Noustiny

Produce a cast sheet of 1–4 named characters from a story seed. Each entry has a canonical-but-IP-free visual description and a hero-portrait prompt ready to drop into a text-to-image model. Downstream: portraits become the reference frames every subsequent beat image will condition on, locking character consistency across the whole storyboard. Fires once per story at canvas-enter, after story-copyright-detector.

Pick the narrator persona for a story and emit a YouTube search query that will surface a clean speaking-voice reference clip for `voice_sample_builder` to fetch. Returns {persona_label, search_query, fallback_query, reasoning} as strict JSON. Designed for SINGLE-NARRATOR storytelling (one voice carries the whole reel) — not multi-cast dialogue. Critical guarantee: search queries MUST use narration/prologue/monologue/interview/audiobook modifiers, NEVER scene/fight/battle/action — the latter surface drama clips with screams and music that diarization cannot rescue.

Branching story chat — checkpoint-scale. Kritik anlara atlayan story flow.

Decide whether a downstream narrative beat still makes sense after an upstream insertion. Returns a three-way verdict — still_valid, needs_rewrite, or must_delete — with a one-sentence reason and a severity score. Use when reharmonising a story graph: for each downstream node, call once with the inserted beat and the node under review. Strict JSON output, no prose, no tool calls.

Adjudicate a rewritten narrative beat against the insert that triggered it and the original beat it replaces. Returns strict JSON with an approved boolean, a score between 0 and 1, and a one-sentence reason. This is the final gate in the reharmonize chain before a rewrite becomes canon. No prose, no tool calls.

Rewrite a downstream narrative beat so it is consistent with a newly inserted upstream beat while preserving its original purpose in the canon. Input carries the insert, the node under rewrite, and the critic's reason for flagging it. Returns strict JSON with title, summary, body, imagePrompt, mood, and a short reason explaining what changed and why. No prose, no tool calls.

Compare a rendered narrative image against the beat's intent (title + body + prior canon). Flag faithfulness failures so the image pipeline can re-render with correction. Returns strict JSON {approved, score, issues, fix_hint}. No prose, no tool calls.

Flesh a single-sentence author intent into a full Detroit-style narrative beat that splices into an existing canon path. Returns strict JSON with title, summary, body, imagePrompt, mood, tone, and worldPercent. Use when the user is inserting a beat between two known story nodes and has typed a short intent describing what should happen there. No prose, no reasoning, no tool calls.

Seal a canon path into flowing prose. Given the ordered list of canon beats, write the story as continuous present-tense prose — scene by scene, with tonal continuity and motif carry-through. Output is prose, not JSON. Use when the user asks to write the story, seal the canon as prose, render the canon path, or compile the final read. Do not emit any tool calls, JSON, or XML tags.

Reveal the scene-and-act structure already present in a branching story tree. Groups every node into a scene, labels each scene with a story-specific title, assigns an act number, and names a one-word motif. Returns strict JSON. Use when the user asks to compose scenes, group beats into scenes, organise into acts, or build the three-act skeleton over an existing tree.

Classify a story seed by its intellectual-property weight so downstream image pipelines can pick the right render strategy. Returns {ip_level: known|inspired|original, franchise, model_preference: flux-photoreal|gemini-stylised} as strict JSON. Known franchises (Marvel, Star Wars, Harry Potter, GoT, Avatar, DC, LOTR, Anime) trigger the FLUX + moderation-rewriter ladder because their vocabulary sets off BFL/Google safety filters. Original stories get sent straight to Gemini/Nano Banana — cheaper, faster, stylised, no filter dance required. Use once per story, at canvas-enter time.

Decide cinematic intro parameters for the Noustiny storybook tool. Given a story title, snapshot path beats and an image count, choose the right pace, tone, transition and duration so the opening montage matches the story's energy. Use this skill whenever the noustiny_storybook tool is being invoked in audiobook mode and any of intro_pace, intro_tone, intro_transition, intro_duration_secs are left for the agent to decide.

Rewrite a narrative beat into a rich photoreal visual description suitable for text-to-image models. Strips every named intellectual-property reference and replaces each character / prop / place with a precise physical description. Output is strict JSON — one ≤60-word prompt (≤90 for climax beats), zero IP names, built for FLUX / Nano Banana / SeeDream.