Supabase Development and Debugging
supabase/agent-skills
General Supabase skill for database, auth, Edge Functions, Realtime and storage work, plus client libraries, migrations, security audits, debugging and reading logs.
A skill your agent uses when turning a Calliope scene into a video job — chaining from a previous clip, ordering reference images, or picking duration settings.
Install Scene To Video
$ npx skills add benjiyaya/Calliope --skill scene-to-video -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install benjiyaya/Calliope scene-to-video --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/benjiyaya/Calliope.git skills-src && mkdir -p .claude/skills && cp -r skills-src/calliope-backend/skills_builtin/scene-to-video .claude/skills/scene-to-video && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "scene-to-video" agent skill from https://github.com/benjiyaya/Calliope/tree/main/calliope-backend/skills_builtin/scene-to-video into .claude/skills/scene-to-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-to-video", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/benjiyaya/Calliope/tree/main/calliope-backend/skills_builtin/scene-to-videoType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add benjiyaya/Calliope --skill scene-to-video -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install benjiyaya/Calliope scene-to-video --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benjiyaya/Calliope.git skills-src && mkdir -p .agents/skills && cp -r skills-src/calliope-backend/skills_builtin/scene-to-video .agents/skills/scene-to-video && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scene-to-video" agent skill from https://github.com/benjiyaya/Calliope/tree/main/calliope-backend/skills_builtin/scene-to-video into .agents/skills/scene-to-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-to-video", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add benjiyaya/Calliope --skill scene-to-video -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install benjiyaya/Calliope scene-to-video --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benjiyaya/Calliope.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/calliope-backend/skills_builtin/scene-to-video .cursor/skills/scene-to-video && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "scene-to-video" agent skill from https://github.com/benjiyaya/Calliope/tree/main/calliope-backend/skills_builtin/scene-to-video into .cursor/skills/scene-to-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-to-video", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/benjiyaya/Calliope.git --path calliope-backend/skills_builtin/scene-to-video--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add benjiyaya/Calliope --skill scene-to-video -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install benjiyaya/Calliope scene-to-video --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benjiyaya/Calliope.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/calliope-backend/skills_builtin/scene-to-video .gemini/skills/scene-to-video && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "scene-to-video" agent skill from https://github.com/benjiyaya/Calliope/tree/main/calliope-backend/skills_builtin/scene-to-video into .gemini/skills/scene-to-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-to-video", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install benjiyaya/Calliope scene-to-videoInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add benjiyaya/Calliope --skill scene-to-video -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/benjiyaya/Calliope.git skills-src && mkdir -p .github/skills && cp -r skills-src/calliope-backend/skills_builtin/scene-to-video .github/skills/scene-to-video && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "scene-to-video" agent skill from https://github.com/benjiyaya/Calliope/tree/main/calliope-backend/skills_builtin/scene-to-video into .github/skills/scene-to-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-to-video", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add benjiyaya/Calliope --skill scene-to-video -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install benjiyaya/Calliope scene-to-video --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benjiyaya/Calliope.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/calliope-backend/skills_builtin/scene-to-video .opencode/skills/scene-to-video && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "scene-to-video" agent skill from https://github.com/benjiyaya/Calliope/tree/main/calliope-backend/skills_builtin/scene-to-video into .opencode/skills/scene-to-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-to-video", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
scene-to-video- GitHub stars
- 242
- Token cost
- ~552 tokens
- SKILL.md length
- 280 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when turning a Calliope scene into a video job — chaining from a previous clip, ordering reference images, or picking duration settings.
- Works in 5 steps: Read the scene first — get_workspace or… → Prompt style follows the workflow's… → References fill slots in node-id order:… → …
- Turning a Calliope scene into a video job — chaining from a previous clip
- SKILL.md covers Overview, When to Use, The Flow and Failure Handling
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Scene To Video is an agent skill from benjiyaya/Calliope. Use when turning a Calliope scene into a video job — chaining from a previous clip, ordering reference images, or picking duration settings.
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Backend & APIs. It works with ComfyUI and SvelteKit. The repository describes itself as: Local-first AI Idea-to-video studio — FastAPI + SvelteKit + ComfyUI. The licence is MIT.
When your agent uses it
- Turning a Calliope scene into a video job — chaining from a previous clip
- Ordering reference images
- Picking duration settings
Example prompts
- “/scene-to-video”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read the scene first — get_workspace or list_scenes for the scene's
- Prompt style follows the workflow's prompt_profile — prose (flat
- References fill slots in node-id order: characters in scene order, then
- Continue scenes need the workflow to have an (Input:video) node. Auto
- Confirm before enqueue — use ask_user with scope:"render" when the
What it can do on your machine
Read from SKILL.md and the folder at commit 0a75919. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Scene To Video loads about 552 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 280 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from benjiyaya/Calliope at commit 0a75919, republished under its MIT licence (© benjiyaya). 280 words, ~552 tokens.
Download SKILL.mdSave it as
.claude/skills/scene-to-video/SKILL.md (or your agent's skills folder).- name
- scene-to-video
- description
- Use when turning a Calliope scene into a video job — chaining from a previous clip, ordering reference images, or picking duration settings.
- version
- 1.0.0
- license
- MIT
- metadata.author
- Calliope
- metadata.tags
- video, scenes, comfyui, minimax-h3, references
Scene to Video
Overview
Recipe for driving a scene through Calliope's video path: draft prompt → resolve references → enqueue → track the artifact. The machine contract (role tags, profiles) is enforced by Calliope; this skill is the judgment layer on top.
When to Use
- The user asks to generate video for one or more scenes
- A scene should continue from the previous clip (
chain_from_prev) - Reference ordering matters (which character/image is
<Subject 1>)
The Flow
- Read the scene first —
get_workspaceorlist_scenesfor the scene's draft text, characters in scene order, and location. Never enqueue from a summary alone. - Prompt style follows the workflow's
prompt_profile—prose(flat paragraph) orminimax_h3_ref(six-section, rewritten by an LLM at enqueue time). Don't hand-format H3 sections unless the user asked for a raw prompt; the profile owns the format. - References fill slots in node-id order: characters in scene order, then
the location, capped at the workflow's
(Input:image)slot count.<Subject 1>= lowest node id. If a specific character must be Subject 1, say so and let the user re-wire the data edges on the canvas. - Continue scenes need the workflow to have an
(Input:video)node. Auto mode takes the nearest earlier clip; if it doesn't exist, surface the error — don't retry blind. - Confirm before enqueue — use
ask_userwithscope:"render"when the user hasn't explicitly asked to generate. Thenenqueue_video_jobswith the scene_id, and track via the returned job ids.
Failure Handling
job.failedwith a Comfy node name in the error: report the node and its likely input gap (missing ref file, bad dimension pair).- Poll timeout: the queue may still be busy — check
get_workspacejob status before re-enqueueing; double enqueues waste GPU-hours.
© benjiyaya, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in calliope-backend/skills_builtin/scene-to-video of benjiyaya/Calliope.
Open the folder on GitHubat commit 0a75919
Compare with similar skills
Scene To Video next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Scene To Video this skillbenjiyaya/Calliope | 242 | — | ~552 | Automated safety check: Pass | MIT | |
| Supabase Development and Debuggingsupabase/agent-skills | 2.7k | 3 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Sanity Best Practicessanity-io/agent-toolkit | 188 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Comfyui Gatewaysickn33/agentic-awesome-skills | 47k | 2 repos | ~3.8k | Automated safety check: Notes | MIT | |
| Framework Adaptershashgraph-online/awesome-codex-plugins | 1.3k | — | ~2.9k | Automated safety check: Notes | Apache-2.0 | |
| Turnstile Spincloudflare/skills | 3k | 4 repos | ~7.2k | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
- Official
Sanity Best Practices
sanity-io/agent-toolkit
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints…
Comfyui Gateway
sickn33/agentic-awesome-skills
REST API gateway for ComfyUI servers. An agent skill from sickn33/agentic-awesome-skills.
Framework Adapters
hashgraph-online/awesome-codex-plugins
Official @dodopayments/ framework adapters that mount Checkout, CustomerPortal, and Webhooks route handlers.
- Official
Turnstile Spin
cloudflare/skills
Set up, repair, or migrate to Cloudflare Turnstile bot verification in an existing frontend and backend, including server-side Siteverify.
Sanity Best Practices
robotostudio/turbo-start-sanity
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and…
More from benjiyaya/Calliope
Shot Composer Blockout
benjiyaya/Calliope
A skill your agent uses when the user asks to build, pose, frame, or ANIMATE a 3D scene in Build Scene — characters, primitives, shot framing, keyframe motion, or exporting a blockout as a…
Calliope
benjiyaya/Calliope
Write finished Calliope story content — beats, cast, screenplay scenes, shot clips, continuity requirements — into an existing Calliope project through the calliope-cli bridge.
Character Consistency
benjiyaya/Calliope
A skill your agent uses when writing or improving character image prompts — sheets, portraits, and reference images that stay consistent across scenes.
H3 Video Prompt Enhancer
benjiyaya/Calliope
A skill your agent uses when making MiniMax H3 video prompts from media + ideas.
Related
Categories
Questions about Scene To Video
What does Scene To Video do?
A skill your agent uses when turning a Calliope scene into a video job — chaining from a previous clip, ordering reference images, or picking duration settings. Scene To Video is an agent skill from benjiyaya/Calliope. Use when turning a Calliope scene into a video job — chaining from a previous clip, ordering reference images, or picking duration settings.
When should I use Scene To Video?
Scene To Video fits situations like: turning a Calliope scene into a video job — chaining from a previous clip; ordering reference images; picking duration settings.
How do I install Scene To Video in Claude Code?
Run `npx skills add benjiyaya/Calliope --skill scene-to-video -a claude-code`. Or copy the skill folder (calliope-backend/skills_builtin/scene-to-video in benjiyaya/Calliope) into .claude/skills/scene-to-video in your project. Claude Code loads it when a task matches its description.
How do I install Scene To Video in Codex?
Run `npx skills add benjiyaya/Calliope --skill scene-to-video -a codex`. Or copy the skill folder (calliope-backend/skills_builtin/scene-to-video in benjiyaya/Calliope) into .agents/skills/scene-to-video in your project. Codex loads it when a task matches its description.
Can I use Scene To Video in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add benjiyaya/Calliope --skill scene-to-video -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scene-to-video, .gemini/skills/scene-to-video, .github/skills/scene-to-video and .opencode/skills/scene-to-video in your project.
What does Scene To Video need to run?
SKILL.md names no scripts, command-line tools or credentials: Scene To Video is instructions for the agent only.
Does Scene To Video access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Scene To Video safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Scene To Video use?
Scene To Video is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Scene To Video use?
About 552 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Scene To Video?
Skills that share tags, products or a category with Scene To Video: Supabase Development and Debugging (supabase/agent-skills, 2.7k stars), Sanity Best Practices (sanity-io/agent-toolkit, 188 stars), Comfyui Gateway (sickn33/agentic-awesome-skills, 47k stars) and Framework Adapters (hashgraph-online/awesome-codex-plugins, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Scene To Video?
benjiyaya (a GitHub user) maintains it in benjiyaya/Calliope, which has 242 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.
Source: benjiyaya/Calliope on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.