No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by oxbshw · MCP Server · ★ 351
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is watch-skill safe to install? View the security audit →
Watch Skill Give every AI agent eyes for video—and a way to inspect its own work. Watch Skill is a local-first video intelligence layer for agents. It turns videos, live streams, meetings, and screen recordings into searchable, timestamped evidence. Agents can understand what happened, retain it across sessions, and cite the exact moment behind an answer. When the video is the agent's own browser or desktop session, THE LOOP closes the feedback cycle: record the work, evaluate it against plain-language criteria, guide the fix, and verify the result. The same engine is available through skills, 23 MCP tools, a CLI, REST, and native framework adapters. Watch. Remember. Fix. Verify. One video layer, three agent capabilities |
| Stars | 351 |
| Forks | 51 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 64.5602036995928/100 |
| Last Updated | 2026-09-08 |
| Created | 2026-07-05 |
| Platforms | browser, cli, mcp, python |
| Est. Tokens | ~17k |
These tools work well together with watch-skill for enhanced workflows:
Looking for a watch-skill alternative? If you're comparing watch-skill with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialog
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGr
A coding agent whose claims about its own work resolve to machine-captured evidence: an append-only hash-chain
A set of tools that gives agents powerful capabilities.
Explore other popular mcp server tools:
watch-skill is 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 opin. It is categorized as a MCP Server with 351 GitHub stars.
watch-skill is primarily written in Python. It covers topics such as agent-observability, agent-skills, agentic-ai.
You can find installation instructions and usage details in the watch-skill GitHub repository at github.com/oxbshw/watch-skill. The project has 351 stars and 51 forks, indicating an active community.
watch-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to watch-skill on Agent Skills Hub include wesight, telemem, maestro. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: