Agent skill

Storyboard Cheatcode

by alecs5am in alecs5am/ralphy

Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render.

MITAuto-check passedMedia & Creative

Install Storyboard Cheatcode

skills CLI
$ npx skills add alecs5am/ralphy --skill storyboard-cheatcode -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alecs5am/ralphy storyboard-cheatcode --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alecs5am/ralphy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/notes/skills/storyboard-cheatcode .claude/skills/storyboard-cheatcode && rm -rf skills-src

Use ~/.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/

Facts

Skill name
storyboard-cheatcode
GitHub stars
136
Token cost
~2k tokens
SKILL.md length
1,075 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render.

  • Works in 7 steps: CONCEPT — one sentence describing the… → ASPECT RATIO — 16:9 (default), 9:16, or… → NUMBER OF PANELS — 4, 6 (default), or 9 → …
  • The user asks to build a storyboard
  • SKILL.md covers Skip to a cheap preview video… and Remaining balance
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Storyboard Cheatcode is an agent skill from alecs5am/ralphy. Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render. Uses the Higgsfield MCP server (image and video tools). Asks the user before every render and never assumes budget tolerance. Use when the user asks to build a storyboard, plan AI video shots, generate a previs sheet, or wants an AI video from a concept.

Its SKILL.md is about 2k 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 Media & Creative, covering Comics and storyboards and AI video generation. It works with Model Context Protocol. The repository describes itself as: Open-source desktop app for content creation, with an agent runtime and standalone CLI. The licence is MIT.

When your agent uses it

  • The user asks to build a storyboard
  • Plan AI video shots
  • Generate a previs sheet
  • Wants an AI video from a concept

Example prompts

  • “/storyboard-cheatcode”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. CONCEPT — one sentence describing the scene or sequence
  2. ASPECT RATIO — 16:9 (default), 9:16, or 1:1
  3. NUMBER OF PANELS — 4, 6 (default), or 9
  4. PANEL ART STYLE — photoreal cinematic (default), manga, noir ink, hand-drawn storyboard, Pixar warmth, or your own
  5. FACE / CHARACTER REFERENCE — image URL or uploaded image (or "none")
  6. PRODUCT / OBJECT REFERENCE — image URL or uploaded image (or "none")
  7. HARD NEGATIVES — anything that must NOT appear (e.g. "no weapons", "no on-screen text")

What it can do on your machine

Read from SKILL.md and the folder at commit 8d139f0. 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

    Links to these hosts (documentation or services it may open):

    • mcp.higgsfield.ai

    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

Storyboard Cheatcode loads about 2k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 1,075 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 alecs5am/ralphy at commit 8d139f0, republished under its MIT licence (© alecs5am). 1,075 words, ~1,960 tokens.

Download SKILL.mdSave it as .claude/skills/storyboard-cheatcode/SKILL.md (or your agent's skills folder).
name
storyboard-cheatcode
description
Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render. Uses the Higgsfield MCP server (image and video tools). Asks the user before every render and never assumes budget tolerance. Use when the user asks to build a storyboard, plan AI video shots, generate a previs sheet, or wants an AI video from a concept.
license
MIT

Storyboard Cheatcode

name: storyboard-cheatcode description: Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render. Uses the Higgsfield MCP server (image and video tools). Asks the user before every render and never assumes budget tolerance. Use when the user asks to build a storyboard, plan AI video shots, generate a previs sheet, or wants an AI video from a concept. storyboard-cheatcode A previs-first AI-video pipeline. You generate a multi-panel storyboard image, then offer escalating render tiers — cheap preview first, hero render only on confirmation. All generation runs through the Higgsfield MCP server.

Operating principle — always ask, never guess Every step begins by asking the user. Do not pre-fill creative choices, do not infer budget tolerance, do not chain steps without explicit confirmation.

Renders cost real credits (~7 per storyboard image, ~50–70 per 12s 720p Seedance clip). The user is the creative director; you are the operator. Iterating cheaply on the storyboard image before any video render is the single biggest cost saver. Prerequisite The user must have the Higgsfield MCP connector added to Claude. If the Higgsfield tools (e.g. higgsfield_generate_image, higgsfield_generate_video) are not available in this session, stop and tell the user:

Add the Higgsfield connector first: Settings → Connectors → Add custom MCP → URL: https://mcp.higgsfield.ai/mcp. Sign in with your Higgsfield account when prompted.

Then re-run the skill.

Step 1 — Collect inputs (one batched ask) Ask the user for all of these in a single message. Do not ask one at a time. Mark each clearly:

  1. CONCEPT — one sentence describing the scene or sequence
  2. ASPECT RATIO — 16:9 (default), 9:16, or 1:1
  3. NUMBER OF PANELS — 4, 6 (default), or 9
  4. PANEL ART STYLE — photoreal cinematic (default), manga, noir ink, hand-drawn storyboard, Pixar warmth, or your own
  5. FACE / CHARACTER REFERENCE — image URL or uploaded image (or "none")
  6. PRODUCT / OBJECT REFERENCE — image URL or uploaded image (or "none")
  7. HARD NEGATIVES — anything that must NOT appear (e.g. "no weapons", "no on-screen text") When their answers come back, echo a one-line plan summary and ask explicitly: "Ready to generate the storyboard sheet?" Do not proceed without a yes.

Step 2 — Generate the storyboard sheet Build a single prompt that:

Names the grid explicitly: "A {N}-panel storyboard previs sheet, laid out as a {rows}×{cols} grid on a black background with thin white panel borders. Each panel labeled in clean white sans-serif text in the bottom-left corner ('SHOT 1' through 'SHOT {N}') with a short scene title." Describes each panel in 1–2 sentences. Always include the camera angle per panel (wide establishing / medium / close-up / low hero angle / over-shoulder / etc). Lists negatives under a HARD RULES: block, spelled out explicitly. Ends with: "ONE single image — the entire {N}-panel sheet in one composition, {aspect}. Each panel {style}." Call the Higgsfield MCP image tool. Use gpt_image_2 as the model (best for grids, text, detail). Pass any provided reference images.

higgsfield_generate_image( model = "gpt_image_2", prompt = "<full storyboard prompt>", aspect_ratio = "<aspect>", resolution = "2k", quality = "high", reference_images = [<face-ref-if-provided>, <product-ref-if-provided>] ) The MCP returns a job_id. Immediately call higgsfield_wait_for_job(job_id) and wait for the result URL.

Show the resulting image to the user. Then ask:

  • Regenerate with feedback (tell me what to change)
  • Generate an end-frame anchor (lock the final shot of the video)
Show full SKILL.md (533 more words)Show less

Skip to a cheap preview video render

Done — keep the sheet only Step 3 — Generate an end-frame anchor If the user wants to lock in the final shot (e.g., a specific triumphant pose, product reveal):

  • Prompt for the final shot, using the storyboard as a reference to maintain consistency.
  • If the storyboard doesn't capture the detail needed, describe the final scene in detail, referencing the knight/product assets.
  • Call Higgsfield generate for this still.
  • Wait for the job, show the result. Ask: "End-frame land the destination? (1) regenerate, (2) proceed to preview render, (3) keep the still only."

Step 4 — Cheap preview render (Seedance 2.0 at 480p) Only on confirmation. Default to 480p — half the credits, mobile-feed-authentic.

Before calling, run higgsfield_check_cost with the same parameters and report the estimate. If the estimate exceeds 100 credits, stop and confirm again before submitting.

Build a Seedance prompt as a single paragraph with bracketed timecodes — e.g. "(0–2s) wide establishing shot of... (2–4s) cut to medium... (4–5s) close-up of...". Narrative prose, not bullet points.

higgsfield_generate_video( model = "seedance_2_0", prompt = "<beat-by-beat prompt with timecodes>", aspect_ratio = "<aspect>", resolution = "480p", duration = <5 | 8 | 10 | 12>, genre = "<auto | epic | action | drama | comedy | noir | horror>", start_image = <storyboard-sheet-url-from-step-2>, end_image = <end-frame-url-from-step-3-if-generated>, reference_images = [<product-ref-if-provided>] ) Get the job_id, call higgsfield_wait_for_job(job_id), show the resulting MP4.

Ask: "Preview look right? (1) commit to 1080p hero render at this duration, (2) tweak the prompt and re-preview, (3) try Kling 3.0 Pro instead, (4) done — preview is enough."

Step 5 — Hero render (1080p) Only on confirmation. Same call as Step 4 but resolution = "1080p". Honor the duration the user already validated.

If the user picked Kling 3.0 Pro: use model = "kling3_0". Kling only accepts start_image and end_image (no separate reference_images array) — make sure the product look is already locked into those frames.

Run higgsfield_check_cost first, report the estimate, and confirm again before submitting if it exceeds 200 credits.

Wait for the job, show the final MP4. Then call higgsfield_get_credits and report:

Remaining balance

Total credits spent across this session (sum the costs of every generate call you made) Defaults and guardrails Always pass the face reference twice when identity drift is a risk — once in reference_images, and again called out in the prompt body: "use the attached face image as the EXACT identity reference; preserve facial features, beard line, eye shape, nose, lip shape exactly." Render storyboard sheets at 2k, not 4k — panels are small; 4k adds cost without resolvable detail. Never recommend Sora as a fallback — discontinued. Never auto-fire a video render. The user controls every render. Always run higgsfield_check_cost before video calls — confirm if estimate exceeds 100 credits (preview) or 200 credits (hero). Common failure modes (warn proactively) Generic-looking product in the final shot → the product reference wasn't attached, or no end-frame anchor was generated. Recommend Step 3. Identity drift across cuts in the video → face reference wasn't passed, or wasn't doubled-up in the prompt body. Random extra shot at the end of a long Seedance clip → duration was too long for the prompt's beats. Shorten the duration or add more beats. Wrong watch / wrong logo / wrong garment in the destination shot → the model invented because it wasn't shown. Build the destination as a still first, pass it as end_image.

© alecs5am, 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 notes/skills/storyboard-cheatcode of alecs5am/ralphy.

Open the folder on GitHubat commit 8d139f0

Compare with similar skills

Storyboard Cheatcode 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.

Storyboard Cheatcode compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Storyboard Cheatcode this skillalecs5am/ralphy136—~2kAutomated safety check: PassMIT
Generate StoryboardArcReel/ArcReel5.4k—~816Automated safety check: PassAGPL-3.0
Music Videoguaardvark/guaardvark255—~774Automated safety check: PassMIT
Seedance2 APIaiskillstore/marketplace430—~3.7kAutomated safety check: PassMIT
Video ComposeUtopai-Research/pai-code3541 repos~4.1kAutomated safety check: PassCustom licence
Scroll Promo Site Builderkangarooking/kangarooking-skills657—~2.6kAutomated safety check: PassMIT

Similar skills

  • Generate Storyboard

    ArcReel/ArcReel

    为分镜生成分镜图。当用户说"生成分镜"、"预览分镜画面"、想重新生成某些分镜图、或剧本中有分镜缺少分镜图时使用。自动保持角色和画面连续性。

    5.4k GitHub stars~816 tokensUpdated today
    Media & CreativeAuto-check passed
  • Music Video

    guaardvark/guaardvark

    Turn a song into a beat-synced music video with Guaardvark's Director: song analysis, per-cut shot prompts, storyboard keyframes, image-to-video renders, cuts on the beat.

    255 GitHub stars~774 tokensUpdated today
    Media & CreativeAuto-check passed
  • Seedance2 API

    aiskillstore/marketplace

    Out-of-the-box Seedance 2.0 API skill — just one API key to generate AI videos.

    430 GitHub stars~3.7k tokensUpdated today
    Media & CreativeAuto-check passed
  • Video Compose

    Utopai-Research/pai-code

    Generates and prompts video clips on the filmmaking canvas. An agent skill from Utopai-Research/pai-code.

    354 GitHub starsUsed in 1 repo~4.1k tokens
    Media & CreativeAuto-check passed
  • Scroll Promo Site Builder

    kangarooking/kangarooking-skills

    Create a scroll-controlled cinematic product website with rich motion (动效网站) from product materials, reference pages or videos, and brand assets.

    657 GitHub stars~2.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Motion Graphics Music Video

    makevoid/motion-graphics-music-video-skill

    Create and revise animated character music videos from a supplied song and creative prompt, with researched storyboards, Fal character and video generation, p5 motion graphics, audio editing, and…

    140 GitHub stars~3.3k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed

More from alecs5am/ralphy

All 28 skills in this repo
  • Gsap

    alecs5am/ralphy

    GSAP animation reference for HyperFrames. An agent skill from alecs5am/ralphy.

    136 GitHub stars~2.4k tokensUpdated 15 days ago
    Auto-check passed
  • Researcher

    alecs5am/ralphy

    Deep-research workflow for UGC reference material — turns one or more URLs / handles / trend queries into a single cited research report (report.md + sources.json) that a scenarist or art-director…

    136 GitHub stars~1.9k tokensUpdated 15 days ago
    Auto-check passed
  • Editor

    alecs5am/ralphy

    Composition and render craft — assembles scenario.json plus asset-manifest.json into a HyperFrames HTML composition and renders the mp4.

    136 GitHub stars~3.6k tokensUpdated 15 days ago
    Auto-check passed
  • Evaluator

    alecs5am/ralphy

    Quality evaluation of rendered UGC mp4s — scene segmentation, audio loudness / dead-air, caption density, and per-scene visual analysis.

    136 GitHub stars~3.6k tokensUpdated 15 days ago
    Auto-check passed
  • Producer

    alecs5am/ralphy

    End-to-end orchestration — the wrapper that drives the whole production contract across roles, plus batch production.

    136 GitHub stars~4.7k tokensUpdated 15 days ago
    Auto-check passed
  • Scenarist

    alecs5am/ralphy

    Scenario and script craft — writes and reworks the scene-by-scene scenario.json: hook, beat structure, per-scene VO, on-screen text, pacing, and the language/aspect pre-flight.

    136 GitHub stars~3.2k tokensUpdated 15 days ago
    Auto-check passed

Questions about Storyboard Cheatcode

What does Storyboard Cheatcode do?

Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render. Storyboard Cheatcode is an agent skill from alecs5am/ralphy. Turn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render.

When should I use Storyboard Cheatcode?

Storyboard Cheatcode fits situations like: the user asks to build a storyboard; plan AI video shots; generate a previs sheet; wants an AI video from a concept.

How do I install Storyboard Cheatcode in Claude Code?

Run `npx skills add alecs5am/ralphy --skill storyboard-cheatcode -a claude-code`. Or copy the skill folder (notes/skills/storyboard-cheatcode in alecs5am/ralphy) into .claude/skills/storyboard-cheatcode in your project. Claude Code loads it when a task matches its description.

How do I install Storyboard Cheatcode in Codex?

Run `npx skills add alecs5am/ralphy --skill storyboard-cheatcode -a codex`. Or copy the skill folder (notes/skills/storyboard-cheatcode in alecs5am/ralphy) into .agents/skills/storyboard-cheatcode in your project. Codex loads it when a task matches its description.

Can I use Storyboard Cheatcode 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 alecs5am/ralphy --skill storyboard-cheatcode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/storyboard-cheatcode, .gemini/skills/storyboard-cheatcode, .github/skills/storyboard-cheatcode and .opencode/skills/storyboard-cheatcode in your project.

What does Storyboard Cheatcode need to run?

SKILL.md names no scripts, command-line tools or credentials: Storyboard Cheatcode is instructions for the agent only.

Does Storyboard Cheatcode access the network?

SKILL.md names 1 domain. As links in the text: mcp.higgsfield.ai. This is read from the text; nothing was executed.

Is Storyboard Cheatcode 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 Storyboard Cheatcode use?

Storyboard Cheatcode 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 Storyboard Cheatcode use?

About 2k tokens (SKILL.md is roughly 7.8k 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 Storyboard Cheatcode?

Skills that share tags, products or a category with Storyboard Cheatcode: Generate Storyboard (ArcReel/ArcReel, 5.4k stars), Music Video (guaardvark/guaardvark, 255 stars), Seedance2 API (aiskillstore/marketplace, 430 stars) and Video Compose (Utopai-Research/pai-code, 354 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Storyboard Cheatcode?

alecs5am (a GitHub user) maintains it in alecs5am/ralphy, which has 136 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on September 22, 2026.

Source: alecs5am/ralphy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.