Results for “vision-scenarios”

Transform text plans into interactive visual documents with diagrams, code snippets, and review surfaces for coding agents.

Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes.

LongVA: Long Context Transfer from Language to Vision

当需要为某个生活领域或项目确立一个初步的、可迭代的积极方向时

Watch and understand video files by converting them to viewable image storyboards for enjoyment, analysis, species identification, behavior tracking, and comprehension

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Scaling Vision with Sparse Mixture of Experts

Expert real-time VFX artist specializing in particle systems, shader effects, and the invisible craft that makes games feel satisfying. Masters Niagara, VFX Graph, Godot GPU particles, and understands the AAA principles that make effects read clearly at 60fps. Use when "particle system, visual effects, vfx, particles, niagara, vfx graph, flipbook, sprite sheet, explosion effect, magic effect, trail effect, beam effect, dissolve, distortion, force field, hit effect, muzzle flash, impact effect, smoke particles, fire effect, soft particles, game juice, screen shake, particle overdraw, effect optimization, vfx, particles, effects, niagara, vfx-graph, game-juice, visual-effects, shaders, flipbook, trails, beams, explosions, optimization, gpu-particles" mentioned.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.

Build a visual sequence that proves, explains, and supports decisions.

Analyzes an existing Vue project's UI to map components, extract design tokens, and identify code patterns, then generates a project-specific contextual skill file for consistent future development.

Use when user flows already exist and the team needs a screen inventory, screen responsibilities, key states, and view hierarchy for a product or feature. Trigger on requests to break a flow into pages, views, or screen-level structure.

Draft or revise a scene on a goal-conflict-disaster spine with sensory grounding.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Brainstorm an inspiring, achievable, and emotional product vision that motivates teams and aligns stakeholders.

COCO: Microsoft COCO: Common Objects in Context

Generates structured usability test scenarios with realistic tasks, success criteria, and facilitation notes — ready to run with real participants or in a moderated session.

Skeptical pushback on visual placement — both density and quality. Reads the annotated outline plus the visuals manifest and asks (a) whether the article hits the density target from editorial-principles-visuals.md, (b) whether each [VISUAL:...] earns its place, (c) whether sections without one would benefit. One revision pass on FAIL (BLOG_AGENT_VISUALS_REVISION_BUDGET, default 1).

Voce e o precificador de features do REVERSA. Sua missao e cruzar o profile de cobranca do usuario com as metricas estruturais da feature ativa e produzir tres cenarios educativos em `_reversa_sdd/_pricing/<feature>/estimate.md` e `estimate.json`.

Generates diagrams and visuals from code or descriptions, routing to specialized tools for hand-drawn, formal, academic, or architectural output.

Draft a scene-by-scene video script with timing, visual direction, narration, and source attribution from upstream creator-media artifacts

Generate visual storyboards with AI image generation, covering shot types, camera angles, movement, continuity rules, and panel layout for video planning and pre-production.

Structured visual QA verdict for screenshot-to-reference comparisons

从思想性、艺术性、观赏性三维度评估影视剧本并打分。适用于剧本开发质量评估、修改方向确定、项目立项前审查

当需要明确个人或组织想要避免的未来状态，以激发行动力时

This skill provides guidance for video analysis and processing tasks using computer vision techniques. It should be used when analyzing video frames, detecting motion or events, tracking objects, extracting temporal data (e.g., identifying specific frames like takeoff/landing moments), or performing frame-by-frame processing with OpenCV or similar libraries.

Vision-language chat: VQA, captioning, image dialogue.