Stats
Actions
Available In
Tags
Plugin
pai-pro
Build a filmmaking project inside Claude Code: write screenplays, design characters and locations, generate storyboard images and video clips, attach voice lines to characters, and organize everything on a local canvas with notes and semantic groups.
What's Inside
Skills7
add-note
/add-note
Appends a note node to the filmmaking canvas and links it to the previous note. Use when the user says "take a note", "annotate", "jot down", "save this", "remember that", or any phrasing that asks the agent to capture a short piece of text on the canvas.
groups-compose
/groups-compose
Designs and maintains semantic groupings of nodes on the filmmaking canvas — scenes, character-reference sets, act beats, and other reading-clarity frames. Use when nodes on the canvas cluster around a shared meaning (same scene, same character, same act, same production state) and would read more clearly with a titled frame around them. Don't force it — groups are a view concern, not an organizing tax.
image-compose
/image-compose
Generates or edits images on the filmmaking canvas via the local generate_image.js CLI, following the canvas-aware conventions for subtype stamping, reference wiring, and provenance edges. Use when the user asks to design a character, portrait, hero, or villain; design an establishing still of a script location or setting; edit, change, swap, add, or remove something in an existing canvas image; make a variation, turnaround, 3D version, or alternate-style version of an image; compose a scene featuring one or more existing characters; generate a standalone still unrelated to existing canvas content; or lay out a storyboard mosaic, shot list, keyframe sheet, or image previs from a script's shots and locations. STORYBOARD SHAPE — storyboard / mosaic / 分镜 / shot list / keyframe sheet / coverage / previs = ONE composite image with N×M panels per location, NOT N separate calls. Re-invoke this skill (Pattern 6) before firing the CLI.
script-compose
/script-compose
Handles screenplay work on the filmmaking canvas, only on explicit user intent (never on a file drop). Triages input as an official screenplay (use verbatim), a story or concept (iterate then rewrite at the target duration), or neither (defer to image/video skills). Captures the finalized script as a canvas note and sets the workflow title. Separately, on an explicit user command, splits the script into shot notes capped at 15 seconds each and offers to design character portraits plus location stills. Use when the user asks to write, adapt, or rewrite a script, story, or screenplay; to split a script into shots or clips; to extract or design characters or locations from a script; or to analyze or break down a canvas script. Preserves dialogue verbatim. Does NOT split or analyze without explicit user intent.
show-dag
/show-dag
Prints a compact rundown of the current canvas notes to chat. Use when the user says "what do we have", "show the graph", "list the notes", "summarize", or any phrasing asking for a rundown of what is currently on the canvas.
Stats
Version0.1.0
LanguageTypeScript
Stars6
Forks1
MaintenanceExcellent
Last Commit
Added
Available In
Tags
Technologies
Topics
Categories
