Results for “screen-flows”

9 skills

Use when testing, fixing, or extending the MarketingClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

More results

Generate images, video, and audio via diffusion workflows.

nv-generate-ct-rflow

Generates synthetic CT volumes and masks using NVIDIA's rectified-flow pipeline for medical imaging research.

Generate images, video, and audio via diffusion workflows.

Analyze recent screen activity via a local screenpipe daemon, detect repeated research workflows, and draft new skills or composition recipes for uncovered patterns.

30.2k · bundle

Control Adobe desktop apps - Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition - from the shell via Flue, without an MCP server.

Generate images, video, and audio via diffusion workflows.

Evaluates spatial realism and temporal flow consistency of AI-generated videos using embedding spaces and Fourier transforms, producing bounded STREAM-S and STREAM-T scores.

capture-visuals

Walk through the manual-capture.md checklist for a slug, driving Chrome via the Claude in Chrome MCP to capture each visual that needs more than a static URL — multi-step flows, conversation states, settings panels, age gates on third-party sites. Runs equally well locally (your desktop Chrome) or on a VPS with always-on Chrome + the extension installed. Defaults to unattended mode when `BLOG_AGENT_AUTONOMOUS=1` (which forces `UNATTENDED=1`). Use after /generate-visuals has flagged action-shot or failed-screenshot entries.