
to-storyboard
Use when complete, lineage-valid video scenes need to be translated into HyperFrames frame boundaries, shot moments, transitions, and timing before production.
- Installs
- 40
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/sugarforever/boring-video-studio --skill to-storyboard- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads to-storyboard automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
To storyboard
Turn SCENES.md and NARRATION.md into HyperFrames STORYBOARD.md. Scenes define events; the storyboard defines how the viewer sees them.
Process
- Recompute the beats, narration, and scenes artifact digests. Continue only when
NARRATION.mdpoints to the current beats andSCENES.mdpoints to the current beats and narration, with every stored artifact digest matching its file. Open the HyperFrames project and revision recorded bySCENES.md, then load/hyperframesand read its currentreferences/storyboard-format.md. That canonical contract is authoritative for the single currentSTORYBOARD.md. - Choose the HyperFrames frame boundary:
- start a new frame for a hard edit, independent transition, new visual world, materially different media source, or independently buildable unit;
- keep continuous camera movement and shared object state in one frame, describing its internal shot moments.
- Treat each HyperFrames frame as one buildable block. Within its narrative body, write an ordered
Shot momentslist at changes in viewpoint, shot scale, subject action, or information focus. Each moment declares:- moment ID and approximate offset;
- initial state → action → final state;
- camera and attention path;
- narration anchors, or
silent; - handoff to the next moment or frame.
- Use canonical metadata wherever the current contract already carries the meaning. Put the document-level
boring_source_scenes_digest,boring_source_narration_digest,boring_hyperframes_project,boring_hyperframes_revision, andboring_artifact_digestexactly once as unknown keys in the global YAML frontmatter, where the canonical parser preserves them underglobals.extra. Computeboring_artifact_digestas SHA-256 of the complete storyboard file after removing only that single digest line. Frame-level workflow extras, such asboring_scene_id, remain on their frames and never carry document digests or project identity. - Use the scene's world, hero, event, continuity, rhythm, and feasibility as constraints. Preserve the cognitive job from
BEATS.md.- Preserve each demonstration's exact content, truth mode, and visible code labels in the relevant shot moments. Do not upgrade an instructional reconstruction into apparent evidence.
- When a frame shows terminal-hosted code entry, shell commands, CLI output, database output, or a TUI, REQUIRED SUB-SKILL: Use
record-terminal. Carry its evidence-backed, seek-safe replay contract and selected visual treatment into the shot moments.
- Treat canonical HyperFrames fields as authoritative. A
boring_*extra supplements the contract; it never restates a canonical field. - Leave every new frame at
status: outline; planning does not create or claim an implementedsrc. Reference relevant scene proofs when a frame's composition depends on an already reviewed visual decision. HyperFrames production owns composition HTML and advances frames tobuiltoranimated. - Audit the sequence: every narration anchor is covered by one or more shot moments, the visual state supports the spoken idea at that moment, intentionally silent moments carry no anchor, frame boundaries follow the rules above, demonstrations preserve their declared truth and labels, and duration allocations fit the target. Treat timing as a plan until HyperFrames Studio confirms it against the built timeline.
- Carry forward the rendered-evidence decisions recorded by
SCENES.mdand project state. Record the current project identity and revision for continuity, but do not mutate the project or build an animatic in this stage.
Before presenting STORYBOARD.md or any later revision, follow ../boring-video/references/markdown-review.md. Review frame boundaries, shot moments, narration mapping, planned durations, and transitions in the authoritative Markdown. HyperFrames Studio later owns playable motion, timing, and transition review.
The storyboard is complete when every frame is an independently buildable outline, its shot moments fully describe the scene event, every narration anchor and planned transition is accounted for, the shared project identity and source revision are recorded, and the Markdown review completion criterion is satisfied. No playable animatic is required before /to-video begins production.
FAQ
What does the to-storyboard skill do?
Use when complete, lineage-valid video scenes need to be translated into HyperFrames frame boundaries, shot moments, transitions, and timing before production.
How do I install to-storyboard?
Run npx skills add https://github.com/sugarforever/boring-video-studio --skill to-storyboard in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/to-storyboard/ (personal) or .claude/skills/to-storyboard/ (project).
Which AI agents can use to-storyboard?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is to-storyboard safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains to-storyboard?
It is published by sugarforever in sugarforever/boring-video-studio. It has 40 recorded installs.
More from sugarforever/boring-video-studio
verysmallwoods-video
sugarforever/boring-video-studio
小木头的个人视频流水线。基于一个主题,一篇文章,或一份口播稿,生成一整套可发布物料:视频成片,封面图,YouTube/Bilibili 文案,博客,以及社交媒体推广文案。视频制作采用 HyperFrames。
to-scenes
sugarforever/boring-video-studio
Open the skill to read its SKILL.md instructions.
boring-video
sugarforever/boring-video-studio
Use when developing a content-driven video from a topic, research bundle, article, or draft, or when routing an existing script or non-argument video into HyperFrames production.
to-video
sugarforever/boring-video-studio
Use when approved video-planning artifacts must be handed to HyperFrames for production, with optional ListenHub narration.
to-narration
sugarforever/boring-video-studio
Use when writing or revising spoken narration from complete, lineage-valid video beats, including scripts that must remain open to later visual direction.
to-spec-beats
sugarforever/boring-video-studio
Use when an approved content article needs to be reorganized into the factual and narrative architecture for a narrated video.
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image