{"owner":"zai-org","repo":"GLM-5","hasSkills":true,"totalSkillsCount":1,"totalTokensCount":1914,"categories":["anthropic-skill"],"hasMcp":false,"mcpConfig":null,"found":["skills/glm-master-skill/SKILL.md"],"skills":{"skills/glm-master-skill/SKILL.md":"---\nname: glm-master-skill\ndescription: |\n  Documentation-only master skill for GLM ecosystem discovery and installation.\n  This skill does not execute scripts or subprocess commands.\n  It provides a curated list of official GLM skills, install methods, and source links.\nmetadata:\n  openclaw:\n    requires:\n      env: []\n      bins: []\n    emoji: \"🎯\"\n    homepage: https://github.com/zai-org/GLM-5/tree/main/skills/glm-master-skill\n---\n\n# GLM Master Skill (Guide Only) / GLM 技能总览（仅指南）\n\nThis is a **documentation-only** master skill.\n\n- ✅ It **introduces** available GLM skills.\n- ✅ It **provides official install links and commands**.\n- ❌ It **does not run any local scripts**.\n- ❌ It **does not use subprocess**.\n\n本 Skill 只做导航与安装说明，不执行任何本地脚本。\n\n---\n\n\n## Official Skills Catalog / 官方技能目录\n\n### GLM-OCR\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmocr` | General OCR (text extraction) | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr |\n| `glmocr-table` | Table extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-table |\n| `glmocr-formula` | Formula extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-formula |\n| `glmocr-handwriting` | Handwriting OCR | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-handwriting |\n| `sdk` | GLM-OCR SDK guidance | https://github.com/zai-org/GLM-OCR/tree/main/skills/sdk |\n\n### GLM-Image\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glm-image-generation` | Text-to-image generation | https://github.com/zai-org/GLM-Image/tree/main/skills/glm-image-generation |\n\n### GLM-V\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmv-caption` | Image/video/file captioning | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-caption |\n| `glmv-prompt-gen` | Prompt generation from visual input | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prompt-gen |\n| `glmv-resume-screen` | Resume screening | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-resume-screen |\n| `glmv-grounding` | Image/video target localization & bounding-box visualization | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-grounding |\n| `glmv-doc-based-writing` | Document-based content generation (PDF/DOCX) | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-doc-based-writing |\n| `glmv-pdf-to-ppt` | PDF to HTML presentation conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-ppt |\n| `glmv-pdf-to-web` | PDF to academic project website conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-web |\n| `glmv-prd-to-app` | Build full-stack web app from PRD documents & prototypes | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prd-to-app |\n| `glmv-web-replication` | Frontend visual replication of public websites | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-web-replication |\n\n---\n\n## Installation Methods / 安装方式\n\n### Method A: Install from Clawhub (Recommended first)\n\n```bash\nnpx clawhub@latest install <skill-name>\n```\n\nExample:\n\n```bash\nnpx clawhub@latest install glmocr\nnpx clawhub@latest install glmv-caption\nnpx clawhub@latest install glm-image-generation\n```\n\nClawhub accepts one skill per `install` command. To install multiple skills,\nrun one command per skill. This shell loop stops on the first failed install\n(for example, if the registry is rate-limited):\n\n```bash\nfor skill in \\\n  glmocr glmocr-table glmocr-formula glmocr-handwriting \\\n  glm-image-generation glmv-caption glmv-prompt-gen glmv-resume-screen \\\n  glmv-grounding glmv-doc-based-writing glmv-pdf-to-ppt glmv-pdf-to-web \\\n  glmv-prd-to-app glmv-web-replication; do\n  npx clawhub@latest install \"$skill\" || break\ndone\n```\n\nClawhub 的每条 `install` 命令只接受一个技能；以上循环逐个安装，并在首次失败时停止。\n\n### Method B: If Clawhub is rate-limited\n\nYou may see errors like:\n\n```text\n✖ Rate limit exceeded (retry in 47s, remaining: 0/20, reset in 47s)\n```\n\nUse one of the following:\n\n1. Wait and retry after reset time.\n2. Install from the official GitHub skill directory directly.\n\n你可能会遇到 Clawhub 频率限制；可等待重试，或改用 GitHub 源安装。\n\n### Method C: Install from GitHub source\n\nUse each skill's official path (see catalog above).\n\nGeneral idea:\n\n```bash\ngit clone https://github.com/zai-org/<REPO>.git\n```\n\nThen follow that skill's own `SKILL.md` for exact setup steps.\n\n---\n\n## API Key Setup (required by most downstream skills)\n\nMost GLM skills require the environment variable `ZHIPU_API_KEY`. This master skill itself does **not** read or use the key, but downstream skills will.\n\n> **Security best practices:**\n> - Create a **limited-scope** API key with only the permissions needed for the skills you plan to use.\n> - Store the key in environment variables only — **never hardcode** it in source files or commit it to version control.\n> - If storing the key in a `.env` file, add the **file path** `.env` to `.gitignore`, not the variable name `ZHIPU_API_KEY`. Git ignores files by path, not by their contents. Ignoring a file does not untrack one already committed; if a key was committed, revoke it and remove the secret from the repository.\n> - Rotate the key periodically and revoke unused keys at https://bigmodel.cn/usercenter/proj-mgmt/apikeys.\n\nGet API key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\nSet in shell:\n\n```bash\nexport ZHIPU_API_KEY=\"your_key\"\n```\n\n或者写入环境配置文件（如 `~/.zshrc`）以长期生效，但请确保该文件不会被提交到版本控制系统。\n\n---\n\n## How an Agent should use this Master Skill\n\nWhen user asks for GLM OCR / GLM Image / GLM-V capabilities:\n\n1. Match user intent to one or more skills in the catalog.\n2. Recommend installation via `npx clawhub@latest install <skill-name>` first.\n3. If rate-limited, tell user to retry later or use GitHub skill source.\n4. Open the selected skill's official `SKILL.md` and follow its instructions.\n\n当用户提出具体任务时，Agent 按上述流程引导安装并跳转到对应技能文档。\n\n---\n\n## Resource Links\n\n- GLM-5: https://github.com/zai-org/GLM-5\n- GLM-OCR: https://github.com/zai-org/GLM-OCR\n- GLM-Image: https://github.com/zai-org/GLM-Image\n- GLM-V: https://github.com/zai-org/GLM-V\n- API Docs: https://docs.bigmodel.cn/\n- API Key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\n---\n\n## Why this design / 设计原因\n\nSome skill-sharing platforms may flag `subprocess` execution as high risk during review.\n\nTo keep this master skill safe and easy to pass review:\n\n1. No helper `.py` installer.\n2. No local command execution logic.\n3. Only official links + clear installation instructions.\n\n由于 `subprocess` 在审核中可能被视为高风险，这里采用“纯文档”方式。\n\n---\n\n## Security Note\n\nThis master skill intentionally avoids executable helper scripts.\nIt is designed for safer sharing/review in public skill marketplaces.\n\n本 Skill 刻意不包含可执行安装脚本，以降低审核风险。\n"},"files":{"skills/glm-master-skill/SKILL.md":"---\nname: glm-master-skill\ndescription: |\n  Documentation-only master skill for GLM ecosystem discovery and installation.\n  This skill does not execute scripts or subprocess commands.\n  It provides a curated list of official GLM skills, install methods, and source links.\nmetadata:\n  openclaw:\n    requires:\n      env: []\n      bins: []\n    emoji: \"🎯\"\n    homepage: https://github.com/zai-org/GLM-5/tree/main/skills/glm-master-skill\n---\n\n# GLM Master Skill (Guide Only) / GLM 技能总览（仅指南）\n\nThis is a **documentation-only** master skill.\n\n- ✅ It **introduces** available GLM skills.\n- ✅ It **provides official install links and commands**.\n- ❌ It **does not run any local scripts**.\n- ❌ It **does not use subprocess**.\n\n本 Skill 只做导航与安装说明，不执行任何本地脚本。\n\n---\n\n\n## Official Skills Catalog / 官方技能目录\n\n### GLM-OCR\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmocr` | General OCR (text extraction) | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr |\n| `glmocr-table` | Table extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-table |\n| `glmocr-formula` | Formula extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-formula |\n| `glmocr-handwriting` | Handwriting OCR | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-handwriting |\n| `sdk` | GLM-OCR SDK guidance | https://github.com/zai-org/GLM-OCR/tree/main/skills/sdk |\n\n### GLM-Image\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glm-image-generation` | Text-to-image generation | https://github.com/zai-org/GLM-Image/tree/main/skills/glm-image-generation |\n\n### GLM-V\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmv-caption` | Image/video/file captioning | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-caption |\n| `glmv-prompt-gen` | Prompt generation from visual input | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prompt-gen |\n| `glmv-resume-screen` | Resume screening | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-resume-screen |\n| `glmv-grounding` | Image/video target localization & bounding-box visualization | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-grounding |\n| `glmv-doc-based-writing` | Document-based content generation (PDF/DOCX) | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-doc-based-writing |\n| `glmv-pdf-to-ppt` | PDF to HTML presentation conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-ppt |\n| `glmv-pdf-to-web` | PDF to academic project website conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-web |\n| `glmv-prd-to-app` | Build full-stack web app from PRD documents & prototypes | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prd-to-app |\n| `glmv-web-replication` | Frontend visual replication of public websites | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-web-replication |\n\n---\n\n## Installation Methods / 安装方式\n\n### Method A: Install from Clawhub (Recommended first)\n\n```bash\nnpx clawhub@latest install <skill-name>\n```\n\nExample:\n\n```bash\nnpx clawhub@latest install glmocr\nnpx clawhub@latest install glmv-caption\nnpx clawhub@latest install glm-image-generation\n```\n\nClawhub accepts one skill per `install` command. To install multiple skills,\nrun one command per skill. This shell loop stops on the first failed install\n(for example, if the registry is rate-limited):\n\n```bash\nfor skill in \\\n  glmocr glmocr-table glmocr-formula glmocr-handwriting \\\n  glm-image-generation glmv-caption glmv-prompt-gen glmv-resume-screen \\\n  glmv-grounding glmv-doc-based-writing glmv-pdf-to-ppt glmv-pdf-to-web \\\n  glmv-prd-to-app glmv-web-replication; do\n  npx clawhub@latest install \"$skill\" || break\ndone\n```\n\nClawhub 的每条 `install` 命令只接受一个技能；以上循环逐个安装，并在首次失败时停止。\n\n### Method B: If Clawhub is rate-limited\n\nYou may see errors like:\n\n```text\n✖ Rate limit exceeded (retry in 47s, remaining: 0/20, reset in 47s)\n```\n\nUse one of the following:\n\n1. Wait and retry after reset time.\n2. Install from the official GitHub skill directory directly.\n\n你可能会遇到 Clawhub 频率限制；可等待重试，或改用 GitHub 源安装。\n\n### Method C: Install from GitHub source\n\nUse each skill's official path (see catalog above).\n\nGeneral idea:\n\n```bash\ngit clone https://github.com/zai-org/<REPO>.git\n```\n\nThen follow that skill's own `SKILL.md` for exact setup steps.\n\n---\n\n## API Key Setup (required by most downstream skills)\n\nMost GLM skills require the environment variable `ZHIPU_API_KEY`. This master skill itself does **not** read or use the key, but downstream skills will.\n\n> **Security best practices:**\n> - Create a **limited-scope** API key with only the permissions needed for the skills you plan to use.\n> - Store the key in environment variables only — **never hardcode** it in source files or commit it to version control.\n> - If storing the key in a `.env` file, add the **file path** `.env` to `.gitignore`, not the variable name `ZHIPU_API_KEY`. Git ignores files by path, not by their contents. Ignoring a file does not untrack one already committed; if a key was committed, revoke it and remove the secret from the repository.\n> - Rotate the key periodically and revoke unused keys at https://bigmodel.cn/usercenter/proj-mgmt/apikeys.\n\nGet API key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\nSet in shell:\n\n```bash\nexport ZHIPU_API_KEY=\"your_key\"\n```\n\n或者写入环境配置文件（如 `~/.zshrc`）以长期生效，但请确保该文件不会被提交到版本控制系统。\n\n---\n\n## How an Agent should use this Master Skill\n\nWhen user asks for GLM OCR / GLM Image / GLM-V capabilities:\n\n1. Match user intent to one or more skills in the catalog.\n2. Recommend installation via `npx clawhub@latest install <skill-name>` first.\n3. If rate-limited, tell user to retry later or use GitHub skill source.\n4. Open the selected skill's official `SKILL.md` and follow its instructions.\n\n当用户提出具体任务时，Agent 按上述流程引导安装并跳转到对应技能文档。\n\n---\n\n## Resource Links\n\n- GLM-5: https://github.com/zai-org/GLM-5\n- GLM-OCR: https://github.com/zai-org/GLM-OCR\n- GLM-Image: https://github.com/zai-org/GLM-Image\n- GLM-V: https://github.com/zai-org/GLM-V\n- API Docs: https://docs.bigmodel.cn/\n- API Key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\n---\n\n## Why this design / 设计原因\n\nSome skill-sharing platforms may flag `subprocess` execution as high risk during review.\n\nTo keep this master skill safe and easy to pass review:\n\n1. No helper `.py` installer.\n2. No local command execution logic.\n3. Only official links + clear installation instructions.\n\n由于 `subprocess` 在审核中可能被视为高风险，这里采用“纯文档”方式。\n\n---\n\n## Security Note\n\nThis master skill intentionally avoids executable helper scripts.\nIt is designed for safer sharing/review in public skill marketplaces.\n\n本 Skill 刻意不包含可执行安装脚本，以降低审核风险。\n"},"items":[{"name":"SKILL.md","path":"skills/glm-master-skill/SKILL.md","rawUrl":"https://raw.githubusercontent.com/zai-org/GLM-5/HEAD/skills/glm-master-skill/SKILL.md","title":"glm-master-skill","category":"anthropic-skill","format":"markdown","content":"---\nname: glm-master-skill\ndescription: |\n  Documentation-only master skill for GLM ecosystem discovery and installation.\n  This skill does not execute scripts or subprocess commands.\n  It provides a curated list of official GLM skills, install methods, and source links.\nmetadata:\n  openclaw:\n    requires:\n      env: []\n      bins: []\n    emoji: \"🎯\"\n    homepage: https://github.com/zai-org/GLM-5/tree/main/skills/glm-master-skill\n---\n\n# GLM Master Skill (Guide Only) / GLM 技能总览（仅指南）\n\nThis is a **documentation-only** master skill.\n\n- ✅ It **introduces** available GLM skills.\n- ✅ It **provides official install links and commands**.\n- ❌ It **does not run any local scripts**.\n- ❌ It **does not use subprocess**.\n\n本 Skill 只做导航与安装说明，不执行任何本地脚本。\n\n---\n\n\n## Official Skills Catalog / 官方技能目录\n\n### GLM-OCR\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmocr` | General OCR (text extraction) | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr |\n| `glmocr-table` | Table extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-table |\n| `glmocr-formula` | Formula extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-formula |\n| `glmocr-handwriting` | Handwriting OCR | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-handwriting |\n| `sdk` | GLM-OCR SDK guidance | https://github.com/zai-org/GLM-OCR/tree/main/skills/sdk |\n\n### GLM-Image\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glm-image-generation` | Text-to-image generation | https://github.com/zai-org/GLM-Image/tree/main/skills/glm-image-generation |\n\n### GLM-V\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmv-caption` | Image/video/file captioning | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-caption |\n| `glmv-prompt-gen` | Prompt generation from visual input | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prompt-gen |\n| `glmv-resume-screen` | Resume screening | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-resume-screen |\n| `glmv-grounding` | Image/video target localization & bounding-box visualization | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-grounding |\n| `glmv-doc-based-writing` | Document-based content generation (PDF/DOCX) | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-doc-based-writing |\n| `glmv-pdf-to-ppt` | PDF to HTML presentation conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-ppt |\n| `glmv-pdf-to-web` | PDF to academic project website conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-web |\n| `glmv-prd-to-app` | Build full-stack web app from PRD documents & prototypes | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prd-to-app |\n| `glmv-web-replication` | Frontend visual replication of public websites | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-web-replication |\n\n---\n\n## Installation Methods / 安装方式\n\n### Method A: Install from Clawhub (Recommended first)\n\n```bash\nnpx clawhub@latest install <skill-name>\n```\n\nExample:\n\n```bash\nnpx clawhub@latest install glmocr\nnpx clawhub@latest install glmv-caption\nnpx clawhub@latest install glm-image-generation\n```\n\nClawhub accepts one skill per `install` command. To install multiple skills,\nrun one command per skill. This shell loop stops on the first failed install\n(for example, if the registry is rate-limited):\n\n```bash\nfor skill in \\\n  glmocr glmocr-table glmocr-formula glmocr-handwriting \\\n  glm-image-generation glmv-caption glmv-prompt-gen glmv-resume-screen \\\n  glmv-grounding glmv-doc-based-writing glmv-pdf-to-ppt glmv-pdf-to-web \\\n  glmv-prd-to-app glmv-web-replication; do\n  npx clawhub@latest install \"$skill\" || break\ndone\n```\n\nClawhub 的每条 `install` 命令只接受一个技能；以上循环逐个安装，并在首次失败时停止。\n\n### Method B: If Clawhub is rate-limited\n\nYou may see errors like:\n\n```text\n✖ Rate limit exceeded (retry in 47s, remaining: 0/20, reset in 47s)\n```\n\nUse one of the following:\n\n1. Wait and retry after reset time.\n2. Install from the official GitHub skill directory directly.\n\n你可能会遇到 Clawhub 频率限制；可等待重试，或改用 GitHub 源安装。\n\n### Method C: Install from GitHub source\n\nUse each skill's official path (see catalog above).\n\nGeneral idea:\n\n```bash\ngit clone https://github.com/zai-org/<REPO>.git\n```\n\nThen follow that skill's own `SKILL.md` for exact setup steps.\n\n---\n\n## API Key Setup (required by most downstream skills)\n\nMost GLM skills require the environment variable `ZHIPU_API_KEY`. This master skill itself does **not** read or use the key, but downstream skills will.\n\n> **Security best practices:**\n> - Create a **limited-scope** API key with only the permissions needed for the skills you plan to use.\n> - Store the key in environment variables only — **never hardcode** it in source files or commit it to version control.\n> - If storing the key in a `.env` file, add the **file path** `.env` to `.gitignore`, not the variable name `ZHIPU_API_KEY`. Git ignores files by path, not by their contents. Ignoring a file does not untrack one already committed; if a key was committed, revoke it and remove the secret from the repository.\n> - Rotate the key periodically and revoke unused keys at https://bigmodel.cn/usercenter/proj-mgmt/apikeys.\n\nGet API key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\nSet in shell:\n\n```bash\nexport ZHIPU_API_KEY=\"your_key\"\n```\n\n或者写入环境配置文件（如 `~/.zshrc`）以长期生效，但请确保该文件不会被提交到版本控制系统。\n\n---\n\n## How an Agent should use this Master Skill\n\nWhen user asks for GLM OCR / GLM Image / GLM-V capabilities:\n\n1. Match user intent to one or more skills in the catalog.\n2. Recommend installation via `npx clawhub@latest install <skill-name>` first.\n3. If rate-limited, tell user to retry later or use GitHub skill source.\n4. Open the selected skill's official `SKILL.md` and follow its instructions.\n\n当用户提出具体任务时，Agent 按上述流程引导安装并跳转到对应技能文档。\n\n---\n\n## Resource Links\n\n- GLM-5: https://github.com/zai-org/GLM-5\n- GLM-OCR: https://github.com/zai-org/GLM-OCR\n- GLM-Image: https://github.com/zai-org/GLM-Image\n- GLM-V: https://github.com/zai-org/GLM-V\n- API Docs: https://docs.bigmodel.cn/\n- API Key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\n---\n\n## Why this design / 设计原因\n\nSome skill-sharing platforms may flag `subprocess` execution as high risk during review.\n\nTo keep this master skill safe and easy to pass review:\n\n1. No helper `.py` installer.\n2. No local command execution logic.\n3. Only official links + clear installation instructions.\n\n由于 `subprocess` 在审核中可能被视为高风险，这里采用“纯文档”方式。\n\n---\n\n## Security Note\n\nThis master skill intentionally avoids executable helper scripts.\nIt is designed for safer sharing/review in public skill marketplaces.\n\n本 Skill 刻意不包含可执行安装脚本，以降低审核风险。\n","frontmatter":{"name":"glm-master-skill","description":"Documentation-only master skill for GLM ecosystem discovery and installation.\nThis skill does not execute scripts or subprocess commands.\nIt provides a curated list of official GLM skills, install methods, and source links.\n","metadata":{"openclaw":{"requires":{"env":[],"bins":[]},"emoji":"🎯","homepage":"https://github.com/zai-org/GLM-5/tree/main/skills/glm-master-skill"}}},"isInternal":false,"tokens":1914,"sizeBytes":7061}],"systemPromptSnippet":"<yakaai_skills repo=\"zai-org/GLM-5\">\n<!-- File: skills/glm-master-skill/SKILL.md (Tokens: ~1914 | Category: anthropic-skill) -->\n---\nname: glm-master-skill\ndescription: |\n  Documentation-only master skill for GLM ecosystem discovery and installation.\n  This skill does not execute scripts or subprocess commands.\n  It provides a curated list of official GLM skills, install methods, and source links.\nmetadata:\n  openclaw:\n    requires:\n      env: []\n      bins: []\n    emoji: \"🎯\"\n    homepage: https://github.com/zai-org/GLM-5/tree/main/skills/glm-master-skill\n---\n\n# GLM Master Skill (Guide Only) / GLM 技能总览（仅指南）\n\nThis is a **documentation-only** master skill.\n\n- ✅ It **introduces** available GLM skills.\n- ✅ It **provides official install links and commands**.\n- ❌ It **does not run any local scripts**.\n- ❌ It **does not use subprocess**.\n\n本 Skill 只做导航与安装说明，不执行任何本地脚本。\n\n---\n\n\n## Official Skills Catalog / 官方技能目录\n\n### GLM-OCR\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmocr` | General OCR (text extraction) | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr |\n| `glmocr-table` | Table extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-table |\n| `glmocr-formula` | Formula extraction | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-formula |\n| `glmocr-handwriting` | Handwriting OCR | https://github.com/zai-org/GLM-OCR/tree/main/skills/glmocr-handwriting |\n| `sdk` | GLM-OCR SDK guidance | https://github.com/zai-org/GLM-OCR/tree/main/skills/sdk |\n\n### GLM-Image\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glm-image-generation` | Text-to-image generation | https://github.com/zai-org/GLM-Image/tree/main/skills/glm-image-generation |\n\n### GLM-V\n\n| Skill | Purpose | Link |\n|---|---|---|\n| `glmv-caption` | Image/video/file captioning | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-caption |\n| `glmv-prompt-gen` | Prompt generation from visual input | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prompt-gen |\n| `glmv-resume-screen` | Resume screening | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-resume-screen |\n| `glmv-grounding` | Image/video target localization & bounding-box visualization | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-grounding |\n| `glmv-doc-based-writing` | Document-based content generation (PDF/DOCX) | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-doc-based-writing |\n| `glmv-pdf-to-ppt` | PDF to HTML presentation conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-ppt |\n| `glmv-pdf-to-web` | PDF to academic project website conversion | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-pdf-to-web |\n| `glmv-prd-to-app` | Build full-stack web app from PRD documents & prototypes | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-prd-to-app |\n| `glmv-web-replication` | Frontend visual replication of public websites | https://github.com/zai-org/GLM-V/tree/main/skills/glmv-web-replication |\n\n---\n\n## Installation Methods / 安装方式\n\n### Method A: Install from Clawhub (Recommended first)\n\n```bash\nnpx clawhub@latest install <skill-name>\n```\n\nExample:\n\n```bash\nnpx clawhub@latest install glmocr\nnpx clawhub@latest install glmv-caption\nnpx clawhub@latest install glm-image-generation\n```\n\nClawhub accepts one skill per `install` command. To install multiple skills,\nrun one command per skill. This shell loop stops on the first failed install\n(for example, if the registry is rate-limited):\n\n```bash\nfor skill in \\\n  glmocr glmocr-table glmocr-formula glmocr-handwriting \\\n  glm-image-generation glmv-caption glmv-prompt-gen glmv-resume-screen \\\n  glmv-grounding glmv-doc-based-writing glmv-pdf-to-ppt glmv-pdf-to-web \\\n  glmv-prd-to-app glmv-web-replication; do\n  npx clawhub@latest install \"$skill\" || break\ndone\n```\n\nClawhub 的每条 `install` 命令只接受一个技能；以上循环逐个安装，并在首次失败时停止。\n\n### Method B: If Clawhub is rate-limited\n\nYou may see errors like:\n\n```text\n✖ Rate limit exceeded (retry in 47s, remaining: 0/20, reset in 47s)\n```\n\nUse one of the following:\n\n1. Wait and retry after reset time.\n2. Install from the official GitHub skill directory directly.\n\n你可能会遇到 Clawhub 频率限制；可等待重试，或改用 GitHub 源安装。\n\n### Method C: Install from GitHub source\n\nUse each skill's official path (see catalog above).\n\nGeneral idea:\n\n```bash\ngit clone https://github.com/zai-org/<REPO>.git\n```\n\nThen follow that skill's own `SKILL.md` for exact setup steps.\n\n---\n\n## API Key Setup (required by most downstream skills)\n\nMost GLM skills require the environment variable `ZHIPU_API_KEY`. This master skill itself does **not** read or use the key, but downstream skills will.\n\n> **Security best practices:**\n> - Create a **limited-scope** API key with only the permissions needed for the skills you plan to use.\n> - Store the key in environment variables only — **never hardcode** it in source files or commit it to version control.\n> - If storing the key in a `.env` file, add the **file path** `.env` to `.gitignore`, not the variable name `ZHIPU_API_KEY`. Git ignores files by path, not by their contents. Ignoring a file does not untrack one already committed; if a key was committed, revoke it and remove the secret from the repository.\n> - Rotate the key periodically and revoke unused keys at https://bigmodel.cn/usercenter/proj-mgmt/apikeys.\n\nGet API key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\nSet in shell:\n\n```bash\nexport ZHIPU_API_KEY=\"your_key\"\n```\n\n或者写入环境配置文件（如 `~/.zshrc`）以长期生效，但请确保该文件不会被提交到版本控制系统。\n\n---\n\n## How an Agent should use this Master Skill\n\nWhen user asks for GLM OCR / GLM Image / GLM-V capabilities:\n\n1. Match user intent to one or more skills in the catalog.\n2. Recommend installation via `npx clawhub@latest install <skill-name>` first.\n3. If rate-limited, tell user to retry later or use GitHub skill source.\n4. Open the selected skill's official `SKILL.md` and follow its instructions.\n\n当用户提出具体任务时，Agent 按上述流程引导安装并跳转到对应技能文档。\n\n---\n\n## Resource Links\n\n- GLM-5: https://github.com/zai-org/GLM-5\n- GLM-OCR: https://github.com/zai-org/GLM-OCR\n- GLM-Image: https://github.com/zai-org/GLM-Image\n- GLM-V: https://github.com/zai-org/GLM-V\n- API Docs: https://docs.bigmodel.cn/\n- API Key: https://bigmodel.cn/usercenter/proj-mgmt/apikeys\n\n---\n\n## Why this design / 设计原因\n\nSome skill-sharing platforms may flag `subprocess` execution as high risk during review.\n\nTo keep this master skill safe and easy to pass review:\n\n1. No helper `.py` installer.\n2. No local command execution logic.\n3. Only official links + clear installation instructions.\n\n由于 `subprocess` 在审核中可能被视为高风险，这里采用“纯文档”方式。\n\n---\n\n## Security Note\n\nThis master skill intentionally avoids executable helper scripts.\nIt is designed for safer sharing/review in public skill marketplaces.\n\n本 Skill 刻意不包含可执行安装脚本，以降低审核风险。\n</yakaai_skills>"}