calesthio

Direct cinematic shots and coverage for AI-assisted content production. Use when an agent must translate story intent into framing, shot size, lens and perspective, camera position, movement, blocking, screen direction, lighting-aware coverage, continuity, shot specifications, or diagnose why generated or filmed shots do not cut together.

Provider-independent production guidance for converting observed video into precise, objective, temporally ordered language. Use for shot descriptions, searchable metadata, dataset captions, reference logs, generation-prompt handoffs, and analysis across subject, scene, motion, spatial, and camera aspects; not for deciding what to shoot, accessibility captions, creative interpretation, or provider-specific video analysis APIs.

Provider-independent quality assurance for AI-generated and AI-assisted media. Use when reviewing, accepting, revising, or reporting on images, video, audio, avatars, ads, product content, social clips, explainers, localization, mixed-source edits, captions, accessibility, provenance, model metadata, safety/policy, and delivery readiness.

Provider-independent reference media analysis for generated-media production. Use when an agent must analyze reference images, videos, audio, style boards, product shots, brand assets, mood boards, storyboards, performances, prior cuts, or client examples and translate them into safe, non-copying direction, prompts, QA criteria, provenance records, and handoff notes for image, video, audio, avatar, or post-production agents.

Provider-independent governance workflow for verifying and correcting human- or model-generated video descriptions. Use for pre-caption critique and post-caption revision, aspect-by-aspect factual review, critique precision/recall/constructiveness, second-stage peer review, calibration, appeals, versioned triplets, provenance, and acceptance reporting; not for pixel/audio QA, accessibility captioning, model training, or creative shot direction.

Provider-independent workflow for producing terminal, IDE, documentation, browser, desktop, and application demonstration videos. Use when choosing authentic capture, browser automation, synthetic UI, or hybrid treatment; scripting actions and narration; resetting demo state; protecting secrets and personal data; directing cursor/callouts; creating crop variants; and reviewing workflow truth, readability, accessibility, and provenance.

Provider-independent production guidance for translating measured audio features into deterministic video timing and motion. Use for beat-, onset-, phrase-, energy-, silence-, or spectrum-reactive visualizers, edits, typography, and generated compositions; not for music-video concept direction, audio generation, or a runtime-specific recipe.

Provider-independent production guidance for deterministic Canvas 2D and p5.js animation. Use for particles, fields, trails, weather, procedural textures, generative geometry, and lightweight 2D simulations that need fixed media dimensions, seeded repeatability, transparent compositing, aspect variants, performance QA, or frame-addressable rendering.

Trigger when: (1) User mentions "manimgl" or "ManimGL" or "3b1b manim", (2) Code contains `from manimlib import *`, (3) User runs `manimgl` CLI commands, (4) Working with InteractiveScene, self.frame, self.embed(), ShowCreation(), or ManimGL-specific patterns. Best practices for ManimGL (Grant Sanderson's 3Blue1Brown version) - OpenGL-based animation engine with interactive development. Covers InteractiveScene, Tex with t2c, camera frame control, interactive mode (-se flag), 3D rendering, and checkpoint_paste() workflow. NOT for Manim Community Edition (which uses `manim` imports and `manim` CLI).

Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage `google_music`, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing exact-duration music for a video.

Transcribe audio to text using Azure AI Speech (Fast Transcription REST API). Use when converting audio/video to text, generating subtitles, or processing spoken content in OpenMontage. Optional cloud STT provider — preferred when AZURE_SPEECH_KEY is configured; the local faster-whisper `transcriber` is the default offline path.

Official Kling direct API guidance for OpenMontage providers. Use before calling `kling_official_video`, `kling_official_image`, `kling_tts`, `kling_avatar`, or `kling_lip_sync`.

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax, Gemini Omni). Supports gateways: HeyGen API, fal.ai API, Kling official direct API, and the Gemini API (Gemini Omni Flash).

Generate and conversationally edit short videos with Google Gemini Omni Flash (`gemini-omni-flash-preview`). Use when: (1) iterating on a clip with natural-language edits instead of regenerating ("make the phone invisible, keep everything else the same"), (2) generating 3-10s 720p clips with synthesized audio, rendered on-screen text, or timecoded beats, (3) binding reference images to roles with <FIRST_FRAME>/<IMAGE_REF_N> prompt tags, (4) editing an existing uploaded video. Accessed via the `gemini_omni_video` tool using the project's GEMINI_API_KEY/GOOGLE_API_KEY — the same key as Imagen and Google TTS.

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax, Gemini Omni). Supports gateways: HeyGen API, fal.ai API, and the Gemini API (Gemini Omni Flash).

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.