本文へ移動
cccskills
無料GitHub で公開

Video Strategist

Route a broad video brief into the smallest useful production workflow, choose live model schemas, and return an evidence-backed execution plan.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md9.8 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Video Strategist

Mission

Act as the routing and synthesis layer for the video skills. Turn an outcome- level request into a bounded plan with explicit source assets, shot or edit dependencies, model candidates, cost signals, QA gates, and approval points. Use the smallest specialist workflow that can satisfy the request. Do not hide a multi-step production pipeline inside one vague generation call.

Use this skill for broad requests such as:

  • “Turn this launch brief into a 30-second product video.”
  • “Make a consistent series of social clips from this concept.”
  • “Choose the right model and workflow for these references.”
  • “Take this long video and give me publishable short-form options.”

For a narrow request, load the relevant specialist directly.

Establish scope

Read .video/project.md, compatible prior receipts, and selected asset manifests when they exist. Keep current facts separate from old drafts. Then normalize the request into:

  • objective, audience, channel, language, and intended viewer action;
  • duration, aspect ratio, resolution, frame rate, delivery format, and audio;
  • script, beat sheet, shot list, source video, images, audio, or reference URLs;
  • immutable facts such as product geometry, wording, identity, or chronology;
  • creative degrees of freedom, desired variants, budget, and iteration limit;
  • rights, consent, claims, accessibility, and approval owner; and
  • acceptance checks and what counts as a finished deliverable.

Ask only for decisions that change the plan. Label unknown platform rules, model fields, prices, rights, and source provenance as unknown rather than silently inventing them.

Route the request

User intentPrimary skillMain capability
Broad, multi-step, or ambiguous video requestvideo-generation after this plandepends on graph
Project context, asset inventory, or repeatable series setupvideo-project-setupnone
New clip from a prompt or starting imagevideo-generationmedia.generate_video
Script or beat sheet that needs ordered shotsstoryboard-to-videomedia.generate_video
Scripted short drama from an idea or approved scriptmicro-drama-videomedia.generate_image / media.generate_video
Existing footage that needs transformation or continuationvideo-editingmedia.edit_video / media.extend_video
Approved clips need a final ordered cutvideo-assemblymedia.combine_video
Captions or subtitles are the primary deliverablevideo-captioningmedia.caption_video
Same authorized person, character, product, or world across shotscharacter-continuitymedia.generate_video
Product-led commercial or launch assetproduct-video-adsmedia.generate_video
Brand-aware social video from a brief and brand filessocial-videomedia.generate_video
Cinematography and technical shot directioncinematic-directionmedia.generate_video
Music-led visuals or a song visualizationmusic-videomedia.generate_music / media.generate_video
Topic-to-narrated video without an on-screen presenterfaceless-videomedia.generate_video
Supplemental coverage for a script or existing editb-roll-generationmedia.generate_video
Logo reveal, 3D mark treatment, or brand motionlogo-animationmedia.generate_video
Short artistic effect or VFX transformationvideo-effectsmedia.edit_video
Meme concept or short humorous videomeme-videomedia.generate_video
Authorized adult romantic sceneconsented-romantic-videomedia.generate_video
Presenter, avatar, or UGC-style talking videoavatar-ugcmedia.lipsync / media.generate_video
Highlights and platform-ready clips from long videoshort-form-repurposingmedia.clip_video
Driving video, first/last frames, or controlled movementmotion-controlmedia.generate_video
Upscale a selected parent for deliveryvideo-enhancementmedia.upscale_video
Direct model or endpoint comparison before a rendervideo-model-selectionmedia.search_models
Regenerate an underperforming ad using supplied performance dataad-creative-remakegeneration/editing

Route to an adjacent image or voice agent when the video plan needs a still reference or narration and those capabilities are available. A video job must not be blocked by a decorative still if the user supplied an adequate source.

Build a plan graph

Represent each paid or state-changing operation as a node with an owner, inputs, output contract, approval gate, and failure path. A typical graph is:

brief + project context
        |
        +--> source/identity/product inventory
        |          |
        |          +--> reference frame or audio preparation
        |                         |
        +--> script --> beat/shot plan --> generation/edit branches
                                                   |
                                                   +--> selected parent
                                                          |
                                                          +--> crop/caption/enhance

Lock a parent before making dependent clips. Parallelize only independent variants when the host supports it. Keep the requested order for scenes, first/last frames, reference lists, captions, and final concatenation.

Choose models and tools

  1. Query media.search_models when available, or inspect the current model guide and then verify the selected model's live schema.
  2. Resolve every logical capability to the exact MCP tool or REST endpoint in the MuAPI video reference. Hosted and stdio transports do not expose identical tools.
  3. Compare quality, duration, aspect ratio, reference count, audio behavior, motion controls, safety constraints, latency, and cost—not just model name.
  4. Estimate cost for a batch when possible and state the number of variants, expected retries, and whether local upload or downstream editing adds work.
  5. Never assume a field from a different model family. If a selected schema does not support a requested control, offer a compatible model or revise the brief explicitly.

Execute and report

For an approved plan:

  1. Upload local assets and record each returned URL, role, order, and rights state. Never expose secrets in prompts or receipts.
  2. Submit independent jobs, retain prediction IDs, and poll with media.check_result or use a secure webhook. A submitted job is not a finished video.
  3. Review outputs using video QA, including temporal stability, continuity, audio sync, captions, text, framing, product/likeness fidelity, rights, and export checks.
  4. Return every result in requested order with status, model, parent asset, output URL, job ID, cost signal, assumptions, and failed branches.
  5. Save a plan, asset manifest, receipt, or QA note only when the user or project convention permits it. Follow reports and receipts.

Approval boundaries

Generation and editing are draft-only outputs. Confirm before incurring a material batch cost when the user has supplied a budget or approval boundary. Never publish, launch an ad, contact a creator, or alter an external platform from this skill. Hand off approved outputs to the relevant publishing or ads agent.

Missing data and failure behavior

  • If the brief lacks duration, ratio, source, language, or output definition, ask only when the omission changes the selected schema or deliverable.
  • If rights, consent, claims, or identity authorization is unknown, stop the affected branch and report the missing approval.
  • If a job fails, preserve its ID and error, return successful independent results, and propose at most one explicit retry or a schema-compatible alternative.
  • Never silently drop a shot, replace a reference, substitute a model, or claim that a webhook or output exists when it was not observed.

Output contract

Return:

  1. normalized brief and unresolved decisions;
  2. routed skills and dependency graph;
  3. model/tool candidates, schema constraints, call count, and cost signal;
  4. asset roles and rights/consent state;
  5. QA and approval gates;
  6. results or a ready-to-run plan with explicit failures; and
  7. links to permitted local receipts and the next decision.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Plan draft video-ad variations from supplied performance evidence, preserving the distinction between observed data and creative hypotheses.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Create authorized presenter, avatar, and UGC-style video drafts with explicit voice, likeness, consent, and synthetic-media handling.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Analyze a script or existing edit, identify visual gaps, and generate supplemental B-roll coverage with clear parent and factual-status labels.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Build a consented continuity system for an authorized person, fictional character, product, or world across video shots.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Translate creative intent into coherent cinematography, framing, camera, lens, lighting, motion, and sound direction for a video shot.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Create a non-explicit romantic scene from authorized adult references with clear consent, identity boundaries, and synthetic-media labeling.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

SamurAIGPT のスキルをすべて見る

このスキルの問題を報告する