oxbshw/watch-skill

Cross-references: mentioned by 1 indexed plugin →

★ 518 GitHub stars · Python · Terminal & CLI

About watch-skill

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

watch-skill is one of 29 projects listed under Terminal & CLI on DSHToolkit. Terminal interfaces, command line tools and CLI wrappers for DSH.

Installation

git clone https://github.com/oxbshw/watch-skill.git
cd watch-skill
# follow the README for install steps

Most DeepSeek Harness plugins install as npm packages or DSH extensions. After installing, restart DSH so the plugin registers. If the project ships a desktop client or a plugin market, you can install it with one click instead.

Install and configure watch-skill

git clone https://github.com/oxbshw/watch-skill.git
cd watch-skill
pip install -e .
# then point DeepSeek Harness at the local package per its README

Python projects here ship as importable packages, so an editable install keeps your checkout and the runtime in sync while you evaluate it.

Configuration

# dsh.config.py — typical registration shape
plugins = [
    # confirm the exact import path in the README before using this
    "watch-skill",
]

Registration shapes vary between plugins. The snippet above shows the common case — " copy the exact name from the README rather than trusting this example verbatim.

Is it the right choice?

• Choose it if you need exactly this narrow capability. At 518 stars it is a small project, so expect to read the source when something breaks.
• Licensing is MIT, which is permissive enough to vendor into a commercial product without a legal review.
• Stack: written in Python, tagged agent-observability, agent-skills, agentic-ai, ai-agents. If your team does not work in that language, every fix becomes a research task.

Things that commonly go wrong

• Version drift. DSH is young and moves fast. A plugin that worked three months ago may target an API that has since changed. Check the last commit date before you plan around it.
• No sandbox guarantee. Plugins run with the runtime's permissions. Read the source of anything that touches your filesystem, shell or API keys before installing it.
• Single maintainer risk. Most projects here are one person's side work. That is fine for a utility, risky for infrastructure you depend on.

Star history

Recorded on 4 days. Over that window the project moved +0 stars (+0.0%).

Window	Change
2026-10-24 → 2026-10-25	+0
2026-10-25 → 2026-10-26	+0
2026-10-26 → 2026-10-28	+0

These numbers are our own daily snapshots, not an estimate. A directory that only shows a single static star count hides whether a project is alive.

Details

Language	Python
License	MIT
Stars	518
Last updated	2026-10-14
Category	Terminal & CLI
Homepage	https://pypi.org/project/watch-skill/

Topics

FAQ

What is watch-skill?

watch-skill is a DeepSeek Harness plugin by oxbshw. Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

How do I install watch-skill?

Clone or install from the repository at https://github.com/oxbshw/watch-skill, follow the README install steps, then restart DeepSeek Harness. Plugins are usually npm packages or DSH extensions.

Is watch-skill free?

watch-skill is published under the MIT license. Check the repository for the current terms.

How popular is watch-skill?

watch-skill has 518 GitHub stars and was last updated on 2026-10-14.

Related plugins