[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72AXK7D63EY4ZKWYEW45JR2":3,"skill-same:01M72AXK7D63EY4ZKWYEW45JR2":46},{"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},"01M72AXK7D63EY4ZKWYEW45JR2","zendesk-automation",null,"Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.","Sansar35\u002Fclaude-agent","Sansar35","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145020281?v=4","01M724CQ2SCC86MGNSD87D0D4K","01M724CQ3965G9WJ3QXE3AJ5YY",1,"MIT","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fantigravity\u002Fzendesk-automation\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: zendesk-automation\ndescription: \"Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.\"\nrisk: critical\nsource: community\ndate_added: \"2026-02-27\"\n---\n\n# Zendesk Automation via Rube MCP\n\nAutomate Zendesk operations through Composio's Zendesk toolkit via Rube MCP.\n\n## Prerequisites\n\n- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)\n- Active Zendesk connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `zendesk`\n- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas\n\n## Setup\n\n**Get Rube MCP**: Add `https:\u002F\u002Frube.app\u002Fmcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.\n\n\n1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds\n2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `zendesk`\n3. If connection is not ACTIVE, follow the returned auth link to complete Zendesk auth\n4. Confirm connection status shows ACTIVE before running any workflows\n\n## Core Workflows\n\n### 1. List and Search Tickets\n\n**When to use**: User wants to view, filter, or search support tickets\n\n**Tool sequence**:\n1. `ZENDESK_LIST_ZENDESK_TICKETS` - List all tickets with pagination [Required]\n2. `ZENDESK_GET_ZENDESK_TICKET_BY_ID` - Get specific ticket details [Optional]\n\n**Key parameters**:\n- `page`: Page number (1-based)\n- `per_page`: Results per page (max 100)\n- `sort_by`: Sort field ('created_at', 'updated_at', 'priority', 'status')\n- `sort_order`: 'asc' or 'desc'\n- `ticket_id`: Ticket ID for single retrieval\n\n**Pitfalls**:\n- LIST uses `page`\u002F`per_page` pagination, NOT offset-based; check `next_page` in response\n- Maximum 100 results per page; iterate with page numbers until `next_page` is null\n- Deleted tickets are not returned by LIST; use GET_BY_ID which returns status 'deleted'\n- Ticket comments and audits are included in GET_BY_ID but not in LIST responses\n\n### 2. Create and Update Tickets\n\n**When to use**: User wants to create new tickets or modify existing ones\n\n**Tool sequence**:\n1. `ZENDESK_SEARCH_ZENDESK_USERS` - Find requester\u002Fassignee [Prerequisite]\n2. `ZENDESK_CREATE_ZENDESK_TICKET` - Create a new ticket [Required]\n3. `ZENDESK_UPDATE_ZENDESK_TICKET` - Update ticket fields [Optional]\n4. `ZENDESK_DELETE_ZENDESK_TICKET` - Delete a ticket [Optional]\n\n**Key parameters**:\n- `subject`: Ticket subject line\n- `description`: Ticket body (for creation; becomes first comment)\n- `priority`: 'urgent', 'high', 'normal', 'low'\n- `status`: 'new', 'open', 'pending', 'hold', 'solved', 'closed'\n- `type`: 'problem', 'incident', 'question', 'task'\n- `assignee_id`: Agent user ID to assign\n- `requester_id`: Requester user ID\n- `tags`: Array of tag strings\n- `ticket_id`: Ticket ID (for update\u002Fdelete)\n\n**Pitfalls**:\n- Tags on UPDATE REPLACE existing tags entirely; merge with current tags to preserve them\n- Use `safe_update` with `updated_stamp` to prevent concurrent modification conflicts\n- DELETE is permanent and irreversible; tickets cannot be recovered\n- `description` is only used on creation; use REPLY_ZENDESK_TICKET to add comments after creation\n- Closed tickets cannot be updated; create a follow-up ticket instead\n\n### 3. Reply to Tickets\n\n**When to use**: User wants to add comments or replies to tickets\n\n**Tool sequence**:\n1. `ZENDESK_GET_ZENDESK_TICKET_BY_ID` - Get current ticket state [Prerequisite]\n2. `ZENDESK_REPLY_ZENDESK_TICKET` - Add a reply\u002Fcomment [Required]\n\n**Key parameters**:\n- `ticket_id`: Ticket ID to reply to\n- `body`: Reply text content\n- `public`: Boolean; true for public reply, false for internal note\n- `author_id`: Author user ID (defaults to authenticated user)\n\n**Pitfalls**:\n- Set `public: false` for internal notes visible only to agents\n- Default is public reply which sends email to requester\n- HTML is supported in body text\n- Replying can also update ticket status simultaneously\n\n### 4. Manage Users\n\n**When to use**: User wants to find or create Zendesk users (agents, end-users)\n\n**Tool sequence**:\n1. `ZENDESK_SEARCH_ZENDESK_USERS` - Search for users [Required]\n2. `ZENDESK_CREATE_ZENDESK_USER` - Create a new user [Optional]\n3. `ZENDESK_GET_ABOUT_ME` - Get authenticated user info [Optional]\n\n**Key parameters**:\n- `query`: Search string (matches name, email, phone, etc.)\n- `name`: User's full name (required for creation)\n- `email`: User's email address\n- `role`: 'end-user', 'agent', or 'admin'\n- `verified`: Whether email is verified\n\n**Pitfalls**:\n- User search is fuzzy; may return partial matches\n- Creating a user with an existing email returns the existing user (upsert behavior)\n- Agent and admin roles may require specific plan features\n\n### 5. Manage Organizations\n\n**When to use**: User wants to list, create, or manage organizations\n\n**Tool sequence**:\n1. `ZENDESK_GET_ALL_ZENDESK_ORGANIZATIONS` - List all organizations [Required]\n2. `ZENDESK_GET_ZENDESK_ORGANIZATION` - Get specific organization [Optional]\n3. `ZENDESK_CREATE_ZENDESK_ORGANIZATION` - Create organization [Optional]\n4. `ZENDESK_UPDATE_ZENDESK_ORGANIZATION` - Update organization [Optional]\n5. `ZENDESK_COUNT_ZENDESK_ORGANIZATIONS` - Get total count [Optional]\n\n**Key parameters**:\n- `name`: Organization name (unique, required for creation)\n- `organization_id`: Organization ID for get\u002Fupdate\n- `details`: Organization details text\n- `notes`: Internal notes\n- `domain_names`: Array of associated domains\n- `tags`: Array of tag strings\n\n**Pitfalls**:\n- Organization names must be unique; duplicate names cause creation errors\n- Tags on UPDATE REPLACE existing tags (same behavior as tickets)\n- Domain names can be used for automatic user association\n\n## Common Patterns\n\n### Pagination\n\n**List endpoints**:\n- Use `page` (1-based) and `per_page` (max 100)\n- Check `next_page` URL in response; null means last page\n- `count` field gives total results\n\n### Ticket Lifecycle\n\n```\nnew -> open -> pending -> solved -> closed\n                  |          ^\n                  v          |\n                hold --------+\n```\n\n- `new`: Unassigned ticket\n- `open`: Assigned, being worked on\n- `pending`: Waiting for customer response\n- `hold`: Waiting for internal action\n- `solved`: Resolved, can be reopened\n- `closed`: Permanently closed, cannot be modified\n\n### User Search for Assignment\n\n```\n1. Call ZENDESK_SEARCH_ZENDESK_USERS with query (name or email)\n2. Extract user ID from results\n3. Use user ID as assignee_id in ticket creation\u002Fupdate\n```\n\n## Known Pitfalls\n\n**Tags Behavior**:\n- Tags on update REPLACE all existing tags\n- Always fetch current tags first and merge before updating\n- Tags are lowercase, no spaces (use underscores)\n\n**Safe Updates**:\n- Use `safe_update: true` with `updated_stamp` (ISO 8601) to prevent conflicts\n- Returns 409 if ticket was modified since the stamp\n\n**Deletion**:\n- Ticket deletion is permanent and irreversible\n- Consider setting status to 'closed' instead of deleting\n- Deleted tickets cannot be recovered via API\n\n**Rate Limits**:\n- Default: 400 requests per minute\n- Varies by plan tier\n- 429 responses include Retry-After header\n\n## Quick Reference\n\n| Task | Tool Slug | Key Params |\n|------|-----------|------------|\n| List tickets | ZENDESK_LIST_ZENDESK_TICKETS | page, per_page, sort_by |\n| Get ticket | ZENDESK_GET_ZENDESK_TICKET_BY_ID | ticket_id |\n| Create ticket | ZENDESK_CREATE_ZENDESK_TICKET | subject, description, priority |\n| Update ticket | ZENDESK_UPDATE_ZENDESK_TICKET | ticket_id, status, tags |\n| Reply to ticket | ZENDESK_REPLY_ZENDESK_TICKET | ticket_id, body, public |\n| Delete ticket | ZENDESK_DELETE_ZENDESK_TICKET | ticket_id |\n| Search users | ZENDESK_SEARCH_ZENDESK_USERS | query |\n| Create user | ZENDESK_CREATE_ZENDESK_USER | name, email |\n| My profile | ZENDESK_GET_ABOUT_ME | (none) |\n| List orgs | ZENDESK_GET_ALL_ZENDESK_ORGANIZATIONS | page, per_page |\n| Get org | ZENDESK_GET_ZENDESK_ORGANIZATION | organization_id |\n| Create org | ZENDESK_CREATE_ZENDESK_ORGANIZATION | name |\n| Update org | ZENDESK_UPDATE_ZENDESK_ORGANIZATION | organization_id, name |\n| Count orgs | ZENDESK_COUNT_ZENDESK_ORGANIZATIONS | (none) |\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# Zendesk Automation via Rube MCP\n\nAutomate Zendesk operations through Composio's Zendesk toolkit via Rube MCP.\n\n## Prerequisites\n\n- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)\n- Active Zendesk connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `zendesk`\n- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas\n\n## Setup\n\n**Get Rube MCP**: Add `https:\u002F\u002Frube.app\u002Fmcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.\n\n\n1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds\n2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `zendesk`\n3. If connection is not ACTIVE, follow the returned auth link to complete Zendesk auth\n4. Confirm connection status shows ACTIVE before running any workflows\n\n## Core Workflows\n\n### 1. List and Search Tickets\n\n**When to use**: User wants to view, filter, or search support tickets\n\n**Tool sequence**:\n1. `ZENDESK_LIST_ZENDESK_TICKETS` - List all tickets with pagination [Required]\n2. `ZENDESK_GET_ZENDESK_TICKET_BY_ID` - Get specific ticket details [Optional]\n\n**Key parameters**:\n- `page`: Page number (1-based)\n- `per_page`: Results per page (max 100)\n- `sort_by`: Sort field ('created_at', 'updated_at', 'priority', 'status')\n- `sort_order`: 'asc' or 'desc'\n- `ticket_id`: Ticket ID for single retrieval\n\n**Pitfalls**:\n- LIST uses `page`\u002F`per_page` pagination, NOT offset-based; check `next_page` in response\n- Maximum 100 results per page; iterate with page numbers until `next_page` is null\n- Deleted tickets are not returned by LIST; use GET_BY_ID which returns status 'deleted'\n- Ticket comments and audits are included in GET_BY_ID but not in LIST responses\n\n### 2. Create and Update Tickets\n\n**When to use**: User wants to create new tickets or modify existing ones\n\n**Tool sequence**:\n1. `ZENDESK_SEARCH_ZENDESK_USERS` - Find requester\u002Fassignee [Prerequisite]\n2. `ZENDESK_CREATE_ZENDESK_TICKET` - Create a new ticket [Required]\n3. `ZENDESK_UPDATE_ZENDESK_TICKET` - Update ticket fields [Optional]\n4. `ZENDESK_DELETE_ZENDESK_TICKET` - Delete a ticket [Optional]\n\n**Key parameters**:\n- `subject`: Ticket subject line\n- `description`: Ticket body (for creation; becomes first comment)\n- `priority`: 'urgent', 'high', 'normal', 'low'\n- `status`: 'new', 'open', 'pending', 'hold', 'solved', 'closed'\n- `type`: 'problem', 'incident', 'question', 'task'\n- `assignee_id`: Agent user ID to assign\n- `requester_id`: Requester user ID\n- `tags`: Array of tag strings\n- `ticket_id`: Ticket ID (for update\u002Fdelete)\n\n**Pitfalls**:\n- Tags on UPDATE REPLACE existing tags entirely; merge with current tags to preserve them\n- Use `safe_update` with `updated_stamp` to prevent concurrent modification conflicts\n- DELETE is permanent and irreversible; tickets cannot be recovered\n- `description` is only used on creation; use REPLY_ZENDESK_TICKET to add comments after creation\n- Closed tickets cannot be updated; create a follow-up ticket instead\n\n### 3. Reply to Tickets\n\n**When to use**: User wants to add comments or replies to tickets\n\n**Tool sequence**:\n1. `ZENDESK_GET_ZENDESK_TICKET_BY_ID` - Get current ticket state [Prerequisite]\n2. `ZENDESK_REPLY_ZENDESK_TICKET` - Add a reply\u002Fcomment [Required]\n\n**Key parameters**:\n- `ticket_id`: Ticket ID to reply to\n- `body`: Reply text content\n- `public`: Boolean; true for public reply, false for internal note\n- `author_id`: Author user ID (defaults to authenticated user)\n\n**Pitfalls**:\n- Set `public: false` for internal notes visible only to agents\n- Default is public reply which sends email to requester\n- HTML is supported in body text\n- Replying can also update ticket status simultaneously\n\n### 4. Manage Users\n\n**When to use**: User wants to find or create Zendesk users (agents, end-users)\n\n**Tool sequence**:\n1. `ZENDESK_SEARCH_ZENDESK_USERS` - Search for users [Required]\n2. `ZENDESK_CREATE_ZENDESK_USER` - Create a new user [Optional]\n3. `ZENDESK_GET_ABOUT_ME` - Get authenticated user info [Optional]\n\n**Key parameters**:\n- `query`: Search string (matches name, email, phone, etc.)\n- `name`: User's full name (required for creation)\n- `email`: User's email address\n- `role`: 'end-user', 'agent', or 'admin'\n- `verified`: Whether email is verified\n\n**Pitfalls**:\n- User search is fuzzy; may return partial matches\n- Creating a user with an existing email returns the existing user (upsert behavior)\n- Agent and admin roles may require specific plan features\n\n### 5. Manage Organizations\n\n**When to use**: User wants to list, create, or manage organizations\n\n**Tool sequence**:\n1. `ZENDESK_GET_ALL_ZENDESK_ORGANIZATIONS` - List all organizations [Required]\n2. `ZENDESK_GET_ZENDESK_ORGANIZATION` - Get specific organization [Optional]\n3. `ZENDESK_CREATE_ZENDESK_ORGANIZATION` - Create organization [Optional]\n4. `ZENDESK_UPDATE_ZENDESK_ORGANIZATION` - Update organization [Optional]\n5. `ZENDESK_COUNT_ZENDESK_ORGANIZATIONS` - Get total count [Optional]\n\n**Key parameters**:\n- `name`: Organization name (unique, required for creation)\n- `organization_id`: Organization ID for get\u002Fupdate\n- `details`: Organization details text\n- `notes`: Internal notes\n- `domain_names`: Array of associated domains\n- `tags`: Array of tag strings\n\n**Pitfalls**:\n- Organization names must be unique; duplicate names cause creation errors\n- Tags on UPDATE REPLACE existing tags (same behavior as tickets)\n- Domain names can be used for automatic user association\n\n## Common Patterns\n\n### Pagination\n\n**List endpoints**:\n- Use `page` (1-based) and `per_page` (max 100)\n- Check `next_page` URL in response; null means last page\n- `count` field gives total results\n\n### Ticket Lifecycle\n\n```\nnew -> open -> pending -> solved -> closed\n                  |          ^\n                  v          |\n                hold --------+\n```\n\n- `new`: Unassigned ticket\n- `open`: Assigned, being worked on\n- `pending`: Waiting for customer response\n- `hold`: Waiting for internal action\n- `solved`: Resolved, can be reopened\n- `closed`: Permanently closed, cannot be modified\n\n### User Search for Assignment\n\n```\n1. Call ZENDESK_SEARCH_ZENDESK_USERS with query (name or email)\n2. Extract user ID from results\n3. Use user ID as assignee_id in ticket creation\u002Fupdate\n```\n\n## Known Pitfalls\n\n**Tags Behavior**:\n- Tags on update REPLACE all existing tags\n- Always fetch current tags first and merge before updating\n- Tags are lowercase, no spaces (use underscores)\n\n**Safe Updates**:\n- Use `safe_update: true` with `updated_stamp` (ISO 8601) to prevent conflicts\n- Returns 409 if ticket was modified since the stamp\n\n**Deletion**:\n- Ticket deletion is permanent and irreversible\n- Consider setting status to 'closed' instead of deleting\n- Deleted tickets cannot be recovered via API\n\n**Rate Limits**:\n- Default: 400 requests per minute\n- Varies by plan tier\n- 429 responses include Retry-After header\n\n## Quick Reference\n\n| Task | Tool Slug | Key Params |\n|------|-----------|------------|\n| List tickets | ZENDESK_LIST_ZENDESK_TICKETS | page, per_page, sort_by |\n| Get ticket | ZENDESK_GET_ZENDESK_TICKET_BY_ID | ticket_id |\n| Create ticket | ZENDESK_CREATE_ZENDESK_TICKET | subject, description, priority |\n| Update ticket | ZENDESK_UPDATE_ZENDESK_TICKET | ticket_id, status, tags |\n| Reply to ticket | ZENDESK_REPLY_ZENDESK_TICKET | ticket_id, body, public |\n| Delete ticket | ZENDESK_DELETE_ZENDESK_TICKET | ticket_id |\n| Search users | ZENDESK_SEARCH_ZENDESK_USERS | query |\n| Create user | ZENDESK_CREATE_ZENDESK_USER | name, email |\n| My profile | ZENDESK_GET_ABOUT_ME | (none) |\n| List orgs | ZENDESK_GET_ALL_ZENDESK_ORGANIZATIONS | page, per_page |\n| Get org | ZENDESK_GET_ZENDESK_ORGANIZATION | organization_id |\n| Create org | ZENDESK_CREATE_ZENDESK_ORGANIZATION | name |\n| Update org | ZENDESK_UPDATE_ZENDESK_ORGANIZATION | organization_id, name |\n| Count orgs | ZENDESK_COUNT_ZENDESK_ORGANIZATIONS | (none) |\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":23,"source":24,"date_added":25,"description":7},"critical","community","2026-02-27","main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Fantigravity\u002Fzendesk-automation","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Sansar35\u002Fclaude-agent --skill zendesk-automation",{"tool":38,"command":39},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill zendesk-automation",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill zendesk-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fantigravity\u002Fzendesk-automation\u002FSKILL.md",true,[],[47,54,61,68,75,83],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M72DVAN1JYEA302MT0C5MGD6","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M72DV8J5NBRRM4RPDFRV95N7","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M72DV5EMHW0BHP9BZ167MDCB","zinc-database","Access ZINC (230M+ purchasable compounds). Search by ZINC ID\u002FSMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzinc-database\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M72DV216QY0E693ZPEVQ0DBS","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M72DTXQREMCRKA8NHCVKHN4W","zapier-workflows","Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to \"run\" any process. Also handles Perplexity-based research and Google Sheets data tracking.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M72DTT17TBSJ0Y8J2XZ4C9TZ","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[]]