SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

visual-skillssmixs/visual-skills

Translates "what to shoot" into prompts and storyboard structures that AI image/video models can execute directly,…

No ratings yet Rate this skill
Stars499
Forks64
Watchers499
Open Issues2

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/smixs/visual-skills.git

OverviewOverview

Key Features

Translates "what to shoot" into prompts and storyboard structures that AI image/video models can execute directly, solving inaccurate prompts and inconsistent style across multiple models. Key capabilities include: 1. Dramaturgy structure: breaks a narrative down by scene formula and beats, turning one idea into a shot sequence with setup, development and payoff so generated video has rhythm instead of flat narration; 2. Universal rules: 12 built-in rules unify shot language, composition and prompt phrasing so style does not have to be re-derived for every render; 3. One model file: consolidates a single model's invocation and prompt conventions into one model file, so switching models means editing one place while reusing the whole pipeline; 4. Task modules when needed: loads only the task module required at the moment, cutting irrelevant context so the agent stays focused on the current production task.

Use Cases

AI short film and ad storyboard scripting, text-to-image and text-to-video prompt writing, multi-model (Veo/Kling/Seedance/GPT-Image/Nano Banana) production pipeline orchestration, shot beat and narrative structure design.

Target Roles

Film/TV director & audio-video producer, content creator / social media operator, UI/UX & visual designer, product manager (PM).

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1932
Data sourceGitHub
Repositorysmixs/visual-skills
CategoryCreative Design & Content Generation / AI Image & Video Generation
Primary languageOther
LicenseCreative Commons Attribution 4.0 International
Default branchmain
GitHub repository ID1221303916
Node IDR_kgDOSMuebA
Rank#1268 (position within the source ranking)
Site-wide popularity rank#1445 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006002026-09-292026-10-112026-09-29 · 4552026-10-11 · 499
  • Now499
  • Previous point · 09-29 455
  • vs previous point +44
  • 2 data points 12 days
0204060802026-09-292026-10-112026-09-29 · 592026-10-11 · 64
  • Now64
  • Previous point · 09-29 59
  • vs previous point +5
  • 2 data points 12 days

TimelineTimeline

Repository created2026-04-26 02:46:336 months ago
Data last updated2026-10-26 12:11:3023 days ago
Last commit2026-09-16 13:21:462 months ago

CommitLatest commit

Version [latest] committed by smixs. Update Category: Codebase Iteration & Routine Maintenance. Commit details: image+video: de-slop, story-arc selection, timed storyboard grids, Style DNA + Reject Checklist, deck styles; video desc. This update updates core functional modules and advances project iteration.

92be33a vlatest smixs 2026-09-16

Next stepsNext steps