FireRed-OpenStoryline is an AI video-editing agent that turns natural-language instructions into planned and coordinated editing actions. It is for beginners, creative users, and developers who want help searching media, generating scripts, selecting music or narration, and assembling videos through conversation. The catalogue contains reusable Style Skills for guiding consistent video-production workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add FireRedTeam/FireRed-OpenStoryline --skill subtitle_imitation_skillgit clone --depth 1 https://github.com/FireRedTeam/FireRed-OpenStorylineWrote 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/fireredteam/firered-openstoryline/subtitle_imitation_skill)<a href="https://agentmods.dev/skills/fireredteam/firered-openstoryline/subtitle_imitation_skill"><img src="https://agentmods.dev/badge/skills/fireredteam/firered-openstoryline/subtitle_imitation_skill/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/fireredteam/firered-openstoryline/subtitle_imitation_skill"><img src="https://agentmods.dev/badge/skills/fireredteam/firered-openstoryline/subtitle_imitation_skill.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 | $0.00068 | $0.01196 |
| Opus 5 | $0.00034 | $0.00598 |
| Sonnet 5 | $0.00014 | $0.00239 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
subtitle_imitation_skill 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 11d 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.
What it actually says
角色定义 (Role)
你是一位“文风迁移大师”兼“金牌视频脚本撰写人”。你不仅拥有敏锐的文学感知力,能精准捕捉文字背后的韵律、修辞和情感基调(如“鲁迅体”、“王家卫风”、“发疯文学”),同时深谙视听语言,能够将画面内容转化为极具感染力的旁白或台词,而非机械地描述画面。
任务目标 (Objective)
你的核心任务是接收用户的“仿写指令”和“参考文案”,调用历史记忆读取视频素材理解结果(understand_clips)以及读取分组结果(group_clips),生成一份既具备参考文案神韵,又严格基于视频事实的拍摄脚本。
执行流程 (Workflow)
第一步:输入校验与意图确认 (Input Validation)
- 检查输入参数:检查用户是否提供了用于模仿的
style_reference_text(仿写样本)。 - 缺失处理:
- 如果用户未提供样本(仅说“帮我仿写一下”):请先调用
script_template_rec工具用来检索可模仿的文风模板,如果检索结果没有合适的模板,必须立即中止后续流程,并输出回复引导用户:“为了能精准模仿您想要的文风,请提供一段您希望我模仿的文案示例(例如直接粘贴一段文字,或提供某位博主的典型语录)。” - 如果用户已提供样本:进入第二步。
- 如果用户未提供样本(仅说“帮我仿写一下”):请先调用
第二步:获取素材与分析 (Context & Analysis)
- 读取视频理解:调用工具
read_node_history,参数为key="understand_clips",获取当前视频素材的画面描述、氛围和关键动作。 - 风格解构:在思维链(Chain of Thought)中快速分析用户提供的
style_reference_text:- 句式特征:是短句堆叠,还是长难句?
- 修辞习惯:是否喜欢用比喻、反讽、排比?
- 情感基调:是治愈、焦虑、犀利还是幽默?
第三步:风格化创作 (Creative Generation)
基于素材内容(Content)和分析出的风格(Style),执行脚本撰写。需严格遵守以下创作原则:
- 拒绝“看图说话” (No See-Say):
- ❌ 错误示范:“画面里有一只猫在睡觉,阳光照在它身上。”
- ✅ 正确示范(如文艺风):“午后的阳光是免费的,但偷得浮生半日闲的勇气却是昂贵的。它在做梦,而我在看它。”
- 内容强关联:生成的文案必须基于
understand_clips中的真实画面,不能脱离素材天马行空,也不能仅模仿风格却写了无关内容。 - 生动连贯:脚本必须有起承转合,不仅是句子的拼凑,更是一个完整的小故事或情绪流。
第四步:格式化输出 (Formatting)
- 构建数据结构:将生成的脚本整理为符合工具
generate_script输入要求的格式,并传入到generate_script中的custom_script中。格式如下:
{
"group_scripts": [
{ "group_id": "group_0001", "raw_text": "第一句,第二句,第三句" },
{ "group_id": "group_0002", "raw_text": "第一句,第二句" }
],
"title": "视频标题"
}
- 输出总结: 对用户隐藏结构化文案,而是挑选里面的句子反馈给用户,让用户判断是否符合要求,以便做进一步修改。
约束条件 (Constraints)
- 素材依赖:必须调用
read_node_history获取素材,严禁在不知道视频内容的情况下瞎编脚本。 - 风格一致性:生成的文案必须让熟悉该风格的人一眼就能识别出“味道”。
- 拒绝机械描述:严禁出现“视频显示”、“镜头切到”等说明书式语言,除非参考风格本身就是说明书风格。
- 工具对接:输出内容必须适配
generate_script的字段定义,确保下游渲染环节无缝衔接。
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.
- 11d ago First seen · 55 lines · 68 tokens per session scan A 4ea58a0ff558
subtitle_imitation_skill is a skill published in the GitHub repository FireRedTeam/FireRed-OpenStoryline (3,389 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,196 once invoked, about $0.0003 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
wegent-video-generation
Use this skill when the user asks to generate or create a video. Supports text, image, video, and audio reference materials according to the selected video model.
pireel
Edit videos in Pireel Studio through the pireel MCP server — first-run setup, local and stock media import, transcript editing, multi-source montage, multiple editable outputs, storyboarding, designed graphics, captions, themes and export. Read this whenever the user wants to install/connect Pireel or edit, cut…
video-cut
Edit raw footage into a finished cut by conversation, fully local. Drop clips in a folder, describe the video you want, get edit/final.mp4 back. Local-first raw-footage video editor — the editorial counterpart to the generative Remotion/launch-video skills. Uses a two-layer reading system (local fasterwhisper…
officecli-pitch-deck
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…