Agent skill · Media & Video

openstoryline-use

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”.

FireRedTeamgithub.com/FireRedTeamGitHub ↗
claude-codeships scriptsApache-2.0
Install
npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 3
SKILL.md size: 9 KB
Bundled scripts: yes
Path: .claude/skills/openstoryline-use/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 3,183
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 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”： 1. 检查并修改 `config.toml` 的必要字段。 2. 启动 MCP server。 3. 启动 `uvicorn agent_fastapi:app`。 4. 创建 session 并发送剪辑请求。 5. 等待并验证输出视频产物。 6. 在同一个 `session_id` 上继续对话，执行二次编辑。 7. 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 1. 默认只监听 `127.0.0.1`，不要主动暴露到局域网。 2. 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` 3. 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。 4. **不要**在启动命令后面追加这些包装： - `| head` - `| tail` - `grep` - `timeout` - `sleep` - `pkill` - 以及其它会截断日志、提前退出、强行杀进程的包装 5. 询问用户需要剪辑哪些素材及其路径。 6. 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。 7. 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。 8. 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。 9. 每次完成任务后，都要向用户明确返回： - `sess

What's inside
Steps it walks through
  1. Scope
  2. Core Rules
  3. OpenClaw Execution Strategy (Important)
  4. 长驻服务怎么跑
  5. 一次性命令怎么跑
  6. 观察哪个日志最有用
  7. Standard Workflow (OpenClaw)
  8. 0) 确认仓库根目录
  9. 1) 进入项目根目录并配置
  10. 2) 启动 MCP Server
  11. 3) 启动 Web 服务（uvicorn）
  12. 4) 创建剪辑会话
  13. 5) 上传素材
  14. 6) 开始剪辑对话（自动创建 session）
Ships with 2 files
  • scripts/bridge_openstoryline.py
  • scripts/feishu_file_sender.py
Commands it runs
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
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set local_mcp_server.port=8002
cd <repo-root> && source .venv/bin/activate && python scripts/update_config.py --config ./config.toml --set search_media.pexels_api_key=REPLACE_WITH_PEXELS_KEY
minimax
bytedance
More from FireRed-OpenStoryline
All skills →
openstoryline-installInstall, configure, and start FireRed-OpenStoryline from source on a local machine. Use when a user…Backend & APIcreate_profile_style_skill【META SKILL】分析当前剪辑逻辑与风格，总结并生成一个新的可复用 Skill 文件，存入剪辑技能库。Analyze the current editing logic and style…Documentationdefault_editing_workflow_skill【WORKFLOW SKILL】通用剪辑流程。可用于剪辑日常/旅行 vlog，或是任何用户需求不明确的场景。A universal editing workflow. It can be used…Workflow & Productivityspeech_rough_cut_skill【WORKFLOW SKILL】根据输入视频的音频信息进行口播粗剪。Rough cut based on audio information from the input video for…Media & Videosubtitle_imitation_skill【CAPABILITY SKILL】基于用户提供的参考文案样本，对视频素材内容进行深度文风仿写，生成风格化脚本。Based on user-provided reference text…Documentation
About this skill
What does the openstoryline-use skill do?

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”.

How do I install it?

Run `npx skills add FireRedTeam/FireRed-OpenStoryline --skill openstoryline-use --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From FireRedTeam/FireRed-OpenStoryline, a repository with 3,183 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.