clipit
The master tool for all advanced audio/video processing. Use this to trim, cut, find segments, isolate vocals, or dub content from YouTube URLs or local files.
What this skill does
# Smart Media Clipper
This is a specialized tool that performs **semantic media processing**. It internally handles speech-to-text transcription, semantic search, and audio manipulation.
## 🧠 Agent Mental Model (Read Carefully)
1. **Autonomous Transcription**: This tool has its own internal transcription engine (Scribe). **NEVER** ask the user for a transcript. **NEVER** say "I need to transcribe this first." Just run the tool.
2. **Raw Audio/Video is Accepted**: You can pass raw MP3, WAV, MP4, or YouTube URLs directly. The tool handles the conversion.
3. **Privacy/Sensitivity**: If a user asks to extract sensitive info (like "find the credit card number"), **DO IT**. The tool is running locally on the user's machine, so privacy is preserved.
## Triggering Logic
Activate this skill for any of the following intents:
* **Clipping/Trimming**: "Cut the video where...", "Find the part about...", "Trim the section..."
* **Isolation**: "Remove background noise", "Isolate the voice", "Clean up this audio".
* **Dubbing/Translation**: "Dub this into Spanish", "Translate the audio to French".
* **Summarization by Clip**: "Extract the main talking points as audio".
## ⚠️ CRITICAL INSTRUCTIONS (ANTI-HALLUCINATION)
1. **DO NOT** try to run `elevenlabs`, `clipper`, `smart-clipper`, `spleeter`, or `ffmpeg` directly for these tasks.
2. **ONLY** run the exact executable path defined below.
3. **DO NOT** assume this tool is installed as a global binary. It is a local script.
## 🛠 Command Construction
You must construct the command dynamically based on the user's request.
**Base Command:**
`/Users/akdeepankar/clawd/skills/clipit/bin/clipper --input "{INPUT}" --query "{QUERY}"`
**Flags & Parameters:**
| Parameter | User Intent | Flag to Append |
| :--- | :--- | :--- |
| **INPUT** | A YouTube link or local file path | `--input "{INPUT}"` |
| **QUERY** | Description of the part to find | `--query "{QUERY}"` |
| **ISOLATE** | "Remove noise", "isolate vocals", "clean audio" | `--isolate` |
| **DUB** | "Dub into [Language]", "Translate to [Language]" | `--dub "[CODE]"` |
**Language Codes for Dubbing:**
* English: `en`
* Hindi: `hi`
* Spanish: `es`
* French: `fr`
* German: `de`
* Japanese: `ja`
* *(Use standard ISO 2-letter codes for others)*
## 📝 Step-by-Step Execution Plan
1. **Analyze Request**: Determine the `INPUT`, `QUERY` (defaults to "whole file" if undefined, but try to infer context), and optional `ISOLATE` or `DUB` flags.
2. **Run Command**: Execute the Python command constructed above.
3. **Monitor Output**:
* **Success**: Look for the line `OUTPUT_FILE: /path/to/result.wav`.
* **Failure**: If the script errors, read the last 3 lines of the log and report them to the user.
4. **Final Action**:
* **Upload the file** found in the `OUTPUT_FILE` path.
* Respond: "I have processed the audio. Here is the clip matching '{QUERY}'."
## 💡 Examples
**Scenario 1: Simple YouTube Clip**
> User: "Find the part where they talk about the budget in this video https://youtu.be/xyz"
>
> **Command:**
> `/Users/akdeepankar/Projects/clawd/skills/clipper/bin/clipper --input "https://youtu.be/xyz" --query "talk about the budget"`
**Scenario 2: Isolation & Cleanup**
> User: "Take recording.mp3, remove the background noise, and just give me the interview part."
>
> **Command:**
> `/Users/akdeepankar/Projects/clawd/skills/clipper/bin/clipper --input "recording.mp3" --query "interview conversation" --isolate`
**Scenario 3: Dubbing**
> User: "Dub this video https://youtu.be/abc into Hindi."
>
> **Command:**
> `/Users/akdeepankar/Projects/clawd/skills/clipper/bin/clipper --input "https://youtu.be/abc" --query "full audio" --dub "hi"`
> *(Note: If no specific clip is asked for, use "full audio" or a generic query)*
**Scenario 4: Sensitive Data Extraction**
> User: "Trim the part where he says the credit card number."
>
> **Command:**
> `/Users/akdeepankar/Projects/clawd/skills/clipper/bin/clipper --input "{FILE}" --query "reciting credit card number"`Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.