AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Video Watch

skill-witnesstodark-mr-mak-workspace-video-watch · by witnesstodark

Inspect a local or publicly accessible video through sampled scene frames, timestamps and a visual report, especially for motion and 3D reference analysis.

↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-witnesstodark-mr-mak-workspace-video-watch

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-witnesstodark-mr-mak-workspace-video-watch)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Video Watch? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Video Watch

Read [the workflow](../../../knowledge/video-watch.md). Use the project helper at scripts/video-watch/extract.py with a local file or supported video URL and a new dated Workspace folder. Install its optional dependencies in a local virtual environment, not the system Python environment.

Inspect the extracted frames. Cite timestamps for observations and open the original clip when a sparse sample cannot establish timing or continuity. For gait and fast action, use denser samples around the relevant range. Do not claim to have watched every frame from a contact sheet.

Keep visual observations separate from audio or transcript claims. URL downloads in this helper prefer video-only streams; do not assume they contain audio. For transcription, use the original audio through a separately configured tool. Create an English summary with evidence and links in the existing task card. Use workspace-authoring for its presentation.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Content & Media