Open Film Skills
Open Film Skills bundles 22 skills for AI film: screenwriting, direction, assets, storyboards, prompts and post-production.
- 129 ★ on the repository
- Last commit
- Apache-2.0
Minimal access
Why this level
- Modules lead an agent to launch image and video generation paid for by the user on the host side.
Install
- Works in
Manual install
python scripts/install_skill.py ai-storyboard-director --platform codexAfter `git clone https://github.com/62656456/ai-film-skills.git`; platforms `codex`, `claude-code`, `trae`, `codebuddy`.
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- Modules lead an agent to launch image and video generation paid for by the user on the host side.
This is third-party code. Review the repository files before installing.
What it does
Open Film Skills gives an agent a set of independent modules for short film and series with AI. Each module owns one stage and accepts materials already prepared: `director-agent` writes and diagnoses a screenplay and drafts a director plan, `ai-storyboard-director` builds storyboards and six-block video prompts, and `character-asset`, `scene-asset` and `prop-asset` prepare reference assets for people, places and props. Production modules exist too: `produce-ai-video` organizes generation, selection and editing and `whitebox-previs-executor` checks blocking in 3D. Three modules are experimental. Video models and accounts are not included, so the agent needs its own tools. The `install_skill.py` installer puts modules into Codex, Claude Code, Trae and CodeBuddy.
Who it is for. Authors of short films and series with AI who need a pipeline from idea to film where each stage can be taken separately.
Good fit when
- A readable screenplay and a diagnosis of scene causality are needed from an idea or novel.
- A finished screenplay must be broken into shots with camera, lighting and rhythm.
- Characters and places have to look the same across all shots of a series.
- Assets and prompts are needed for video generation with shots already chosen.
Not a fit when
- You need a finished film, and the video models are not part of the set.
- The task is outside film: an ad clip or a presentation.
- The agent has no tools for image and video generation.
Example request
Write a screenplay for a short scene from this idea, check the causality of actions and prepare a director plan for storyboarding.Limitations
The agent reads and runs the skills, while image and video generation must be connected separately. Modules are independent, but the heavy production workflow (generation, selection, editing) depends on host tools and permissions. Part of the documentation is in Chinese, with English guides available. The repository has a `COMMERCIAL_USE.md` file: read it together with the Apache-2.0 license before commercial use. The three experimental modules install separately with the `--experimental` flag.
How to disable. Delete the folders of the relevant modules from the agent skills directory. The installer does not overwrite existing files without `--force`, so roll back from a saved copy.
FAQ
How do I install a single module?
Clone the repository and run `python scripts/install_skill.py ai-storyboard-director --platform codex`, substituting the module and platform you need.
Which platforms does the installer support?
Codex, Claude Code, Trae and CodeBuddy, plus any directory through `--target`.
Must I install all 22 modules?
No, modules are independent. Pick the one that solves your stage and pass the result to the next.
Are video models included?
No, the set contains instructions for the agent. The host provides image and video generation.
How do I install an experimental module?
Add the `--experimental` flag, for example `python scripts/install_skill.py hard-sci-fi-visual-director --platform codex --experimental`.
Discussion
No questions or reviews yet.
Related
SkillsSeven AI video skills: promo film planning, scene and fight prompts, acting direction and generation task reliability checks.
A skill and CLI that let Claude Code or Codex make videos as web pages, with the Studio editor to change the result
The agent scripts, voices and draws a narrated documentary in code, with one continuous camera over photos, maps and cards.
A director skill for AI video: turns a script into a shot list, keyframes and motion prompts for Runway, Kling and Veo
A skill that walks a script to a finished film in stages: it fixes the format, then proposes director, camera and lighting.
A list of AI short drama skills plus a skill that picks three to five of them for your stage, video model and agent
README in short
The description splits work into five groups: screenplay and direction, assets, storyboard and camera, prompts and production, research. A table shows when to take each module and what it delivers.
README badge
Original SKILL.md
--- name: director-agent description: Create, revise, or diagnose screenplays and develop director treatments or pre-storyboard decisions covering causality, character action, dialogue, performance, visual storytelling, sound, editing, and optional AI-executable screenplay compilation. Exclude editing an existing image, static visual polishing, static character/scene/prop reference-image design, and shot expansion from an already approved director plan. Use for "导演Agent", "导演思维", "导演分析", "导演方案", "写剧本", "改剧本", "剧本编辑", "剧本诊断", "AI可执行剧本", "AI漫剧剧本", "人物弧光", "对白", "潜台词", "剧本影像化", "把故事电影化", "分镜前分析", "导演阐述", "director plan", "director's treatment", "screenplay", or "script writing". --- # Director Agent Write readable screenplays and make director decisions about story, performance, audience experience, image, sound and time. The requested artifact comes first. An approved director plan is an input to preserve; shot expansion from that plan belongs to the storyboard stage. ## Choose the work and load only its guidance Read the user's material, current scope, locked facts and relevant preceding state. Reuse unchanged references already read in this context. | Work | Required guidance | |---|---| | 写剧本、创作完整故事、substantial 改剧本 | `references/screenplay-writing-core.md`; after the readable draft, `references/screenplay-state-engine.md` for causality and inheritance | | 局部对白、one-scene repair | Relevant sections of `references/screenplay-writing-core.md` plus the affected source and adjoining state; load the state engine only if the repair changes knowledge, causality, a setup or payoff | | 剧本诊断 | Writing core and the state-engine sections relevant to the suspected break; locate the earliest failure before polishing symptoms | | Full screenplay or substantial quality calibration | Add `references/screenplay-exemplar-benchmarks.md`; examples are mechanisms, never plot or dialogue to copy | | 导演方案、导演分析、分镜前分析、创意镜头/转场思路 | `references/director-thinking-spine.md`; read `references/verified-director-logic.md` when the decision needs its detailed framework or source-sensitive premise | | AI可执行剧本、AI漫剧剧本 | Only after readable story and state verification, `references/screenplay-ai-execution-compiler.md`; preserve the readable master | | Full project, multi-scene continuity, or requested workbench | `references/director-workbench-protocol.md`; restore only the supplied project and relevant units | | Explicit 完整分镜 request | Resolve only missing director decisions and pass the selected plan to the available storyboard stage; when this Skill must deliver independently, use `references/production-storyboard-compiler.md` as its self-contained fallback | | Explicit independent audit or substantial script cold read | `references/screenplay-cold-read-protocol.md`; an isolated reader is independent only when explicitly available and allowed | | Large-scope coverage or suspected generic/shallow completion | `references/anti-laziness-contract.md` | | Current facts, disputed theory, named sources or platform capabilities | `references/research-update-protocol.md`; verify only the claims needed now | `references/local-knowledge-map.md` indexes bundled topics; `references/github-project-watchlist.md` is optional research context, not a routine dependency. All runtime references are inside this package. No private knowledge directory or sibling Skill is required. ## Write a story that can be understood Determine who wants what now, what blocks them, what they do, and what each consequence forces or permits next. A character must have a credible reason not to take an obvious safer, cheaper or easier alternative. Keep facts, assumptions and user decisions distinct; mark consequential additions `ASSUMED`. Draft from action and character strategy. Dialogue tries to make someone believe, reveal, do or stop something; motivated evasion, interruption, misunderstanding and silence are valid responses. Preserve distinct voices and imperfect speech. Do not manufacture symmetrical speeches, explanatory slogans, or a climax solution with no setup. After drafting, check relevant facts, knowledge, relationships, physical states and causal links. A twist or recurring object must change meaning, a choice or a result. State ledgers and cold-read labels do not generate the story or prove its quality. For a local line repair, preserve the scene's purpose and unaffected text; do not rebuild the film. ## Direct the audience's experience Make concrete decisions about whom the audience approaches, what they know relative to the characters, how attention changes and what remains at the end. Establish a material-specific image idea, playable actor actions and the sound/time/editing relations that express it. A motif is useful when its variation or payoff matters; do not require a motif or a prescribed number of images in every scene. Character objectives become behavior and spatial relations: approaching, withholding, conceding room, controlling an exit, refusing to sit or continuing to wait. Staging and photography work together. Do not equate emotions with fixed shot sizes, color recipes or camera movements. Include the place's operation in the design: relevant routes, activity, light and sound continue while the protagonists act. Quiet, stable light and deliberate stillness can be correct. Do not automatically add crowds, wind, rain or atmosphere particles. Separate world positions, changing action states and the image projected by a camera; reversing the camera does not move the world.