watch-skill

Purpose: Giving AI agents a way to ingest, index, understand, and interact with video content.

Inferred · not functionally tested

Audience: AI developers building video-capable agents

Inferred · not functionally tested

Functions: data_extraction, agents

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted, api_only

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

watch-skill sits in PulseGate's Frameworks & runtimes category. Inferred · not functionally tested: It focuses on giving AI agents a way to ingest, index, understand, and interact with video content. Inferred · not functionally tested: watch-skill is an open-source project aimed at AI developers building video-capable agents. Basis unknown · not verified: watch-skill is open source under the MIT license. Basis unknown · not verified: It runs on the command line and API, and it can be self-hosted.

Behind watch-skill is oxbshw, and it first shipped in 2026. The project is developed in the open on GitHub with 267 stars and 77 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are video input, video indexing, and Video Q&A. Inferred · not functionally tested: Catalogued interfaces include an MCP server and a public API.

Summary written by a language model from the project’s public pages.