xianxia-cinematic-video-director
liyue-aigc/xianxia-cinematic-video-director
An expert cinematic video director skill focused on designing narrative-driven Eastern xianxia camera choreography, shot lists, and per-shot image-to-video prompts.
Overview
This skill acts as a professional director for Eastern xianxia cinematic videos, converting conceptual ideas, story outlines, reference images, or keyframes into coherent multi-shot production plans. It avoids generic slow zooms, instead tailoring pacing, camera movement, continuity locks, energy curves, and per-shot video generation prompts to serve narrative and emotional goals.
Capabilities
- ▸Story spine and energy curve creation
- ▸Multi-shot sequence and duration allocation
- ▸Camera choreography and shot grammar design
- ▸Continuity locking across characters, environments, and lighting
- ▸Per-shot image-to-video prompt generation
- ▸Reference video diagnosis and correction
Best for
Generating multi-shot video storyboards and per-shot prompts for xianxia narratives, Designing spatial continuity, camera movement, and speed curves for video generation models, Optimizing or correcting contradictory, physically implausible, or monotonous camera prompts, Diagnosing issues in existing xianxia video references such as spatial disorientation or repetitive motion
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Operates purely as a text-based guidance and planning skill with no intrinsic execution risks, arbitrary code execution, or external network requests.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.