← Back to Skills Marketplace
Video Sourcing
by
Samuel Zhang
· GitHub ↗
· v0.2.5
683
Downloads
0
Stars
1
Active Installs
7
Versions
Install in OpenClaw
/install video-sourcing
Description
Run the Video Sourcing Agent with deterministic, concise chat UX for /video_sourcing using a pinned self-bootstrap runtime.
Usage Guidance
This skill does what it says: it will clone a pinned GitHub repo and run its code on your machine, using your GOOGLE_API_KEY and YOUTUBE_API_KEY. Before installing, review or vet the remote repository (https://github.com/Memories-ai-labs/video-sourcing-agent) and its dependencies, verify you trust the maintainer, and be aware the runtime runs unsandboxed and can access your filesystem and any environment variables. If possible, run it in an isolated environment (VM/container) first, use least-privilege API keys, and be prepared to rotate keys if you proceed. Also note the registry metadata omitted a homepage while SKILL.md references the GitHub repo — that mismatch is worth confirming with the skill author.
Capability Analysis
Type: OpenClaw Skill
Name: video-sourcing
Version: 0.2.5
The skill requires host runtime execution (sandbox off) and performs automated bootstrapping by cloning and executing code from an external GitHub repository (Memories-ai-labs/video-sourcing-agent) via the script run_video_query.sh. While the logic appears aligned with its stated purpose of video sourcing, the practice of downloading and running unverified remote payloads on the host with access to sensitive environment variables (GOOGLE_API_KEY, YOUTUBE_API_KEY) is a high-risk pattern that could be exploited if the remote repository is compromised.
Capability Assessment
Purpose & Capability
Name, description, declared binaries (git, uv) and required env vars (GOOGLE_API_KEY, YOUTUBE_API_KEY) align with a video-sourcing agent that queries YouTube/Google-backed APIs. Minor note: SKILL.md mentions other platforms (TikTok/Instagram/X) but no credentials for those are requested — that may be because the pinned runtime handles them differently, but it's not explained.
Instruction Scope
SKILL.md and the script require host runtime execution (sandbox mode off) and will clone a remote repository and execute its code. The runtime bootstraps to ~/.openclaw/data/video-sourcing-agent and runs uv run python -m video_sourcing_agent.integrations.openclaw_runner, meaning arbitrary code from the pinned repo will be executed with access to local environment and files. The skill also references VIDEO_SOURCING_AGENT_ROOT as an override (not listed in required envs) and instructs polling/kill behavior for processes — all expected but increasing attack surface.
Install Mechanism
There is no packaged install spec; the included script clones a pinned GitHub repo (https://github.com/Memories-ai-labs/video-sourcing-agent) at tag v0.2.5 and runs 'uv sync' then 'uv run'. Using GitHub and a pinned tag is better than an unpinned download, but the behavior still writes code to disk and executes third-party dependencies at runtime, which is a high-impact operation and should be audited.
Credentials
The skill only requires GOOGLE_API_KEY and YOUTUBE_API_KEY, which are appropriate for YouTube/Google lookups. However, because the skill bootstraps and runs external code unsandboxed, that code will have access to any other environment variables and local files; treat API keys and other secrets as exposed to the runtime and consider using limited-scope keys or rotating them after use.
Persistence & Privilege
always:false and user-invocable:true (normal). The script persists a managed runtime under ~/.openclaw/data/video-sourcing-agent/v0.2.5 and creates a lock/marker file; this is reasonable for a self-bootstrap runtime. The main privilege concern is the unsandboxed execution of the bootstrapped code rather than any special platform flags.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-sourcing - After installation, invoke the skill by name or use
/video-sourcing - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.2.5
Bump runtime pin to v0.2.5: gemini 3.1 pro model, TikTok share URL fix, deterministic tool policy, typing indicator fixes, personality preservation, Instagram fail-fast retries
v0.2.4
Bump pinned agent runtime to v0.2.3 in SKILL.md and bootstrap script.
v0.2.3
Fix Telegram three-message progress ordering: keep 'Starting video sourcing...' first-only and use minimal heartbeat summaries.
v0.2.2
Pin runtime Python to 3.12 in bootstrap runner to avoid Python 3.14 compatibility issues (e.g., pydantic-core). Runtime repo remains pinned to v0.2.1.
v0.2.1
Hotfix bootstrap robustness: ensure lock directory parent exists, fail fast on marker write errors, and self-heal incomplete managed runtime before execution. Runtime pin moved to Memories-ai-labs/[email protected].
v0.2.0
Self-bootstrap runtime from github.com/Memories-ai-labs/video-sourcing-agent pinned to v0.2.0. VIDEO_SOURCING_AGENT_ROOT is now optional override.
v0.1.0
Initial ClawHub release.
Metadata
Frequently Asked Questions
What is Video Sourcing?
Run the Video Sourcing Agent with deterministic, concise chat UX for /video_sourcing using a pinned self-bootstrap runtime. It is an AI Agent Skill for Claude Code / OpenClaw, with 683 downloads so far.
How do I install Video Sourcing?
Run "/install video-sourcing" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Sourcing free?
Yes, Video Sourcing is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Video Sourcing support?
Video Sourcing is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux).
Who created Video Sourcing?
It is built and maintained by Samuel Zhang (@samuelz12); the current version is v0.2.5.
More Skills