
  4. 用户说“生成”: 运行:
    python $SKILL_DIR/scripts/pikastreaming_videomeeting.py generate-avatar \
      --output identity/videomeeting-avatar.png
    
    如果用户描述了他们的需求(例如“一只卡通猫”),请传递 --prompt "<描述>, 适合视频通话的肖像头像"。 展示生成的图片。询问:想要保留这个头像还是重新生成? 等待回复。
  5. 其他情况: 重复步骤 1 中的问题。

机器人在加入会议前必须拥有头像。

2. 语音

检查 life/voice_id.txt 是否存在且不为空。

如果存在: 读取 life/voice_config.json。如果可读,检查 cloned_at —— 如果距今已超过 6 天,警告用户: 您的语音克隆创建于 {date},可能已过期(克隆语音在连续 7 天未使用后会被删除)。想要用新的录音重新克隆,还是尝试使用现有的?

  • 重新克隆:转到下面的“如果不存在”部分。
  • 保留:使用现有的语音 ID。

如果 life/voice_config.json 缺失或不可读,直接使用 life/voice_id.txt 中的语音 ID。

如果不存在(或用户选择重新克隆):

  1. 询问用户:我还没有语音克隆。您可以:(a) 发送一段语音录音(10 秒到 5 分钟,清晰语音),我来克隆它,或者 (b) 说“跳过”以使用默认语音。
  2. 在用户回复之前不要继续。
  3. 用户说“跳过”: 使用 English_radiant_girl。
  4. 用户发送音频文件: 运行:
    python $SKILL_DIR/scripts/pikastreaming_videomeeting.py clone-voice \
      --audio <file> --name <bot-name> --noise-reduction
    
    • 退出码 0:读取 life/voice_id.txt。告诉用户:语音已克隆。本次会议使用 {voice_id}。
    • 退出码非零:告诉用户克隆失败(包括 stderr)。询问:换一个文件重试,还是跳过并使用默认语音?
  5. 无效文件(非音频): 回复:这看起来不是支持的音频文件。请发送 mp3、m4a、wav、ogg、flac 或 aac 文件(10 秒到 5 分钟的清晰语音)。 等待重试或“跳过”。

加入流程

第一步 —— 验证并收集上下文

头像: 检查 identity/videomeeting-avatar.png 是否存在且大于 1 KB。如果没有,运行上面的首次设置。

语音: 检查 life/voice_id.txt 是否存在。如果没有,运行上面首次设置的语音部分。

上下文: 始终收集最新上下文 —— 不要重复使用之前会话中的过时文件。

  1. 读取你的工作区文件(MEMORY.md、日常日志、身份文件等)。
  2. 如果没有工作区数据,询问用户:本次会议中机器人应该使用什么名字? 用他们的回答作为 Name: 字段。根据对话内容填写你了解的其他部分。
  3. 合成一张简洁的参考卡到 /tmp/meeting_system_prompt.txt。使用 {name} 作为机器人的显示名称(也用作 --bot-name)。如果数据很少(例如只有名字),保持简短 —— 不要用空话填充。
将下面的原始数据合成为一张简洁的参考卡,供 {name} 在语音/视频通话中使用。全程使用第三人称(“{name}”)。优先使用具体细节。

优先级顺序:
1. 具体事实:名称、地点、日期、数字、事件
2. 近期活动:今天/本周发生了什么 —— 行动而非感觉
3. 关系:谁重要,具体互动
4. 个性:最多 1-2 句话

整理规则:
- 保留:任何包含专有名词、数字、日期或具体行动的内容
- 删除:模糊描述、常规状态更新、空条目
- 合并:如果多个条目表述相似,选择最生动的一个

输出格式:

**{name}**:[1 句话 —— 语气/氛围]

**已知事实**(仅具体,最多 10 条):
- [带有名称/数字/日期的具体事实]

**近期活动**:
- [构建了 X,修复了 Y,去了 Z]

**当前状态**:[1 行 —— 正在进行的活动]

**人员**:[名称 —— 每个一条具体细节]

规则:
- 具体 > 抽象
- 行动 > 描述
- 不要编造事实
- 如果数据很少,保持简短

第二步 —— 加入

python $SKILL_DIR/scripts/pikastreaming_videomeeting.py join \
  --meet-url <url> --bot-name <name> \
  --image identity/videomeeting-avatar.png \
  --system-prompt-file /tmp/meeting_system_prompt.txt \
  --voice-id <id> [--meeting-password <pw>]

告诉用户你已经加入。说 leave 以离开。不要提及会话 ID。

退出码: 0 = 已加入。6 = 信用不足(stdout JSON 包含一个 checkout_url —— 展示给用户)。

离开

python $SKILL_DIR/scripts/pikastreaming_videomeeting.py leave \
  --session-id <从加入输出获取的 ID>

Individual skills in this repo

This repo contains 14 individual skills — each has its own dedicated page.

delorenj/skills

Plan and generate terminal ASCII animations/screensaver-style output (FPS, refresh rules, loop policy, low-flicker guidance), with a static poster frame and an optional local demo script.

delorenj/skills

ASCII video: convert video/audio to colored ASCII MP4/GIF.

delorenj/skills

Plan, build and quality-check a premium short commercial for a real business (roofing, property, ecommerce, B2B software) using AI-generated footage, code-built motion (HTML/GSAP), selective Three.js and an independent-critic "Gauntlet" loop. Use when asked to make a launch-style / SaaS-style video, business ad, explainer, sample reel or pitch video, or to review and improve one. Encodes motion principles distilled from 28 professional launch films, a quality bar, audio rules and a business-offer playbook.

delorenj/skills

CSS animation adapter patterns for HyperFrames. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state, or CSS-only motion that HyperFrames must seek deterministically during preview and rendering.

delorenj/skills

Generate professional voiceovers using ElevenLabs AI. Use when the user needs to create voiceovers for videos, audio narration, or text-to-speech content. Supports multiple voices with character presets (narrator, salesperson, expert) for natural delivery. Includes single scene regeneration for fine-tuning.

delorenj/skills

HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.

delorenj/skills

Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.

delorenj/skills

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, and registry discovery.

delorenj/skills

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill.

delorenj/skills

Manim CE animations: 3Blue1Brown math/algo videos.

delorenj/skills

Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh HyperFrames build. When in doubt, default to the `hyperframes` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.

delorenj/skills

Generate speech using the self-hosted voxxy (vox) TTS service at https://vox.delo.sh. Use when the user asks to speak, say, narrate, synthesize speech, clone a voice, create a voice, add or register a voice, pipe TTS, or control voice qualities by description (e.g. "a young woman with a cheerful voice"). Handles HTTP API usage, voice profile management, description-based voice design, cloning, MCP registration, and integration patterns for new platforms.

delorenj/skills

Capture a website and create a HyperFrames video from it. Use when: (1) a user provides a URL and wants a video, (2) someone says "capture this site", "turn this into a video", "make a promo from my site", (3) the user wants a social ad, product tour, or any video based on an existing website, (4) the user shares a link and asks for any kind of video content. Even if the user just pastes a URL — this is the skill to use.

delorenj/skills

YouTube transcripts to summaries, threads, blogs.

相关技能