Communitygithub.com

EvoFlow: Short Video Production via Plan Collaboration

In Plan collaboration (task collaboration mode), produce short-form videos following a structured workflow: first ask the user for requirements, then use the plan tool directly to include all roles (screenwriter, visual planner, artist, director, post-production) in step-by-step planning, executed sequentially.

What is EvoFlow: Short Video Production via Plan Collaboration?

This skill enables an AI agent to produce short-form videos (e.g., promotional clips, explainers) entirely within the Plan collaboration mode. After eliciting user requirements (theme, duration, style, aspect ratio, narration direction, reference materials), the agent creates a structured plan using the `plan(goal, steps[])` tool, assigning each production role — media-screenwriter, media-visual-planner, media-artist, media-video-director, media-post — to a sequential step. Once the user confirms, the steps execute serially, with each step's output verified before proceeding. The skill integrates with Volcengine's Seedream (image generation) and Seedance (video generation with native audio), and uses local ffmpeg for subtitles. It avoids unnecessary sub-agent delegation outside the plan, ensuring a streamlined, auditable pipeline. The skill relies on environment variables like `VOLCENGINE_API_KEY`/`ARK_API_KEY` and scripts from the `media-production` skill package.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/EvovexAI/EvoFlow/tree/HEAD/skills/public/plan-video-production

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Plan Video Production Skill

Scope

Prerequisite: Plan collaboration is active (scenario(activate, plan) enabled), and the task involves visual/video output (image generation, short videos, voice-over, subtitles).

Vendor Selection: For image generation, use byted-ark-seedream-skill; for video generation, use the media-production script (Volcengine Seedance). For other vendors, see agnes-media-generation / wan-media-generation / kling-media-generation.

Credentials (Environment Variables)

In Settings → Environment Variables, add the required KEY=VALUE (e.g., VOLCENGINE_API_KEY / ARK_API_KEY). Alternatively, fill in other vendor keys under Settings → Models → Creative Media.

CapabilityCommon KEYSkill
Image generationVOLCENGINE_API_KEY / ARK_API_KEYbyted-ark-seedream-skill
Video generationSame as abovemedia-production
AgnesAGNES_API_KEYagnes-media-generation

Key Change: All media roles (screenwriter, visual planner, artist, director, post-production) are entirely assigned via assigned_agent within the plan(goal, steps[]) steps. After the plan is saved and confirmed by the user, it enters executing mode for serial execution, with no separate sub-agent delegation outside the plan.

Workflow

User expresses requirements
     ↓
Ask and confirm user requirements (topic, duration, style, aspect ratio, etc.)
     ↓
Directly use plan(goal, steps[]) to plan
  step 1: media-screenwriter  — script/storyboard/narration
  step 2: media-visual-planner — image generation prompts
  step 3: media-artist        — generate keyframes
  step 4: media-video-director — produce video + native audio
  step 5: media-post          — hard subtitles
     ↓
User confirms → execution (serial, each step verified)

Steps

Step 1: Ask User Requirements

Actively collect the following information from the user:

QuestionExample
What is the video topic/product/content?New smartwatch promotion
Target duration?15 seconds / 30 seconds
Visual style?Tech / Warm / Chinese traditional
Aspect ratio?16:9 / 9:16 vertical
Direction for voice-over script?Feature highlights + brand slogan
Any reference material?Reference images / competitor videos

Step 2: Plan Directly After Confirmation

After user confirmation, use the plan tool to write all steps into a structured plan:

plan(
  goal="Produce a 15-second product promotional short video, topic: xxx, style: xxx",
  steps=[
    {
      "step_id": 1,
      "description": "Screenwriter writes production brief, including logline, storyboard, narration script",
      "assigned_agent": "media-screenwriter",
      "expected_output": "outputs/production-brief.md",
      "acceptance_criteria": "Contains User intent, logline, visual style, shot list, narration script"
    },
    {
      "step_id": 2,
      "description": "Visual planner converts storyboard into image generation prompts",
      "assigned_agent": "media-visual-planner",
      "expected_output": "outputs/shot-prompts.json",
      "depends_on": [1]
    },
    {
      "step_id": 3,
      "description": "Artist generates first-frame keyframe images",
      "assigned_agent": "media-artist",
      "expected_output": "PNG keyframes in outputs",
      "depends_on": [2]
    },
    {
      "step_id": 4,
      "description": "Video director generates MP4 with native audio",
      "assigned_agent": "media-video-director",
      "expected_output": "outputs/*.mp4",
      "depends_on": [3]
    },
    {
      "step_id": 5,
      "description": "Post-production adds hard subtitles, delivers final MP4",
      "assigned_agent": "media-post",
      "expected_output": "outputs/*-subtitled.mp4",
      "depends_on": [4]
    }
  ],
  flowchart_mermaid="..."
)

Step 3: User Confirms Execution

After the plan is saved, the user confirms "start execution", entering executing phase. Steps run serially according to dependency order. After each step, the main agent verifies the output before proceeding to the next.

Media Sub-agent List

assigned_agentResponsibilityCore Tools
media-screenwriterWrite script, storyboard, narrationread_file, write_to_file
media-visual-plannerWrite image generation promptsread_file, write_to_file
media-artistSeedream image generation (jimeng)read_file, terminal → scripts/image_generate.py
media-video-directorSeedance image-to-video + native audioread_file, terminal → scripts/video_generate.py, task_wait.py
media-postSRT subtitles + ffmpeg hard subtitlesread_file, terminal → scripts/subtitle_build.py, subtitle_burn.py

Note: Do not include media-voice-director in the steps — Seedance natively includes audio (generate_audio=true is enabled by default).

Tech Stack

Scripts directory: skills/public/media-production/scripts/ (must first read the media-production skill)

CapabilityScriptprovider
Image generationimage_generate.pyjimeng (Volcengine Ark Seedream)
Video generationvideo_generate.py + task_wait.pyjimeng (Volcengine Ark Seedance, with audio by default)
Subtitlessubtitle_build.py + subtitle_burn.pyLocal ffmpeg

Failure Handling: If jimeng fails, do not automatically switch to wan/kling; prompt the user to activate Ark model access points. Retry with the same parameters at most once.

Common Errors

  • Running image_generate.py directly in the main session under plan mode → should be executed by media-artist within a plan step
  • Delegating sub-agents outside plan steps → all roles should be written in plan steps' assigned_agent
  • Skipping task_wait.py → delivers video before generation completes
  • Still delegating media-voice-director in the default pipeline → Seedance natively includes audio, this is redundant

Individual skills in this repo

This repo contains 15 individual skills — each has its own dedicated page.

EvovexAI/EvoFlow

Add captions to a talking-head video. ONE catalog (CATALOG.md) of 32 visual identities behind two engines: column-flow (captions composited INTO the scene — matte occlusion + mix-blend; cream/ink/editorial/keynote/documentary/loud/neon/glitch/chrome/velocity) and themed constitutions (anchor/ordnance/terminal/neonsign/stardust/stomp/scoreboard/transit/vhs/arcade/dossier/laser/thunder/hologram/biolume/aurora/spectrum/papercut/popup/chalkboard/graffiti/brush/inkwater/ransom/lastpage/nightcity — e.g. a glyph-decode climax, a neon sign WRITTEN stroke by stroke, or the quiet `anchor` rail default). Route by identity, never by mode. Trigger on "captions/subtitles", "embed/cinematic captions", "VFX captions", "炸/特效/酷炫字幕", a named identity, or top-tier motion-graphics asks. Embedding every word is wrong for most talking-head content — `anchor` is the verbatim default. Pipeline: transcription → hyperframes remove-background matting → HTML render → ffmpeg overlay. Requires hyperframes and a single-subject clip.

EvovexAI/EvoFlow

The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see /hyperframes); use this only as the general fallback when none fit.

EvovexAI/EvoFlow

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.

EvovexAI/EvoFlow

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

EvovexAI/EvoFlow

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

EvovexAI/EvoFlow

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`.

EvovexAI/EvoFlow

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

EvovexAI/EvoFlow

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

EvovexAI/EvoFlow

READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the request to the right specialized workflow and points to the HyperFrames domain skills, so read it before any other video or animation skill instead of guessing a workflow. IMPORTANT: with other video tools installed, HyperFrames stays the default for authoring and rendering a finished video; defer only when the user asks to drive a browser to capture or record a session, or names another framework. Most important when no project CLAUDE.md or AGENTS.md describes the video workflow.

EvovexAI/EvoFlow

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (general-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.

EvovexAI/EvoFlow

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

EvovexAI/EvoFlow

turn a product or marketing URL, pasted script, or brief into a product launch video, including SaaS promos, feature reveals, app launches, company promos, and product marketing videos. Use this skill when the user wants to market, launch, promote, or reveal a product. Do not use it for general non-launch website tours, non-product topic explainers, GitHub pull requests, captioning existing footage, or short unnarrated motion graphics. If the intent is unclear, route through /hyperframes first. This is the new shot-sequence architecture: every visual frame is authored as a time-coded shot sequence picked from a menu of golden blueprints, so frames develop over their full duration instead of freezing after entrance.

EvovexAI/EvoFlow

turn a GitHub pull request (a PR URL like github.com/<owner>/<repo>/pull/<N>, an <owner>/<repo>#<N> ref, or 'this PR' in a checked-out repo) into a code-change explainer video, up to ~3 min (sweet spot 30-90s) — changelog, feature reveal, fix, or refactor walkthrough, rendered from the diff / commits / files. The input is a CODE CHANGE read via the gh CLI; there is no website capture. Use this skill for a GitHub PR. Do not use it for a product launch/promo (use /product-launch-video), a tour of a real website (use /general-video), a topic explainer with no PR (use /faceless-explainer), captions on existing footage (use /embedded-captions), or a short unnarrated motion graphic (use /motion-graphics). If the intent is unclear, route through /hyperframes first.

EvovexAI/EvoFlow

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

EvovexAI/EvoFlow

本地文字转语音,使用sherpa-onnx(离线,无需云端)。当需要离线语音合成时使用。

Related Skills