OpenChatCut Video Editing
0xsline/OpenChatCut
Connects an MCP-capable agent to the local OpenChatCut video editor to inspect and edit projects through draft edit sessions, with manual approval by default.
Runs an already-installed OpenStoryline video editing agent end to end: starts its MCP and web services, creates a session, sends edits, and verifies rendered video output.
SKILL.md written in Chinese; this summary is our English description.
Install OpenStoryline Usage and Editing
$ npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install FireRedTeam/FireRed-OpenStoryline openstoryline-use --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/FireRedTeam/FireRed-OpenStoryline.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/openstoryline-use .claude/skills/openstoryline-use && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "openstoryline-use" agent skill from https://github.com/FireRedTeam/FireRed-OpenStoryline/tree/main/.claude/skills/openstoryline-use into .claude/skills/openstoryline-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openstoryline-use", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/FireRedTeam/FireRed-OpenStoryline/tree/main/.claude/skills/openstoryline-useType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install FireRedTeam/FireRed-OpenStoryline openstoryline-use --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FireRedTeam/FireRed-OpenStoryline.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/openstoryline-use .agents/skills/openstoryline-use && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "openstoryline-use" agent skill from https://github.com/FireRedTeam/FireRed-OpenStoryline/tree/main/.claude/skills/openstoryline-use into .agents/skills/openstoryline-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openstoryline-use", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install FireRedTeam/FireRed-OpenStoryline openstoryline-use --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FireRedTeam/FireRed-OpenStoryline.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/openstoryline-use .cursor/skills/openstoryline-use && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "openstoryline-use" agent skill from https://github.com/FireRedTeam/FireRed-OpenStoryline/tree/main/.claude/skills/openstoryline-use into .cursor/skills/openstoryline-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openstoryline-use", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/FireRedTeam/FireRed-OpenStoryline.git --path .claude/skills/openstoryline-use--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install FireRedTeam/FireRed-OpenStoryline openstoryline-use --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FireRedTeam/FireRed-OpenStoryline.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/openstoryline-use .gemini/skills/openstoryline-use && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "openstoryline-use" agent skill from https://github.com/FireRedTeam/FireRed-OpenStoryline/tree/main/.claude/skills/openstoryline-use into .gemini/skills/openstoryline-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openstoryline-use", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install FireRedTeam/FireRed-OpenStoryline openstoryline-useInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/FireRedTeam/FireRed-OpenStoryline.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/openstoryline-use .github/skills/openstoryline-use && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "openstoryline-use" agent skill from https://github.com/FireRedTeam/FireRed-OpenStoryline/tree/main/.claude/skills/openstoryline-use into .github/skills/openstoryline-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openstoryline-use", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install FireRedTeam/FireRed-OpenStoryline openstoryline-use --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FireRedTeam/FireRed-OpenStoryline.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/openstoryline-use .opencode/skills/openstoryline-use && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "openstoryline-use" agent skill from https://github.com/FireRedTeam/FireRed-OpenStoryline/tree/main/.claude/skills/openstoryline-use into .opencode/skills/openstoryline-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openstoryline-use", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
openstoryline-use- GitHub stars
- 3.5k
- Token cost
- ~2.3k tokens
- SKILL.md length
- 352 words
- Files
- 3 (incl. scripts)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Runs an already-installed OpenStoryline video editing agent end to end: starts its MCP and web services, creates a session, sends edits, and verifies rendered video output.
- Works in 12 steps: 确认仓库根目录 → 进入项目根目录并配置 → 启动 MCP Server → …
- Starting OpenStoryline's MCP and web services to edit a video
- SKILL.md covers Scope, Core Rules, OpenClaw Execution Strategy… and Standard Workflow (OpenClaw), plus 1 more section
- Runs Python scripts from its folder; calls python, uvicorn and curl; reaches api.minimax.chat; needs REPLACE_WITH_REAL_KEY and REPLACE_WITH_PEXELS_KEY
What it does
Written mostly in Chinese, this skill handles only the use and editing side of OpenStoryline, not installation, which belongs to a separate install skill. It covers checking and adjusting required fields in config.toml, starting the MCP server and the agent FastAPI web service as long-running processes, creating a session and sending an initial edit request, waiting for and verifying the output video, and continuing on the same session id for a second round of edits, then confirming whether that produced a new output file.
Core rules keep the services bound to localhost only, reuse the project's own config-update and bridge scripts rather than rewriting them, and insist that the MCP and web services are started as persistent processes with their logs watched continuously rather than treated as one-off probes; command wrappers like head, tail, grep, timeout, sleep or pkill must not be appended to the startup commands.
The session id returned on first creation must be saved for every later continuation, and if the server reports a prior message still in progress the same session should be reused after waiting rather than creating a new one. The web service log is called out as the most useful place to watch editing progress, through stages like filter_clips, generate_script, generate_voiceover and render_video.
When your agent uses it
- Starting OpenStoryline's MCP and web services to edit a video
- Creating a new OpenStoryline session and sending the first edit request
- Continuing a second round of edits on an existing OpenStoryline session
- Verifying that an OpenStoryline edit produced a new output video file
Example prompts
- “Start OpenStoryline and cut this folder of clips into a video with subtitles.”
- “用 OpenStoryline 剪视频，素材在这个文件夹里。”
- “Continue the edit on session abc123 and make the intro shorter.”
Requirements
- An installed OpenStoryline instance
- A configured config.toml with LLM and VLM model, base URL and API key
Workflow steps
12 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit c9e9452. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonuvicorncurlpython3conda
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
api.minimax.chat
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
REPLACE_WITH_REAL_KEYREPLACE_WITH_PEXELS_KEYREPLACE_WITH_MINIMAX_KEYREPLACE_ACCESS_TOKENREPLACE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
OpenStoryline Usage and Editing loads about 2.3k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 352 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from FireRedTeam/FireRed-OpenStoryline at commit c9e9452, republished under its Apache-2.0 licence (© FireRedTeam). 352 words, ~2,331 tokens.
Download SKILL.mdSave it as
.claude/skills/openstoryline-use/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- openstoryline-use
- description
- Use this skill when OpenStoryline is already installed and the user wants to start the local MCP/Web services, create or continue a session, send editing instructions, perform multi-turn re-editing, and verify rendered video outputs, as well as Chinese requests like “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “用 OpenStoryline 剪视频”.
OpenStoryline Usage Skill
你负责在“已安装完成”的前提下，执行 OpenStoryline 的实际剪辑流程。 OpenStoryline 是一个剪辑 Agent，用户可使用自己的素材，通过自然语言对话的方式剪辑视频。内置素材搜索、内容理解、生成字幕、文字转语音等功能，用户可以多次提出具体的剪辑/修改意见。
目标是：使用已有脚本，稳定地完成一次从启动服务到产出视频的闭环；并且支持在同一个 session_id 上继续对话、二次编辑、重新生成新视频。
Scope
此技能只处理“使用与剪辑”：
- 检查并修改
config.toml的必要字段。 - 启动 MCP server。
- 启动
uvicorn agent_fastapi:app。 - 创建 session 并发送剪辑请求。
- 等待并验证输出视频产物。
- 在同一个
session_id上继续对话，执行二次编辑。 - 验证二次编辑后是否生成了新的
output_*.mp4。
不处理完整安装流程（依赖安装、模型下载、资源下载等），那是安装技能的范围。如果在启动时遇到问题，怀疑是安装问题，再去查看安装Skill openstoryline-install
Core Rules
- 默认只监听
127.0.0.1，不要主动暴露到局域网。 - 优先复用现有脚本，不要重复造轮子：
- 修改配置脚本：位于代码仓库
scripts/update_config.py - Web 服务桥接脚本位于当前 skill 目录下的
scripts/bridge_openstoryline.py。请先定位当前 skill 目录，再拼接scripts/bridge_openstoryline.py
- 修改配置脚本：位于代码仓库
- 长驻服务（MCP / Web）必须按“长驻进程”方式启动，并持续观察日志；不要把启动命令当成一次性探测命令。
- 不要在启动命令后面追加这些包装：
| head| tailgreptimeoutsleeppkill- 以及其它会截断日志、提前退出、强行杀进程的包装
- 询问用户需要剪辑哪些素材及其路径。
- 第一轮创建 session 后返回的
session_id必须保存；后续继续对话、二次编辑都依赖它。 - 如果服务端提示“上一条消息尚未完成，请稍后再发送”，不要新建 session；优先等待，必要时只终止卡住的本地 bridge 进程，然后继续复用原
session_id重试。 - 不要在任务执行中途主动终止 MCP / Web 服务，除非用户明确要求停止，或者服务本身已经确认失活。
- 每次完成任务后，都要向用户明确返回：
session_id- 最终视频
.mp4的完整路径 - 如有二次编辑，还要说明是否生成了新的输出文件
- 下面的示例命令都使用
source .venv/bin/activate作为示例，你需要根据用户实际使用的环境，替换成正确的命令（例如conda activate）。 - 遇到端口被占用的情况，优先换一个端口。
OpenClaw Execution Strategy (Important)
如果你是OpenClaw，一定注意以下关键点：
长驻服务怎么跑
对于以下两类命令：
PYTHONPATH=src python -m open_storyline.mcp.serveruvicorn agent_fastapi:app --host 127.0.0.1 --port 8005
必须按“长驻进程”处理：
- 用
exec启动，并开启 PTY（如果工具支持pty: true，就开启）。 - 启动后不要立刻判失败，MCP Server启动需要几分钟的时间。
- 用
process poll/process log持续观察返回的内容，一定不要急着杀掉进程。 - 看到成功日志再继续下一步。
一次性命令怎么跑
以下命令适合普通一次性 exec：
- 修改
config.toml - 创建 session
- 在现有
session_id上继续对话 - 查找
.mp4 - 查看文件大小
观察哪个日志最有用
实测中，Web 服务日志 最适合看剪辑进度。
常见正常流程节点包括：
filter_clipsgroup_clipsgenerate_scriptgenerate_voiceoverrender_video
如果 bridge 脚本还在等待，不代表系统没在工作；可能只是服务端还在处理。
Standard Workflow (OpenClaw)
0) 确认仓库根目录
后续命令中的 <repo-root> 指向 OpenStoryline 仓库根目录，例如：
/Users/yourname/Desktop/code/Openstoryline/FireRed-Openstoryline所有命令都默认在这个目录下执行，并先激活环境。
1) 进入项目根目录并配置
必填配置
在开始剪辑前，以下 6 个字段必须有值，否则模型调用会失败。你必须先向用户询问这些字段的具体值，然后用脚本进行修改：
[llm].model[llm].base_url[llm].api_key[vlm].model[vlm].base_url[vlm].api_key
直接可用命令（在仓库根目录执行，以.venv为例）：
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set llm.model=REPLACE_WITH_REAL_MODEL
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set llm.base_url=REPLACE_WITH_REAL_URL
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set llm.api_key=sk-REPLACE_WITH_REAL_KEY
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set vlm.model=REPLACE_WITH_REAL_MODEL
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set vlm.base_url=REPLACE_WITH_REAL_URL
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set vlm.api_key=sk-REPLACE_WITH_REAL_KEY选填配置
以下是常见可选项，按需设置：
1. MCP 端口（端口冲突时）
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set local_mcp_server.port=80022. 素材检索（Pexels）
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set search_media.pexels_api_key=REPLACE_WITH_PEXELS_KEY3. TTS（如果需要配音）
在以下 3 家中选一家填写即可：
# minimax
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set generate_voiceover.providers.minimax.base_url=https://api.minimax.chat/v1/t2a_v2
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set generate_voiceover.providers.minimax.api_key=REPLACE_WITH_MINIMAX_KEY
# bytedance
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set generate_voiceover.providers.bytedance.uid=REPLACE_UID
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set generate_voiceover.providers.bytedance.appid=REPLACE_APPID
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set generate_voiceover.providers.bytedance.access_token=REPLACE_ACCESS_TOKEN
# 302
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set generate_voiceover.providers.302.base_url=https://REPLACE_BASE_URL
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set generate_voiceover.providers.302.api_key=REPLACE_API_KEY2) 启动 MCP Server
注意 MCP Server 的启动可能需要几分钟，务必耐心等待，不要急着 kill 掉进程。 macOS/Linux:
cd <repo-root> && source .venv/bin/activate && PYTHONPATH=src python -m open_storyline.mcp.serverWindows:
cd <repo-root>
. .venv\Scripts\Activate.ps1
$env:PYTHONPATH="src"
python -m open_storyline.mcp.server看到类似以下日志，视为成功：
Uvicorn running on http://127.0.0.1:8001Show full SKILL.md (145 more words)Show less
3) 启动 Web 服务（uvicorn）
macOS/Linux:
cd <repo-root> && source .venv/bin/activate && uvicorn agent_fastapi:app --host 127.0.0.1 --port 8005出现以下日志即成功：
INFO: Started server process [PID]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8005 (Press CTRL+C to quit)4) 创建剪辑会话
注意把地址替换为上一步启动 Web 服务时的真实地址。
curl -s -X POST "http://127.0.0.1:8005/api/sessions"这一步会创建一个剪辑会话，拿到一个session_id，非常重要！只要 Web 服务还活着，你就可以拿着这个session_id进行上传素材、多轮对话，务必保留。
5) 上传素材
方案1：
curl -s -X POST "http://127.0.0.1:8005/api/sessions/{session_id}/media" -F "files=@/absolute/path/input.mp4"方案2：对于大文件，建议直接走本地copy
cp path/to/source.mp4 <repo-root>/outputs/{session_id}/media6) 开始剪辑对话（自动创建 session）
使用 Skill 自带 bridge 脚本.
- skills-root: 当前 skill 所在目录。
- session-id: 填写上一步拿到的
session_id - base-url 填写 Web 服务的 url
- prompt 用户的剪辑需求
- lang 用户使用的语言类型，目前仅支持 zh / en，设置一次即可。
cd <repo-root> && source .venv/bin/activate && python <skills-root>/scripts/bridge_openstoryline.py \
--session-id <session_id> \
--base-url http://127.0.0.1:8005 \
--prompt "剪一个小红书风格视频" \
--lang "zh"7) 等待并观察剪辑进度
有时剪辑Agent会先询问剪辑需求；有时会直接开始剪辑，剪辑可能需要几分钟，尤其是带文案、配音、渲染时。
正确做法
- 持续
poll当前 bridge 脚本对应的进程会话。 - 同时查看 Web 服务日志。剪辑 Agent 会实时更新自己的进度。
- 只要 Web 服务日志仍在推进，就继续等待，不要随便重启服务。
实战经验
如果 bridge 命令还没返回，但 Web 服务日志里已经在跑节点，这通常说明服务端仍在正常工作，不要误判为失败。
8) 第二轮：在同一个 session 上继续聊天
根据助手回复，继续向它发出剪辑要求。例如，助手制定了一个剪辑计划，请求确认。那么：
cd <repo-root> && source .venv/bin/activate && python <skills-root>/scripts/bridge_openstoryline.py \
--base-url http://127.0.0.1:8005 \
--session-id <上一步session_id> \
--prompt "开始剪辑"或者需要调整：
cd <repo-root> && source .venv/bin/activate && python <skills-root>/scripts/bridge_openstoryline.py \
--base-url http://127.0.0.1:8005 \
--session-id <上一步session_id> \
--prompt "使用欢快的BGM"9) 检查首轮产物
一般来说，剪辑agent的输出会直接写出剪辑产物的路径。 如果没有，优先检查：
cd <repo-root> && find .storyline/.server_cache/<session_id> -name "output_*.mp4" 2>/dev/null判定标准
有 output_*.mp4 即认为剪辑成功。
10) 发送视频
将生成的视频发送给用户观看，询问用户反馈。
OpenClaw + 飞书 APP 场景视频发送指南
如果你是 OpenClaw 且用户使用手机飞书 APP，使用如下专属指南。要求：
- Python 3.6+
- 已安装
requestsbash python3 -m pip install requests - OpenClaw 已配置飞书渠道
运行脚本示例如下，此脚本会自动从 ~/.openclaw/openclaw.json 读取飞书凭证。 receive-id 的选择
- oc_xxx -> chat_id：发到群聊或当前单聊会话，优先推荐
- ou_xxx -> open_id：发给指定用户
- on_xxx -> user_id：仅当明确拿到的是 user_id 时再使用
cd <repo-root> && source .venv/bin/activate && python <skills-root>/scripts/feishu_file_sender.py --help
cd <repo-root> && source .venv/bin/activate && python <skills-root>/scripts/feishu_file_sender.py --file /absolute/path/to/video.mp4 --receive-id-type chat_id --receive-id oc_xxx11) 二次编辑
在已经生成视频的情况下，如果用户对视频内容不满意，可以复用同一个 session_id 继续修改视频，并生成新的 output_*.mp4。
示例：修改文案风格
cd <repo-root> && source .venv/bin/activate && python <skills-root>/scripts/bridge_openstoryline.py \
--base-url http://127.0.0.1:8005 \
--session-id <session_id> \
--prompt "帮我把文案换成更欢乐、更有活力的风格"- 同一个
session_id下，系统会重新跑相应节点,然后重新渲染. - 同一个
session_id下会出现新的render_video_*目录。 - 新目录里会生成新的
output_*.mp4。
Security Note
只有当用户明确要求手机 / LAN 访问时，才改为 --host 0.0.0.0。
同时提醒：仅在可信网络使用，避免开放到公共网络。
© FireRedTeam, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (scripts) in .claude/skills/openstoryline-use of FireRedTeam/FireRed-OpenStoryline.
- SKILL.md
- scripts/bridge_openstoryline.py
- scripts/feishu_file_sender.py
Open the folder on GitHubat commit c9e9452
Compare with similar skills
OpenStoryline Usage and Editing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| OpenStoryline Usage and Editing this skillFireRedTeam/FireRed-OpenStoryline | 3.5k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| OpenChatCut Video Editing0xsline/OpenChatCut | 2.2k | 1 repos | ~655 | Automated safety check: Pass | AGPL-3.0 | |
| Taisly Social Media Postingtaisly/agent | 217 | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| VectCutAPI Video Editingsun-guannan/VectCutAPI | 2.3k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Cassette Video EditCassette-Editor/oh-my-cassette | 119 | 1 repos | ~3.4k | Automated safety check: Pass | MIT | |
| KinocutKyaniteLabs/kinocut | 198 | — | ~5.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Taisly Social Media Posting
taisly/agent
Free AI-first short-form video publishing to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook from AI agents through Taisly.
VectCutAPI Video Editing
sun-guannan/VectCutAPI
Drives CapCut or JianYing through an HTTP and MCP API: create drafts, add video, audio, text, subtitles and effects, preview on the web and batch-produce videos.
Cassette Video Edit
Cassette-Editor/oh-my-cassette
Edit, trim, cut, caption, subtitle, reframe, combine, add background music to, or export video, audio, and image files through Cassette.
Kinocut
KyaniteLabs/kinocut
Use Kinocut for guarded video editing, source-backed planning, FFmpeg operations, media analysis, subtitles, audio workflows, Hyperframes or Revideo rendering, repurposing packages, and release…
Michel UI Demo Recorder
PackmindHub/packmind
Record polished UI demo videos and screenshots of a running web app using Playwright MCP — for client deliverables, release notes, feature walkthroughs, or bug repros.
More from FireRedTeam/FireRed-OpenStoryline
OpenStoryline Install Helper
FireRedTeam/FireRed-OpenStoryline
Installs, repairs and starts a local source checkout of FireRed-OpenStoryline, from prerequisites and a venv to resources, config and the MCP and web servers.
Related
Works with
Categories
Questions about OpenStoryline Usage and Editing
What does OpenStoryline Usage and Editing do?
Runs an already-installed OpenStoryline video editing agent end to end: starts its MCP and web services, creates a session, sends edits, and verifies rendered video output. Written mostly in Chinese, this skill handles only the use and editing side of OpenStoryline, not installation, which belongs to a separate install skill.toml, starting the MCP server and the agent FastAPI web service as long-running processes, creating a session and sending an initial edit request, waiting for and verifying the output video, and continuing on the same session id for a second round of edits, then confirming whether that produced a new output file.
When should I use OpenStoryline Usage and Editing?
OpenStoryline Usage and Editing fits situations like: starting OpenStoryline's MCP and web services to edit a video; creating a new OpenStoryline session and sending the first edit request; continuing a second round of edits on an existing OpenStoryline session; verifying that an OpenStoryline edit produced a new output video file.
How do I install OpenStoryline Usage and Editing in Claude Code?
Run `npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a claude-code`. Or copy the skill folder (.claude/skills/openstoryline-use in FireRedTeam/FireRed-OpenStoryline) into .claude/skills/openstoryline-use in your project. Claude Code loads it when a task matches its description.
How do I install OpenStoryline Usage and Editing in Codex?
Run `npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a codex`. Or copy the skill folder (.claude/skills/openstoryline-use in FireRedTeam/FireRed-OpenStoryline) into .agents/skills/openstoryline-use in your project. Codex loads it when a task matches its description.
Can I use OpenStoryline Usage and Editing in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openstoryline-use, .gemini/skills/openstoryline-use, .github/skills/openstoryline-use and .opencode/skills/openstoryline-use in your project.
What does OpenStoryline Usage and Editing need to run?
Going by SKILL.md and its folder, OpenStoryline Usage and Editing needs Python for the scripts in its folder, the command-line tools its instructions call (python, uvicorn, curl, python3 and conda) and credentials named REPLACE_WITH_REAL_KEY, REPLACE_WITH_PEXELS_KEY, REPLACE_WITH_MINIMAX_KEY and REPLACE_ACCESS_TOKEN. Our summary lists: An installed OpenStoryline instance; A configured config.toml with LLM and VLM model, base URL and API key.
Does OpenStoryline Usage and Editing access the network?
SKILL.md names 1 domain. In commands or code: api.minimax.chat; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is OpenStoryline Usage and Editing safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does OpenStoryline Usage and Editing use?
OpenStoryline Usage and Editing is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does OpenStoryline Usage and Editing use?
About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to OpenStoryline Usage and Editing?
Skills that share tags, products or a category with OpenStoryline Usage and Editing: OpenChatCut Video Editing (0xsline/OpenChatCut, 2.2k stars), Taisly Social Media Posting (taisly/agent, 217 stars), VectCutAPI Video Editing (sun-guannan/VectCutAPI, 2.3k stars) and Cassette Video Edit (Cassette-Editor/oh-my-cassette, 119 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains OpenStoryline Usage and Editing?
FireRedTeam (a GitHub organization) maintains it in FireRedTeam/FireRed-OpenStoryline, which has 3,471 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 31, 2026.
Source: FireRedTeam/FireRed-OpenStoryline on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.