multimodal-ai skills

addxai/ReflectWorld

Skill Claude CodeCodex

Search and manage ReflectWorld video memories from ReflectWorld cameras.

addxai/ReflectWorld

Skill Claude CodeCodex

Perception automatically analyzes video segments from Eye using cloud VLM (Gemini). Working Memory tracks cross-segment event context. Results flow to ReflectWorld (storage) and Act (rules) via PostProcessor — all automatic.

addxai/ReflectWorld

Skill Claude CodeCodex

You have access to ReflectWorld, a visual perception and persistent memory system. It gives you eyes and memory for cameras.

jomeswang/agnes-ai-skill

Skill Claude CodeCodex

Use when the user wants Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.

grayhatdevelopers/vidxp

Skill Claude CodeCodex

Maintain and review VidXP repository documentation, including README.md, INSTALLATIONGUIDE.md, docs//.md, release copy, and contributor guides. Use when documentation or product behavior, CLI, HTTP, MCP, Desktop, deployment, releases, contributor workflows, architecture, research, or integrations change. Route…

grayhatdevelopers/vidxp

Skill Claude CodeCodex

Use VidXP to search indexed videos and surface inspectable evidence boards, keyframes, and clips before analysis. Trigger for requests such as "find where X appears," "when does Y happen," "what is said," "what happens," or "show me the matching clip," even when the user does not name VidXP. Favor one-pass evidence…

grayhatdevelopers/vidxp

Skill Claude CodeCodex

Install, update, or repair VidXP Desktop or the VidXP CLI and connect its local MCP server to Codex. Use when a user asks to install VidXP, choose between Desktop and CLI, enable local video search features, configure VidXP for an agent, or fix a missing VidXP runtime. This bootstrap skill does not require VidXP to…

Lum1104/video-to-skill

Skill Claude CodeCodex

Turn a video, tutorial, playlist, or course into an installed, evidence-grounded course Skill that can teach, give practice and feedback, apply demonstrated methods, and answer reference questions. Use when the user provides video sources and wants reusable learning or operational capability.

kdr/overcast

Skill Claude CodeCodex

Part of overcast

Map a target's internet-exposed hosts and services with the shodan source, capture host reports, brief the exposure, and optionally stand up a monitor for newly exposed services.

kdr/overcast

Skill Claude CodeCodex

Part of overcast

Be on the lookout — stand up a standing face/image watchlist: register a reference face, point a monitor at incoming feeds, auto-match every new item against the reference, and surface hits as a triage queue + alert so a match announces itself.

kdr/overcast

Skill Claude CodeCodex

Part of overcast

Hunt re-uploads and reskins of original video content across X / YouTube / TikTok — escalate from cheap metadata triage to frame/face/transcript matching and produce citable copycat findings.

loveld322/viral-video-blueprint

Skill Claude CodeCodex

A workflow for analysing a single Douyin, Xiaohongshu, or Bilibili video and creating a plan for an original business video based on its structure. It requires a real supported video link and produces the analysis and script in Chinese.