Agent-first Creative Workspace
This repository also configures its own agents. See what nodetool tells them →
Skill Claude CodeCodex
Set the motion language for a piece before anything is animated — one easing family, one timing unit, one transition family, one stagger rhythm — and audit a timeline against it. Use when starting a title pass or a whole cut, when animation feels busy, cheap or inconsistent across shots, or when turning a brand or…
Skill Claude CodeCodex
Animate typography, clips and transitions on a NodeTool timeline, and check the result by looking at rendered frames. Use for title cards, kinetic text, lower-third motion, clip entrances and exits, transitions between shots, and track layering. Not for writing the copy, cutting the picture, or rendering video.
Skill Claude CodeCodex
Decide how something should move before you animate it — durations, easing curves, stagger offsets, weight, anticipation and follow-through, given as numbers ready to paste into a NodeTool timeline animation. Use when motion feels stiff, floaty, robotic or cheap, when picking a duration or an easing for an entrance…
Skill Claude CodeCodex
Turn confirmed track metadata into a shootable, beat-synced music-video treatment and NodeTool storyboard. Use for music videos and promos, not workflows, pipelines, or finished renders.
Skill Claude CodeCodex
Direct ElevenLabs speech, dialogue, sound effects and music — the bracketed audio tags v3 acts on and why the voice decides whether a tag lands, stability as the delivery dial, punctuation instead of SSML for pacing, the per-line dialogue format for several speakers, source-action-space sound-effect briefs with…
Skill Claude CodeCodex
Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and the seed-locked one-variable-at-a-time loop its sub-second latency makes practical. Use whenever the model id contains…
Skill Claude CodeCodex
Prompt OpenAI's GPT Image 2 — the five-slot Scene/Subject/Details/Use case/Constraints template it responds to, the change-versus-preserve shape for edits, labelled multi-image compositing, and how to get text on an image to render verbatim. Use whenever the model id contains gpt-image-2 (openai/gpt-image-2…
Skill Claude CodeCodex
Prompt MiniMax's Hailuo video line — the chronological beat order it animates from, the fifteen bracketed camera commands the Director endpoints accept and the three-per-bracket rule, when to switch promptoptimizer off, why there is no negative prompt to fall back on, and prompting the delta on image-to-video. Use…
Skill Claude CodeCodex
Prompt Kuaishou's Kling video line from 2.5-turbo onward — which version exposes a shot list, tagged elements, native audio and a CFG dial at all, one shot per entry in multiprompt rather than one paragraph, characters tagged @Element1/@Element2 so a face survives a cut, the labelled dialogue format native audio…
Skill Claude CodeCodex
Prompt MiniMax H3 — choosing between its text-to-video, first-and-last-frame and reference-to-video endpoints, assigning an explicit job to every reference image, clip and audio file, writing a timecoded shot list inside the prompt, art-directing the native stereo audio, and naming a change and its constraint together…
Skill Claude CodeCodex
Prompt Google's Nano Banana Pro image model — the art-director brief it plans against, the lock/change/amount/constraints shape every edit needs, and the patterns for typography, diagrams, product mockups and storyboards. Use whenever the model id contains nano-banana-pro (fal-ai/nano-banana-pro…
Skill Claude CodeCodex
Prompt Alibaba's Qwen-Image line for the typography work it is built for — quoting exact copy so the model stops inventing it, switching prompt expansion off before it rewrites your strings, describing layout in relative position and weight rather than point sizes, writing non-Latin scripts as characters, and…
Skill Claude CodeCodex
Prompt ByteDance's Seedance 2 video line — the Subject/Motion/Environment/Look/Camera/Audio formula, how dialogue in double quotes gets voiced and lip-synced, writing the sound mix instead of leaving it open, cutting between shots in one generation, the JSON beat-sheet brief that holds an arc across a whole piece, and…
Skill Claude CodeCodex
Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must not change before an edit, addressing up to ten references by content instead of by index, and the size to iterate at…
Skill Claude CodeCodex
Prompt Stability's Stable Audio line — the genre/instruments/mood/BPM order its training metadata expects, the TrackType and VocalType tags that separate music, stems and sound effects on Stable Audio 3, matching duration to what you described, which checkpoints guidancescale and step count actually affect, and…
Skill Claude CodeCodex
Prompt Google's Veo 3 video line — the five-element shot/setting/subject/action/dialogue structure, the cinematography vocabulary it reads directly, duration and aspect-ratio tradeoffs, the enhance-prompt and auto-fix preprocessors, and the fixes for visual drift, temporal inconsistency and audio mismatch. Use…
Skill Claude CodeCodex
Keep sound continuous across a multi-scene piece cut from generated video — why one clip per scene hard-cuts the audio at every boundary, when to write all the scenes into a single generation instead, the sound-design vocabulary that survives a provider's copyright filter, and how to check the length, the aspect ratio…
Skill Claude CodeCodex
Prompt Alibaba's Wan 2.6 across its three modes — text-to-video with a global style line plus timing-bracketed shots, image-to-video that describes only what changes over time, and reference-to-video that tags subjects as @Video1/@Video2/@Video3. Covers multishots formatting, the 800-character prompt budget, negative…
Skill Claude CodeCodex
Structure a trailer or teaser as eight audio-first beats — hook, setup, inciting incident, escalation, drop, climax, title, button — with a runtime-scaled timecode grid, event/reception shot pairs, a planted-and-harvested motif, and one unbroken music bed, then store it as a NodeTool storyboard with a character entity…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: