Create, track and update team goals + KPIs via the Deeplake virtual filesystem at memory/goal/ and memory/kpi/. Use whenever the user mentions a goal, objective, KPI, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.

AI 电影/短剧解说视频自动生成（AI 解说大师 CLI Skill）。当用户需要创建电影解说视频、短剧解说、影视二创、AI 配音旁白视频、film commentary、video narration、drama dubbing、movie narration 时触发。内置电影素材库、BGM、多语种配音、解说模板。通过 narrator-ai-cli 命令行实现：搜片→选模板→选 BGM→选配音→生成文案→合成视频的全流程自动化。CLI client for Narrator AI video narration API.

Use for recurring characters, props, creatures, costumes, and environments that must keep stable identity across multi-shot generation, world assets, and continuation runs.

Use for shot-by-shot planning, storyboard generation, camera coverage, blocking, and precise visual sequencing for multi-shot videos.

Use for requests that need precise shot-size vocabulary, angle selection, narrative framing logic, and coverage phrasing for storyboards and prompts.

Use for short-drama, trailer, and retention-first storytelling that must land a hard hook in the first 1-3 seconds and keep escalation pressure inside each clip.

Use for Seedance 2.0 video generation, image-to-video, video-to-video extension, ordered multimodal @video/@image reference prompting, prompt review, continuity enforcement, and engineered 15-second video prompts.

Use for screenplay, scene writing, dialogue formatting, beat outlines, and any request that should produce structured script text compatible with Fountain syntax.

Use for actor blocking, spatial staging, movement through frame, and dynamic scene geography in dialogue, action, or ensemble scenes.

Use for image-to-video, reference-video continuity, keyframe-driven prompting, camera control, and consistency workflows based on official Runway, Kling, and character/style reference patterns.

Use for high-control film and video prompting that must combine a stable world bible, reference placeholders, real-photography fidelity, sound policy, genre fusion, and shot-level execution into one reusable creative template.

Use for ongoing multi-shot, episodic, sequel, or continuation work that needs strong character, environment, prop, and tone consistency over time.

Use for lighting mood design, contrast control, shot-to-shot lighting continuity, and visual tone consistency across sequences.

Use for location-first, no-human, and scene-bible workflows that need stable environment naming, spatial continuity, lighting logic, and clean world extraction without character contamination.

Use for requests that need strong cinematic taste, directing logic, camera language, lighting strategy, lens intent, composition, and premium visual tone.

Use for dialogue scenes, emotional performance beats, actor blocking, lip-sync-driven moments, and character interaction with clear emotional progression.

Use for shot sequencing, axis preservation, 180-degree rule awareness, match-on-action design, and smooth visual continuity between cuts.

Use for advertisements, branded films, and product storytelling that need audience hook logic, benefit framing, desire construction, and concise conversion-oriented visual messaging.

Use for story-driven film, trailer, short drama, adaptation, or multi-shot video requests that need strong narrative escalation, beat design, and production-ready scene structure.

Use for combat, chase, transformation, impact-heavy, or high-kinetic action video prompts that need 15-second temporal slicing, exact hit marks, physical feedback, non-centered camera choreography, and cinematic impact readability.