[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPA7DY91MFSQV80ETS810R":3,"skill-same:01M7EPA7DY91MFSQV80ETS810R":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EPA7DY91MFSQV80ETS810R","openstoryline-install",null,"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”.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fopenstoryline-install\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: openstoryline-install\ndescription: 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”.\n---\n\n# OpenStoryline Install\n\nUse this skill when the task is to install or repair a local source checkout of FireRed-OpenStoryline.\n\nKeep the workflow deterministic:\n\n1. Confirm the repo path and read the current README.md and config.toml.\n2. Detect local prerequisites before changing anything.\n3. Prefer a local `venv` install unless the user explicitly asks for Docker or `conda`.\n4. Download resources only after Python dependencies succeed.\n5. Validate imports and config loading before claiming success.\n6. This skill assumes macOS, Linux, or WSL with a POSIX shell.\n\n## What This Skill Covers\n\n- Clone the GitHub repo if needed\n- Create a Python environment\n- Install Python dependencies\n- Download `.storyline` models and `resource\u002F` assets\n- Fill `config.toml` model settings\n- Start MCP and web servers\n- Explain common installation\u002Fdocumentation gaps\n\n## Preconditions\n\nCheck these first:\n\n- `git`\n- Python `>= 3.11`\n- `ffmpeg`\n- `wget`\n- `unzip`\n\nOptional:\n\n- `docker`\n- `conda`\n\nIf `ffmpeg`, `wget`, or `unzip` are missing, install them through the OS package manager before continuing.\n\nExamples:\n\n- macOS with Homebrew:\n  ```bash\n  brew install ffmpeg wget unzip\n  ```\n\n- Debian\u002FUbuntu:\n  ```bash\n  sudo apt-get update\n  sudo apt-get install -y ffmpeg wget unzip\n  ```\n\nIf no supported package manager or permission is available, stop and report the missing system dependency clearly.\n\n## Interpreter selection\n\nFirst prefer any interpreter that already exists and passes version checks:\n\n1. A system Python `>= 3.11`\n2. An already available conda Python `>= 3.11`\n3. An already available pyenv Python `>= 3.11`, but only if basic stdlib modules work\n\nValidate candidate interpreters before using them:\n\n```bash\n\u002Fpath\u002Fto\u002Fpython -c \"import ssl, sqlite3, venv; print('stdlib_ok')\"\n```\n\nIf no supported interpreter already exists, peferr conda fallback:\n\n```bash\nconda create -y -n openstoryline-py311 python=3.11\nconda run -n openstoryline-py311 python --version\nconda run -n openstoryline-py311 python -m venv .venv\n```\n\nAfter a supported interpreter is found, always create a repo-local .venv and continue using .venv\u002Fbin\u002Fpython for install, config validation, and service startup.\n\nDo not duplicate the rest of the workflow for pyenv or conda unless the user explicitly asks to stay inside a conda environment.\n\n## Preferred Install Path\n\nFrom the repo root:\n\n```bash\n\u002Fpath\u002Fto\u002Fpython -m venv .venv\n.venv\u002Fbin\u002Fpython -m pip install --upgrade pip\n.venv\u002Fbin\u002Fpython -m pip install -r requirements.txt\nbash download.sh\n```\n\nNotes:\n\n- `download.sh` pulls both model weights and a large resource archive. It can take a long time and may resume after network drops.\n- The resource download is required for a full local run, not just the Python package install.\n\n## Configuration\n\nBefore starting the app, update config.toml.\n\nYou can use scripts\u002Fupdate_config.py.\n\nAt minimum, fill:\n\n```bash\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set llm.model=REPLACE_WITH_REAL_MODEL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set llm.base_url=REPLACE_WITH_REAL_URL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set llm.api_key=sk-REPLACE_WITH_REAL_KEY\n\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set vlm.model=REPLACE_WITH_REAL_MODEL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set vlm.base_url=REPLACE_WITH_REAL_URL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set vlm.api_key=sk-REPLACE_WITH_REAL_KEY\n```\n\nOptional but common:\n\n- `search_media.pexels_api_key` for searching media\n- TTS provider keys under `generate_voiceover.providers.*` (choose one provider)\n\n\n## Verification\n\nRun these checks before saying installation is complete:\n\n```bash\n.venv\u002Fbin\u002Fpip check\nPYTHONPATH=src .venv\u002Fbin\u002Fpython -c \"from open_storyline.config import load_settings; load_settings('config.toml'); print('config_ok')\"\n```\n\nAlso confirm key resources exist:\n\n```bash\ntest -f .storyline\u002Fmodels\u002Ftransnetv2-pytorch-weights.pth\ntest -d resource\u002Fbgms\n```\n\n## Start Services\n\nThere are two common paths. These are long-running processes. Do not wait for them to exit normally. Treat successful startup log lines or confirmed listening ports as success, and keep the services running in separate shells\u002Fsessions as needed.\n\nManual start:\n\n```bash\nPYTHONPATH=src .venv\u002Fbin\u002Fpython -m open_storyline.mcp.server\n```\n\nIn a second shell:\n\n```bash\nPYTHONPATH=src .venv\u002Fbin\u002Fpython -m uvicorn agent_fastapi:app --host 127.0.0.1 --port 8005\n```\n\n## Expected Outputs\n\nAfter a successful install:\n\n- `.venv\u002F` exists\n- MCP listens on the configured local port (commonly `127.0.0.1:8001`)\n- Web listens on the configured web port (commonly `127.0.0.1:8005`, though `run.sh` defaults may differ)\n\n## Common Problems\n\n### `download.sh` is slow or interrupted\n\nSymptom:\n\n- Large downloads stall or reconnect\n\nFix:\n\n- Let `wget` continue; it supports resume behavior here\n- Verify extracted outputs instead of trusting the progress meter\n\n### Web\u002FMCP server fails to bind\n\nSymptom:\n\n- `operation not permitted` while binding `127.0.0.1` or `0.0.0.0`\n\nFix:\n\n- In agent sandboxes, request permission to open local listening ports\n- Prefer `127.0.0.1` over `0.0.0.0` unless external access is required\n\n## Response Pattern\n\nWhen reporting status to the user, separate:\n\n- what is installed\n- what is still downloading\n- what config is still missing\n- what address the service is listening on\n\nDo not say \"installation complete\" if only the Python packages are installed but the resource bundle is still missing.","# OpenStoryline Install\n\nUse this skill when the task is to install or repair a local source checkout of FireRed-OpenStoryline.\n\nKeep the workflow deterministic:\n\n1. Confirm the repo path and read the current README.md and config.toml.\n2. Detect local prerequisites before changing anything.\n3. Prefer a local `venv` install unless the user explicitly asks for Docker or `conda`.\n4. Download resources only after Python dependencies succeed.\n5. Validate imports and config loading before claiming success.\n6. This skill assumes macOS, Linux, or WSL with a POSIX shell.\n\n## What This Skill Covers\n\n- Clone the GitHub repo if needed\n- Create a Python environment\n- Install Python dependencies\n- Download `.storyline` models and `resource\u002F` assets\n- Fill `config.toml` model settings\n- Start MCP and web servers\n- Explain common installation\u002Fdocumentation gaps\n\n## Preconditions\n\nCheck these first:\n\n- `git`\n- Python `>= 3.11`\n- `ffmpeg`\n- `wget`\n- `unzip`\n\nOptional:\n\n- `docker`\n- `conda`\n\nIf `ffmpeg`, `wget`, or `unzip` are missing, install them through the OS package manager before continuing.\n\nExamples:\n\n- macOS with Homebrew:\n  ```bash\n  brew install ffmpeg wget unzip\n  ```\n\n- Debian\u002FUbuntu:\n  ```bash\n  sudo apt-get update\n  sudo apt-get install -y ffmpeg wget unzip\n  ```\n\nIf no supported package manager or permission is available, stop and report the missing system dependency clearly.\n\n## Interpreter selection\n\nFirst prefer any interpreter that already exists and passes version checks:\n\n1. A system Python `>= 3.11`\n2. An already available conda Python `>= 3.11`\n3. An already available pyenv Python `>= 3.11`, but only if basic stdlib modules work\n\nValidate candidate interpreters before using them:\n\n```bash\n\u002Fpath\u002Fto\u002Fpython -c \"import ssl, sqlite3, venv; print('stdlib_ok')\"\n```\n\nIf no supported interpreter already exists, peferr conda fallback:\n\n```bash\nconda create -y -n openstoryline-py311 python=3.11\nconda run -n openstoryline-py311 python --version\nconda run -n openstoryline-py311 python -m venv .venv\n```\n\nAfter a supported interpreter is found, always create a repo-local .venv and continue using .venv\u002Fbin\u002Fpython for install, config validation, and service startup.\n\nDo not duplicate the rest of the workflow for pyenv or conda unless the user explicitly asks to stay inside a conda environment.\n\n## Preferred Install Path\n\nFrom the repo root:\n\n```bash\n\u002Fpath\u002Fto\u002Fpython -m venv .venv\n.venv\u002Fbin\u002Fpython -m pip install --upgrade pip\n.venv\u002Fbin\u002Fpython -m pip install -r requirements.txt\nbash download.sh\n```\n\nNotes:\n\n- `download.sh` pulls both model weights and a large resource archive. It can take a long time and may resume after network drops.\n- The resource download is required for a full local run, not just the Python package install.\n\n## Configuration\n\nBefore starting the app, update config.toml.\n\nYou can use scripts\u002Fupdate_config.py.\n\nAt minimum, fill:\n\n```bash\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set llm.model=REPLACE_WITH_REAL_MODEL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set llm.base_url=REPLACE_WITH_REAL_URL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set llm.api_key=sk-REPLACE_WITH_REAL_KEY\n\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set vlm.model=REPLACE_WITH_REAL_MODEL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set vlm.base_url=REPLACE_WITH_REAL_URL\n.venv\u002Fbin\u002Fpython scripts\u002Fupdate_config.py --config .\u002Fconfig.toml --set vlm.api_key=sk-REPLACE_WITH_REAL_KEY\n```\n\nOptional but common:\n\n- `search_media.pexels_api_key` for searching media\n- TTS provider keys under `generate_voiceover.providers.*` (choose one provider)\n\n\n## Verification\n\nRun these checks before saying installation is complete:\n\n```bash\n.venv\u002Fbin\u002Fpip check\nPYTHONPATH=src .venv\u002Fbin\u002Fpython -c \"from open_storyline.config import load_settings; load_settings('config.toml'); print('config_ok')\"\n```\n\nAlso confirm key resources exist:\n\n```bash\ntest -f .storyline\u002Fmodels\u002Ftransnetv2-pytorch-weights.pth\ntest -d resource\u002Fbgms\n```\n\n## Start Services\n\nThere are two common paths. These are long-running processes. Do not wait for them to exit normally. Treat successful startup log lines or confirmed listening ports as success, and keep the services running in separate shells\u002Fsessions as needed.\n\nManual start:\n\n```bash\nPYTHONPATH=src .venv\u002Fbin\u002Fpython -m open_storyline.mcp.server\n```\n\nIn a second shell:\n\n```bash\nPYTHONPATH=src .venv\u002Fbin\u002Fpython -m uvicorn agent_fastapi:app --host 127.0.0.1 --port 8005\n```\n\n## Expected Outputs\n\nAfter a successful install:\n\n- `.venv\u002F` exists\n- MCP listens on the configured local port (commonly `127.0.0.1:8001`)\n- Web listens on the configured web port (commonly `127.0.0.1:8005`, though `run.sh` defaults may differ)\n\n## Common Problems\n\n### `download.sh` is slow or interrupted\n\nSymptom:\n\n- Large downloads stall or reconnect\n\nFix:\n\n- Let `wget` continue; it supports resume behavior here\n- Verify extracted outputs instead of trusting the progress meter\n\n### Web\u002FMCP server fails to bind\n\nSymptom:\n\n- `operation not permitted` while binding `127.0.0.1` or `0.0.0.0`\n\nFix:\n\n- In agent sandboxes, request permission to open local listening ports\n- Prefer `127.0.0.1` over `0.0.0.0` unless external access is required\n\n## Response Pattern\n\nWhen reporting status to the user, separate:\n\n- what is installed\n- what is still downloading\n- what config is still missing\n- what address the service is listening on\n\nDo not say \"installation complete\" if only the Python packages are installed but the resource bundle is still missing.",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fopenstoryline-install",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill openstoryline-install",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill openstoryline-install",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill openstoryline-install","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fopenstoryline-install\u002FSKILL.md",true,[],[47,55,60,67,74,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":56,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":54},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":54},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":54},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":54},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":54},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]