OpenStoryline Install Helper

What it does

When your agent uses it

• Setting up OpenStoryline from source on a local machine
• Troubleshooting a failed OpenStoryline install or startup
• Downloading the models and resources OpenStoryline needs
• Filling in config.toml model settings and launching the MCP and web services

Example prompts

• “Install OpenStoryline in a local venv and start the web service.”
• “OpenStoryline fails to start after the install, so find out what is missing.”
• “Download the required resources and check that config.toml loads.”

Requirements

• git, Python 3.11 or newer, ffmpeg, wget and unzip
• macOS, Linux or WSL with a POSIX shell
• API keys for the models set in config.toml

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm the repo path and read the current README.md and config.toml.
2. 2Detect local prerequisites before changing anything.
3. 3Prefer a local venv install unless the user explicitly asks for Docker or conda.
4. 4Download resources only after Python dependencies succeed.
5. 5Validate imports and config loading before claiming success.
6. 6This skill assumes macOS, Linux, or WSL with a POSIX shell.

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

  Shell commands in SKILL.md call:

  • python
  • conda
  • apt-get
  • brew
  • bash
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  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_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

OpenStoryline Install Helper loads about 1.5k tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 550 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~110

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

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

• NoteRuns commands with sudoSKILL.md:55

  sudo apt-get update

• NoteRuns commands with sudoSKILL.md:56

  sudo apt-get install -y ffmpeg wget unzip

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from FireRedTeam/FireRed-OpenStoryline at commit c9e9452, republished under its Apache-2.0 licence (© FireRedTeam). 550 words, ~1,517 tokens.

name

openstoryline-install

description

Install, configure, and start FireRed-OpenStoryline from source on a local machine. Use when a user asks to set up OpenStoryline, troubleshoot installation, download required resources, fill config.toml API keys, or launch the MCP and web services, as well as Chinese requests like “安装 OpenStoryline”, “配置 OpenStoryline”, “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “修复 OpenStoryline 安装问题”, or “排查 OpenStoryline 启动失败”.

/path/to/python -c "import ssl, sqlite3, venv; print('stdlib_ok')"

conda create -y -n openstoryline-py311 python=3.11
conda run -n openstoryline-py311 python --version
conda run -n openstoryline-py311 python -m venv .venv

/path/to/python -m venv .venv
.venv/bin/python -m pip install --upgrade pip
.venv/bin/python -m pip install -r requirements.txt
bash download.sh

.venv/bin/python scripts/update_config.py --config ./config.toml --set llm.model=REPLACE_WITH_REAL_MODEL
.venv/bin/python scripts/update_config.py --config ./config.toml --set llm.base_url=REPLACE_WITH_REAL_URL
.venv/bin/python scripts/update_config.py --config ./config.toml --set llm.api_key=sk-REPLACE_WITH_REAL_KEY

.venv/bin/python scripts/update_config.py --config ./config.toml --set vlm.model=REPLACE_WITH_REAL_MODEL
.venv/bin/python scripts/update_config.py --config ./config.toml --set vlm.base_url=REPLACE_WITH_REAL_URL
.venv/bin/python scripts/update_config.py --config ./config.toml --set vlm.api_key=sk-REPLACE_WITH_REAL_KEY

.venv/bin/pip check
PYTHONPATH=src .venv/bin/python -c "from open_storyline.config import load_settings; load_settings('config.toml'); print('config_ok')"

test -f .storyline/models/transnetv2-pytorch-weights.pth
test -d resource/bgms

PYTHONPATH=src .venv/bin/python -m open_storyline.mcp.server

PYTHONPATH=src .venv/bin/python -m uvicorn agent_fastapi:app --host 127.0.0.1 --port 8005

© 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

Just SKILL.md in .claude/skills/openstoryline-install of FireRedTeam/FireRed-OpenStoryline.

Open the folder on GitHubat commit c9e9452