flora-mcp-skills: Skill for Claude Code

.agents/skills/flora-script-to-video/SKILL.md

flora-script-to-video is a skill for Claude Code from florafauna-ai/flora-mcp-skills. It costs 126 tokens per session (4,714 once invoked), scanned A, original, MIT.

A staged FLORA workflow that turns a script or story into animated clips. It first makes a shot list, then creates consistent still images for keyframes, and finally animates those keyframes.

In plain words
What is it for?
Use it to turn a narrative into ordered shots, approve the planned keyframes, and create animated clips through FLORA.
Why use it?
It prevents expensive animation work from starting before the shot plan and visual references are approved. This matters because an incorrect keyframe can lead to wasted animation work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is florafauna-ai/flora-mcp-skills's own configuration. It tells Claude Code how to work on flora-mcp-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flora-mcp-skills configures →

Part of the flora-mcp-skills plugin — 15 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to florafauna-ai/flora-mcp-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/florafauna-ai/flora-mcp-skills/main/.agents/skills/flora-script-to-video/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/florafauna-ai/flora-mcp-skills

Made for: Claude Code.

Or install flora-mcp-skills, the plugin that ships this one along with the rest of its 15 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for flora-script-to-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/florafauna-ai/flora-mcp-skills/flora-script-to-video/github.svg)](https://agentmods.dev/skills/florafauna-ai/flora-mcp-skills/flora-script-to-video)
Your own site
<a href="https://agentmods.dev/skills/florafauna-ai/flora-mcp-skills/flora-script-to-video"><img src="https://agentmods.dev/badge/skills/florafauna-ai/flora-mcp-skills/flora-script-to-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for flora-script-to-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/florafauna-ai/flora-mcp-skills/flora-script-to-video"><img src="https://agentmods.dev/badge/skills/florafauna-ai/flora-mcp-skills/flora-script-to-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.04714
Opus 5 $0.00063 $0.02357
Sonnet 5 $0.00025 $0.00943
Haiku 4.5 $0.00013 $0.00471

Measured 12d ago against content hash 0090ea9eeb03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

flora-script-to-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/flora-script-to-video/SKILL.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

flora-script-to-video

Attribution. Pass skill: "flora-script-to-video" on every FLORA call you make while running this skill — execute included — along with a skill_run_id you invent once when the run starts and reuse for the rest of it. Both are reporting only: they change nothing about the call or its result.

What it is

A staged pipeline, not a batch. A set of unrelated items can all be fired at once, because no item's result changes what any other item should be. This is the opposite case: the shot list decides what the keyframes are, and the keyframes are what the video stage spends its money animating.

That dependency is the whole design constraint, and it is a financial one. Measured on FLORA's current catalog:

cheapest still   t2i-flux-2-klein-4b     $0.004
cheapest motion  i2v-wan-2.2             $0.121   (measured, settled)
typical motion   i2v-kling-2.5           $0.327
                 i2v-seedance-pro        $0.347

A clip costs 30–90x its keyframe. So a keyframe that drifted off-style is not a wasted still — it is a wasted still plus the far more expensive clip built on top of it, discovered only after both are paid for. Every gate in this skill exists to catch a mistake while it is still worth $0.004 instead of $0.35.

The law

Never animate an unapproved frame. Each stage ends with the user looking at what it produced and saying go. The gates are the product; the generations are just what happens between them.

The three stages

1  SCRIPT    -> shot list      free          gate: user approves the list
2  SHOTS     -> keyframes      ~$0.004 each  gate: user approves the SET
3  KEYFRAMES -> clips          ~$0.12-0.35   deliver ordered clip URLs

Stage 1 — script to shot list

Free. Nothing is spent, so this is where to be generous with thinking.

Break the script into discrete shots. One shot is one continuous camera setup — when the camera cuts or the subject changes, that is a new shot. Give each:

Read the full file on GitHub · 422 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 422 lines · 126 tokens per session scan A 0090ea9eeb03

Subscribe to this mod's changes

flora-script-to-video is a skill published in the GitHub repository florafauna-ai/flora-mcp-skills (8 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 4,714 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens