[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78RE14PEY8ES7FWDYYWXC08":3,"skill-same:01M78RE14PEY8ES7FWDYYWXC08":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":13,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M78RE14PEY8ES7FWDYYWXC08","switch-modes",null,"Switch between AI models dynamically to optimize costs and performance. Use when the user says mode commands like \"eco mode\", \"balanced mode\", \"smart mode\", or \"max mode\", or when they want to check their current mode with \"\u002Fmodes status\" or configure modes with \"\u002Fmodes setup\".","meghal86\u002Fstacksignal","meghal86","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F37388715?v=4","01M6CS2EW8SK89GH52R2ZEN8QQ","01M728J5CGY456EETEFG6HJBTM",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fswitch-modes\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: switch-modes\ndescription: Switch between AI models dynamically to optimize costs and performance. Use when the user says mode commands like \"eco mode\", \"balanced mode\", \"smart mode\", or \"max mode\", or when they want to check their current mode with \"\u002Fmodes status\" or configure modes with \"\u002Fmodes setup\".\nlicense: MIT\nmetadata:\n  author: serudda\n  version: \"1.0.0\"\n---\n\n# Switch Modes\n\nDynamically switch between AI models to optimize costs and performance.\n\n## When to Use This Skill\n\nActivate this skill when the user mentions:\n\n- Mode switching commands: `eco mode`, `balanced mode`, `smart mode`, `max mode`\n- Status check: `\u002Fmodes status`\n- Configuration: `\u002Fmodes setup`\n\n## How It Works\n\nThe skill manages 4 predefined modes, each mapped to a specific model:\n\n- **eco** → Cheapest model (for summaries, quick questions)\n- **balanced** → Daily driver model (for general work)\n- **smart** → Powerful model (for complex reasoning)\n- **max** → Most powerful model (for critical tasks)\n\nConfiguration is stored in `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json`.\n\n## Step-by-Step Instructions\n\n### 1. Detect Mode Commands\n\nWhen the user message contains any of these patterns:\n\n- `eco mode` or `eco` (standalone)\n- `balanced mode` or `balanced`\n- `smart mode` or `smart`\n- `max mode` or `max`\n- `\u002Fmodes status`\n- `\u002Fmodes setup`\n\n### 2. Handle Setup Command (`\u002Fmodes setup`)\n\nIf the configuration file doesn't exist or user requests setup:\n\n1. Use `AskUserQuestion` to gather model preferences for each mode:\n   - **ECO mode**: Recommend `anthropic\u002Fclaude-3.5-haiku`\n   - **BALANCED mode**: Recommend `anthropic\u002Fclaude-sonnet-4-5`\n   - **SMART mode**: Recommend `anthropic\u002Fclaude-opus-4-5`\n   - **MAX mode**: Recommend `anthropic\u002Fclaude-opus-4-6` or `openai\u002Fo1-pro`\n\n2. Create\u002Fupdate `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json` with the structure:\n\n```json\n{\n\t\"eco\": \"model-id\",\n\t\"balanced\": \"model-id\",\n\t\"smart\": \"model-id\",\n\t\"max\": \"model-id\"\n}\n```\n\n3. Confirm setup completion to the user.\n\n### 3. Handle Status Command (`\u002Fmodes status`)\n\n1. Read the OpenClaw config at `~\u002F.openclaw\u002Fopenclaw.json` to get current model\n2. Read `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json` to get mode mappings\n3. Determine which mode is currently active by matching the current model\n4. Display: `✅ Currently in [MODE] mode using [MODEL_ID]`\n\n### 4. Handle Mode Switch Commands\n\nWhen user requests a mode switch:\n\n1. **Read configuration**:\n\n   ```bash\n   cat ~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json\n   ```\n\n   If file doesn't exist, prompt user to run `\u002Fmodes setup` first.\n\n2. **Get the target model** from the config based on requested mode (eco\u002Fbalanced\u002Fsmart\u002Fmax)\n\n3. **Update OpenClaw config**:\n   - Read current config: `~\u002F.openclaw\u002Fopenclaw.json`\n   - Update the `model` field with the new model ID\n   - Write back to `~\u002F.openclaw\u002Fopenclaw.json`\n\n4. **Confirm to user**:\n   ```\n   ✅ [MODE] mode activated\n   Now using: [MODEL_ID]\n   ```\n\n## Examples\n\n### Example 1: Mode Switch\n\n```\nUser: eco mode\nAgent: [reads switch-modes.json, gets model for \"eco\"]\nAgent: [updates openclaw.json with new model]\nAgent: ✅ ECO mode activated\n      Now using: anthropic\u002Fclaude-3.5-haiku\n```\n\n### Example 2: Status Check\n\n```\nUser: \u002Fmodes status\nAgent: [reads openclaw.json for current model]\nAgent: [reads switch-modes.json for mode mappings]\nAgent: ✅ Currently in BALANCED mode using anthropic\u002Fclaude-sonnet-4-5\n```\n\n### Example 3: First Time Setup\n\n```\nUser: \u002Fmodes setup\nAgent: [uses AskUserQuestion for each mode]\nAgent: [creates ~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json]\nAgent: ✅ Setup complete! You can now use:\n      - eco mode\n      - balanced mode\n      - smart mode\n      - max mode\n```\n\n## File Locations\n\n- **Configuration**: `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json`\n- **OpenClaw Config**: `~\u002F.openclaw\u002Fopenclaw.json`\n- **Example Config**: See `example-config.json` in skill directory\n\n## Common Edge Cases\n\n1. **Config file missing**: Prompt user to run `\u002Fmodes setup`\n2. **Invalid model ID**: Show error and ask user to reconfigure that mode\n3. **Model not available**: Suggest checking API keys and model access in OpenClaw\n4. **Ambiguous input**: If just \"eco\" or \"smart\" without \"mode\", still treat as mode switch command\n5. **Case insensitive**: Accept \"ECO MODE\", \"Eco Mode\", \"eco mode\" all the same\n\n## Important Notes\n\n- Mode switching is instant - no restart required\n- Changes only affect the current session's default model\n- Preserve all other settings in `openclaw.json` when updating model\n- Always validate JSON before writing config files\n- Use absolute paths: `~\u002F.openclaw\u002F...` not relative paths\n\n## Reference\n\nFor detailed troubleshooting, supported models list, and FAQ, see [.\u002FREFERENCE.md](references\u002FREFERENCE.md).\n","# Switch Modes\n\nDynamically switch between AI models to optimize costs and performance.\n\n## When to Use This Skill\n\nActivate this skill when the user mentions:\n\n- Mode switching commands: `eco mode`, `balanced mode`, `smart mode`, `max mode`\n- Status check: `\u002Fmodes status`\n- Configuration: `\u002Fmodes setup`\n\n## How It Works\n\nThe skill manages 4 predefined modes, each mapped to a specific model:\n\n- **eco** → Cheapest model (for summaries, quick questions)\n- **balanced** → Daily driver model (for general work)\n- **smart** → Powerful model (for complex reasoning)\n- **max** → Most powerful model (for critical tasks)\n\nConfiguration is stored in `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json`.\n\n## Step-by-Step Instructions\n\n### 1. Detect Mode Commands\n\nWhen the user message contains any of these patterns:\n\n- `eco mode` or `eco` (standalone)\n- `balanced mode` or `balanced`\n- `smart mode` or `smart`\n- `max mode` or `max`\n- `\u002Fmodes status`\n- `\u002Fmodes setup`\n\n### 2. Handle Setup Command (`\u002Fmodes setup`)\n\nIf the configuration file doesn't exist or user requests setup:\n\n1. Use `AskUserQuestion` to gather model preferences for each mode:\n   - **ECO mode**: Recommend `anthropic\u002Fclaude-3.5-haiku`\n   - **BALANCED mode**: Recommend `anthropic\u002Fclaude-sonnet-4-5`\n   - **SMART mode**: Recommend `anthropic\u002Fclaude-opus-4-5`\n   - **MAX mode**: Recommend `anthropic\u002Fclaude-opus-4-6` or `openai\u002Fo1-pro`\n\n2. Create\u002Fupdate `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json` with the structure:\n\n```json\n{\n\t\"eco\": \"model-id\",\n\t\"balanced\": \"model-id\",\n\t\"smart\": \"model-id\",\n\t\"max\": \"model-id\"\n}\n```\n\n3. Confirm setup completion to the user.\n\n### 3. Handle Status Command (`\u002Fmodes status`)\n\n1. Read the OpenClaw config at `~\u002F.openclaw\u002Fopenclaw.json` to get current model\n2. Read `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json` to get mode mappings\n3. Determine which mode is currently active by matching the current model\n4. Display: `✅ Currently in [MODE] mode using [MODEL_ID]`\n\n### 4. Handle Mode Switch Commands\n\nWhen user requests a mode switch:\n\n1. **Read configuration**:\n\n   ```bash\n   cat ~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json\n   ```\n\n   If file doesn't exist, prompt user to run `\u002Fmodes setup` first.\n\n2. **Get the target model** from the config based on requested mode (eco\u002Fbalanced\u002Fsmart\u002Fmax)\n\n3. **Update OpenClaw config**:\n   - Read current config: `~\u002F.openclaw\u002Fopenclaw.json`\n   - Update the `model` field with the new model ID\n   - Write back to `~\u002F.openclaw\u002Fopenclaw.json`\n\n4. **Confirm to user**:\n   ```\n   ✅ [MODE] mode activated\n   Now using: [MODEL_ID]\n   ```\n\n## Examples\n\n### Example 1: Mode Switch\n\n```\nUser: eco mode\nAgent: [reads switch-modes.json, gets model for \"eco\"]\nAgent: [updates openclaw.json with new model]\nAgent: ✅ ECO mode activated\n      Now using: anthropic\u002Fclaude-3.5-haiku\n```\n\n### Example 2: Status Check\n\n```\nUser: \u002Fmodes status\nAgent: [reads openclaw.json for current model]\nAgent: [reads switch-modes.json for mode mappings]\nAgent: ✅ Currently in BALANCED mode using anthropic\u002Fclaude-sonnet-4-5\n```\n\n### Example 3: First Time Setup\n\n```\nUser: \u002Fmodes setup\nAgent: [uses AskUserQuestion for each mode]\nAgent: [creates ~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json]\nAgent: ✅ Setup complete! You can now use:\n      - eco mode\n      - balanced mode\n      - smart mode\n      - max mode\n```\n\n## File Locations\n\n- **Configuration**: `~\u002F.openclaw\u002Fworkspace\u002Fswitch-modes.json`\n- **OpenClaw Config**: `~\u002F.openclaw\u002Fopenclaw.json`\n- **Example Config**: See `example-config.json` in skill directory\n\n## Common Edge Cases\n\n1. **Config file missing**: Prompt user to run `\u002Fmodes setup`\n2. **Invalid model ID**: Show error and ask user to reconfigure that mode\n3. **Model not available**: Suggest checking API keys and model access in OpenClaw\n4. **Ambiguous input**: If just \"eco\" or \"smart\" without \"mode\", still treat as mode switch command\n5. **Case insensitive**: Accept \"ECO MODE\", \"Eco Mode\", \"eco mode\" all the same\n\n## Important Notes\n\n- Mode switching is instant - no restart required\n- Changes only affect the current session's default model\n- Preserve all other settings in `openclaw.json` when updating model\n- Always validate JSON before writing config files\n- Use absolute paths: `~\u002F.openclaw\u002F...` not relative paths\n\n## Reference\n\nFor detailed troubleshooting, supported models list, and FAQ, see [.\u002FREFERENCE.md](references\u002FREFERENCE.md).\n",{"name":5,"license":14,"metadata":23,"description":7},{"author":24,"version":25},"serudda","1.0.0","main","54afe4b75ed2eb8f0feabb2f5b57dfa4bcbb3c44",".agents\u002Fskills\u002Fswitch-modes","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal","https:\u002F\u002Fgithub.com\u002Fmeghal86","2026-05-17 14:11:28",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add meghal86\u002Fstacksignal --skill switch-modes",{"tool":38,"command":39},"bunx","bunx skills add meghal86\u002Fstacksignal --skill switch-modes",{"tool":41,"command":42},"pnpm","pnpm dlx skills add meghal86\u002Fstacksignal --skill switch-modes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fswitch-modes\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"_meta.json","REFERENCE","参考文档",277,"https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fswitch-modes\u002F_meta.json",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"REFERENCE.md",7918,"https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fswitch-modes\u002FREFERENCE.md",[57,65,73,81,89,96],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":61,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M78XH0FRP65NYEDHF2BT7NB1","zvukogram","Text-to-Speech via Zvukogram API with SSML support. Use when you need to generate speech from text, create podcasts, voice notifications, or work with audio. Supports speed control, stress marks, English word transcription, and audio fragment merging.","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzvukogram\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzvukogram\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M78XEND5ASXYB6MN8AQQGJAF","zohomail","Zoho Mail API integration with managed OAuth. Send, receive, and manage emails, folders, and labels.\nUse this skill when users want to send emails, read messages, manage folders, or work with email labels in Zoho Mail.\nFor other third party apps, use the api-gateway skill (https:\u002F\u002Fclawhub.ai\u002Fbyungkyu\u002Fapi-gateway).\nRequires network access and valid Maton API key.","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzohomail\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzohomail\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M78XEBBV3C6DRZFAJXP6RDKS","zoho-recruit","Zoho Recruit API integration with managed OAuth. Manage candidates, job openings, interviews, and recruitment workflows.\nUse this skill when users want to read, create, update, or search recruitment data like candidates, job openings, interviews, and applications in Zoho Recruit.\nFor other third party apps, use the api-gateway skill (https:\u002F\u002Fclawhub.ai\u002Fbyungkyu\u002Fapi-gateway).\nRequires network access and valid Maton API key.","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-recruit\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-recruit\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M78XE5CQG75DZWYSKGXFR99T","zoho-people","Zoho People API integration with managed OAuth. Manage employees, departments, designations, attendance, and leave.\nUse this skill when users want to read, create, update, or query HR data like employees, departments, designations, and forms in Zoho People.\nFor other third party apps, use the api-gateway skill (https:\u002F\u002Fclawhub.ai\u002Fbyungkyu\u002Fapi-gateway).\nRequires network access and valid Maton API key.","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-people\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-people\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M78XDZKMZAJYFJJFT7MR5ZN2","zoho-mail","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-mail\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-mail\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M78XDST8JK0WVDA1F3VPNWXD","zoho-inventory","Zoho Inventory API integration with managed OAuth. Manage items, sales orders, invoices, purchase orders, bills, contacts, and shipments.\nUse this skill when users want to read, create, update, or delete inventory items, sales orders, invoices, purchase orders, bills, or other inventory records in Zoho Inventory.\nFor other third party apps, use the api-gateway skill (https:\u002F\u002Fclawhub.ai\u002Fbyungkyu\u002Fapi-gateway).\nRequires network access and valid Maton API key.","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-inventory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmeghal86\u002Fstacksignal\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzoho-inventory\u002FSKILL.md",[],[]]