功能描述

AI-native workflow analyzer for Loom recordings. Breaks down recorded business processes into structured, automatable workflows. Use when: - Analyzing Loom videos to understand workflows - Extracting steps, tools, and decision points from screen recordings - Generating Lobster workflow files from video walkthroughs - Identifying ambiguities and human intervention points in processes

使用说明 (SKILL.md)

Loom Workflow Analyzer

Name: Loom Workflow
Author: g9pedro

Transforms Loom recordings into structured, automatable workflows.

Quick Start

# Full pipeline - download, extract, transcribe, analyze
{baseDir}/scripts/loom-workflow analyze https://loom.com/share/abc123

# Individual steps
{baseDir}/scripts/loom-workflow download https://loom.com/share/abc123
{baseDir}/scripts/loom-workflow extract ./video.mp4
{baseDir}/scripts/loom-workflow generate ./analysis.json

Pipeline

Download - Fetches Loom video via yt-dlp
Smart Extract - Captures frames at scene changes + transcript timing
Transcribe - Whisper transcription with word-level timestamps
Analyze - Multimodal AI analysis (requires vision model)
Generate - Creates Lobster workflow with approval gates

Smart Frame Extraction

Frames are captured when:

Scene changes - Significant visual change (ffmpeg scene detection)
Speech starts - New narration segment begins
Combined - Speech + visual change = high-value moment
Gap fill - Max 10s without a frame

Analysis Output

The analyzer produces:

workflow-analysis.json - Structured workflow definition
workflow-summary.md - Human-readable summary
*.lobster - Executable Lobster workflow file

Ambiguity Detection

The analyzer flags:

Unclear mouse movements
Implicit knowledge ("the usual process")
Decision points ("depending on...")
Missing credentials/context
Tool dependencies

Vision Analysis Step

After extraction, use the generated prompt with a vision model:

# The prompt is at: output/workflow-analysis-prompt.md
# Attach frames from: output/frames/

# Example with Claude:
cat output/workflow-analysis-prompt.md | claude --images output/frames/*.jpg

Save the JSON response to workflow-analysis.json, then:

{baseDir}/scripts/loom-workflow generate ./output/workflow-analysis.json

Lobster Integration

Generated workflows use:

approve gates for destructive/external actions
llm-task for classification/decision steps
Resume tokens for interrupted workflows
JSON piping between steps

Requirements

yt-dlp - Video download
ffmpeg - Frame extraction + scene detection
whisper - Audio transcription
Vision-capable LLM for analysis step

Multilingual Support

Works with any language - Whisper auto-detects and transcribes. Analysis should be prompted in the video's language for best results.

安全使用建议

This skill mostly does what it says, but review the following before installing or running it: 1) Privacy: extracted frames contain screen content; the pipeline expects you to run a vision-capable model (e.g., Claude or another cloud API). Only send sensitive recordings to models/endpoints you trust — prefer local models if privacy is a concern. 2) Undeclared credentials: generated Lobster steps reference tools like openclaw.invoke and gmail commands that will need credentials or agent tool access; the skill does not declare or request these. Expect to supply or gate those separately and review generated commands before execution. 3) Prompt & data handling: the scripts create large prompts (and can base64-encode images) — verify the prompt files before sending them to any external service to avoid accidental data leakage. 4) Execution surface: the SKILL.md shows a 'loom-workflow' CLI but the bundle provides individual Python scripts; ensure you understand how the agent will invoke them and test locally first (review scripts/analyze-workflow.py, smart-extract.py, generate-lobster.py). If you need higher assurance, run the pipeline in an isolated environment and avoid uploading recordings with credentials or PII to remote LLM services. If anything about required external services (which model endpoint, API keys) is unclear, ask the skill author for explicit details before use.

功能分析

Type: OpenClaw Skill Name: loom-workflow Version: 1.0.1 The skill is classified as suspicious due to its broad capabilities, even though they are plausibly needed for its stated purpose. It involves downloading videos from arbitrary URLs using `yt-dlp`, executing external binaries like `ffmpeg` and `whisper` for video and audio processing, and generating OpenClaw automation commands that can interact with browser and messaging tools. While there is no clear evidence of intentional malicious behavior or prompt injection against the OpenClaw agent, these extensive permissions and external interactions represent a meaningful high-risk profile, particularly the ability to download from any URL and generate commands for sensitive actions like typing into forms or sending emails, even with approval gates in the generated Lobster file.

能力评估

✓ Purpose & Capability

Name/description match the code and instructions: the scripts download Loom videos (yt-dlp), extract frames (ffmpeg + smart extraction), transcribe (whisper), produce prompts for a vision-capable model, and generate Lobster workflows. Required binaries and steps described are consistent with the stated purpose.

⚠ Instruction Scope

Runtime instructions and scripts explicitly direct the agent to download videos and upload extracted frames/prompts to vision-capable LLMs (example: piping a prompt to 'claude --images ...' and analyze prompts that reference frame image paths). This necessarily transmits potentially sensitive screen content off-host. The SKILL.md and scripts generate large prompts (and include image base64 encoding) which are normal for multimodal analysis but are also the pattern flagged by the pre-scan. The instructions also reference a 'loom-workflow' CLI (Quick Start) while the bundle contains individual Python scripts rather than that wrapper — minor inconsistency but could confuse automated execution.

✓ Install Mechanism

No install spec is present (instruction-only installation). The bundle includes Python scripts that will be present on disk, but there are no external download URLs or archive extraction steps in the install metadata, which lowers installation risk.

⚠ Credentials

The skill declares no required environment variables or credentials, but generated commands refer to other agent tools (openclaw.invoke, gog.gmail.list) and email/listing commands that would typically need service credentials. Those credentials are not declared in requires.env. Also, the workflow will send video frames to external vision models (e.g., Claude or other APIs) — sensitive data exposure is implied but no endpoints/credentials are declared, which is an incoherence/privacy concern.

✓ Persistence & Privilege

always:false and no code tries to persistently modify other skills or system-wide settings. The skill does create local artifacts (frames, manifests) during normal operation, which is expected for its function.

版本历史

v1.0.1

- Minor update to scripts/smart-extract.py; no changes to documentation or user-facing features. - No impact on core functionality or workflow for users.

v1.0.0

Initial release of loom-workflow. - Analyzes Loom screen recordings to extract structured business workflows. - Breaks down videos into actionable steps, tools used, and decision/approval points. - Generates Lobster workflow files and human-readable summaries from video walkthroughs. - Flags process ambiguities, human intervention points, and tool dependencies. - Supports multilingual video transcription and analysis with vision-capable LLM integration. - Includes CLI pipeline for downloading, extracting, transcribing, analyzing, and generating workflows.

元数据

Slug loom-workflow

版本 1.0.1

许可证 —

累计安装 7

当前安装数 7

历史版本数 2

常见问题

Loom Workflow 是什么？

AI-native workflow analyzer for Loom recordings. Breaks down recorded business processes into structured, automatable workflows. Use when: - Analyzing Loom videos to understand workflows - Extracting steps, tools, and decision points from screen recordings - Generating Lobster workflow files from video walkthroughs - Identifying ambiguities and human intervention points in processes. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2071 次。

如何安装 Loom Workflow？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install loom-workflow」即可一键安装，无需额外配置。

Loom Workflow 是免费的吗？

是的，Loom Workflow 完全免费（开源免费），可自由下载、安装和使用。

Loom Workflow 支持哪些平台？

Loom Workflow 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Loom Workflow？

由 G9Pedro（@g9pedro）开发并维护，当前版本 v1.0.1。

Loom Workflow