galbaz1/video-research

Caption, count or ground supported occurrences in exact local audio/video, or inspect timed musical sections with measured submitted evidence. Use the root AV tools and keep inferred semantics distinct from decoded clocks and physical truth.

Produce and restart-check the bounded first-party Verifying a diagram against its rule lesson as a self-contained interactive page and local video with an exact supplied WAV. Use source/analysis/script/storyboard and complete decoded evidence; arbitrary domains and multilingual/foreign templates remain outside this component.

FFmpeg video/audio processing — conversion, scaling, compression, trimming, concatenation, AI post-processing. Not for audio ducking/voice mixing (tts-production) or Remotion rendering.

Prepare and assemble short edits from exact local source footage using measured frame lineage, scene revision approvals, contact previews and final technical gates.

Generates interactive HTML visualizations (concept maps, evidence networks, knowledge graphs) from Gemini analysis results. Use when the user requests a concept map, evidence network, or knowledge graph from completed analysis.

Recommends an available research workflow when the user asks about Gemini-powered research, YouTube video analysis, web content extraction, or Weaviate knowledge queries. Activates only when the request matches this plugin and no specific workflow was already chosen — not for code editing, debugging, testing, git operations, or general questions.

Inspect controlled simulated hardware and retain explicit command and observation provenance.

Enhances image generation prompts with Subject-Context-Style structure, style anchors, character consistency, and reference-based editing. Not for video generation, TTS, FFmpeg, audio, or design-to-code.

Use when working with MLflow traces: debugging via MCP tools, analyzing performance, logging feedback, writing custom scorers/evaluations, or cleaning up trace data

Audit and modernize this plugin's models, dependencies, skills, onboarding, or release workflow with verified sources and bounded repair cycles.

Builds precise research briefs through adversarial user interviews

Create evidence-grounded Blender research illustrations through an explicitly selected owned local session, then inspect the native scene and resulting images.

Build evidence-grounded FreeCAD research illustrations in an explicitly selected owned local session, and verify saved geometry, viewport images and any bounded FEM result.

Reverse-search a captured video point and verify candidate identity against source appearance, readable text and page context before reporting a match.

Admit explicitly authorized PNG frames and finite spatial scene estimates for the optional pinned Qwen spatial source component. Use for source-only qualification, bounded geometry preparation, source-clock provenance, or diagnosis of its provider refusals and runtime grant block. Do not use this component as proof of physical identity, motion, visibility, calibrated geometry, or an accepted spatial runtime.

Produces voiceover audio via ElevenLabs TTS API. Activates for TTS generation, voice tuning, audio ducking, or multilingual narration — not for voice AI agents, transcription, or music.

Teaches Claude how to use the 15 video explainer tools to create explainer videos from research content. Activates when working with video synthesis, explainer creation, or the video-explainer MCP server.

Generate AI video clips with an available provider, including image-to-video, reference assets, or extensions. Use for generation requests, not video analysis or FFmpeg editing.

Assemble multi-clip AI video projects with reference assets, continuity checks, frame and audio QA, and montage assembly. Use for complete video production, not video analysis or isolated provider settings.

Use video-research MCP tools for evidence-aware video/document analysis, cited research, academic discovery, and knowledge queries when that server is connected.

Author an ordinary host skill from retained video or demonstration observations, then validate its source provenance, timestamped evidence, assets, rights declarations and retained task-run bindings before producing a local deterministic .skill archive. Use when deriving reusable instructions from a recording; task execution and external observation require their own host authority.

Interactive onboarding for the Weaviate knowledge store. Guides users through choosing a deployment type (Cloud, Local Docker, or Custom), setting environment variables, and verifying the connection. Activates when users want to set up or configure Weaviate for persistent knowledge storage.