Borrowing it
Nothing to install: this file belongs to cacity/VideoHub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cacity/VideoHub/main/.agents/skills/videohub-film-commentary/SKILL.mdgit clone --depth 1 https://github.com/cacity/VideoHubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cacity/videohub/videohub-film-commentary)<a href="https://agentmods.dev/skills/cacity/videohub/videohub-film-commentary"><img src="https://agentmods.dev/badge/skills/cacity/videohub/videohub-film-commentary/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cacity/videohub/videohub-film-commentary"><img src="https://agentmods.dev/badge/skills/cacity/videohub/videohub-film-commentary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00191 | $0.03441 |
| Opus 5 | $0.00096 | $0.01721 |
| Sonnet 5 | $0.00038 | $0.00688 |
| Haiku 4.5 | $0.00019 | $0.00344 |
Grade A, and why
videohub-film-commentary scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VideoHub Film Commentary
先读取 videohub-story-editor/SKILL.md，本 Skill 只增加影视剧专用的讲述策略和
旁白/原声混合规则，不复制基础流水线。
片名为《东京大饭店》或 Grand Maison Tokyo 时，必须读取并执行
tokyo-grand-maison-production-preset.md。
处理连续剧后续集、要求“沿用上一集规格”或批量制作多集时，必须读取
series-episode-production.md，先继承上一集可验证的制作参数，
再按当前集素材重新建立剧情证据和剪辑计划。新建批量项目还必须读取
series-job-schema.md，使用 scripts/run_series_commentary.py
统一执行预检、计划、渲染、发布包和审计；不得在项目目录继续复制通用生产代码。
用户只提供剧集目录时，先执行 videohub-story-editor 的“剧集素材项目目录”流程，读取目录内
的 videohub_project.json 自动定位当前集视频和最佳字幕，不再要求用户重复提供字幕路径。
默认成片
- 目标时长沿用用户要求；未指定时使用 240 秒。
- 第三者旁白主导，原声锚点通常占成片 5%-12%。剧情高度依赖对白时可提高，但超过 20% 必须解释。
- 旁白区原片声音为 0.30；原声锚点恢复到 1.00。
- 单个原声锚点优先为 2-10 秒，默认保留 4-8 个；不能为了凑比例保留普通对白。
- 外语原声必须有中文或双语字幕。旁白字幕只显示实际播出的解说词。
- 完成影视解说成片后默认生成抖音发布包，包括 1080x1920 封面、3-5 个标题候选、 已选标题、50-100 字文案和 3-8 个话题；用户明确不要时才省略。
- 每期成片默认生成章节信息。通常按剧情转折划分 4-7 章，同时提供带起止时间和内容说明的
chapters.md，以及可直接粘贴到平台的chapters.txt。 - 只处理用户有权下载、剪辑和发布的素材。
1. 理解完整剧情
按 videohub-story-editor 建立 evidence_pack.json 和 story_analysis.json。影视剧分析
必须额外明确：
- 主要人物、关系、欲望、阻碍、秘密和认知变化。
- 引发后续结果的关键选择，而不只是按时间罗列事件。
- 可重排的信息与不能倒置的因果、悬念、身份揭示和情绪积累。
- 角色声音、表情、沉默或环境声不可被旁白替代的表演时刻。
不要根据剪辑前机翻决定人物动机。先使用原文字幕和画面证据理解，再完成选段和重排。
1.1 联网剧情校验
读取 plot-research-and-fact-checking.md。用户明确
要求联网，或片名、集数、人物译名、人物关系、时代背景、字幕含义存在歧义时，必须先检索
可靠资料进行交叉核验，并把查询词、来源、链接、访问日期、被核验事实和可信度写入当前项目
的 references/plot_research.md。
联网资料只是辅助校验层，不能替代字幕和画面证据。具体到本集发生了什么、角色在何时做了
什么、某段能否被剪入成片，必须以用户提供的视频、原文字幕和实际画面为准。网络梗概与本地
素材冲突时，优先采用本地素材；无法消解的冲突写入 story_analysis.json 的 uncertainties，
不得用推测补齐剧情。默认避免引用后续集数的剧透。
2. 设计第三者旁白
读取 narration-and-source-audio.md。旁白用于：
- 快速交代人物、关系、处境、时间跨度和必要文化背景。
- 压缩重复对话、行动过程、支线与低信息场景。
- 在场景跳跃之间补足因果，让观众知道“为什么下一幕会发生”。
- 在转折之后解释其影响，但不要抢在表演之前替角色下结论。
使用具体动词和可验证事实。第三者视角可以解释，但不能把推测写成角色真实想法，也 不能把解说者观点伪装成原片台词。
3. 选择影视原声
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 420 B
- references/douyin-publish-plan-schema.md 3.6 KB
- references/film-commentary-plan-schema.md 1.9 KB
- references/narration-and-source-audio.md 4.3 KB
- references/plot-research-and-fact-checking.md 2.7 KB
- references/series-episode-production.md 3.9 KB
- references/series-job-schema.md 4.1 KB
- references/tokyo-grand-maison-production-preset.md 4.0 KB
- scripts/audit_series_episode.py 9.2 KB runs code
- scripts/build_film_commentary_publish_package.py 20 KB runs code
- scripts/generate_minimax_voice_samples.py 11 KB runs code
- scripts/run_series_commentary.py 36 KB runs code
- scripts/series_commentary_common.py 11 KB runs code
- scripts/validate_commentary_plan.py 2.4 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 219 lines · 191 tokens per session scan A 7cf4cefd77cc
videohub-film-commentary is a skill published in the GitHub repository cacity/VideoHub (147 stars, last pushed 5d ago), licensed MIT. It adds 191 tokens to every session and 3,441 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
qiaomu-cut
A workflow for turning a brief video idea into a planned, sourced, edited, rendered, and checked video project.
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
stage-plan
The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
stage-consistency
Multi-shot narrative & character consistency — a character bible with a locked front-portrait anchor, view-matched reference selection, recent-frame carry-forward, Cameo (a user photo as the lead), and global planning for long scripts/novels. Trigger on top of the generation line when the SAME character must look the…