[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F0JD6P30GT14TF37RWW0MN":3,"skill-same:01M6F0JD6P30GT14TF37RWW0MN":90},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6F0JD6P30GT14TF37RWW0MN","ask-graphql-mcp",null,"Use Ask GraphQL MCP to handle Web3 and on-chain questions through GraphQL endpoints (especially SubQuery\u002FSubGraph). Trigger by default for blockchain\u002FWeb3-related user requests (metrics, protocol activity, token\u002Fpool\u002Fstaking\u002Fgovernance analysis, query debugging). On trigger, use graphql_agent with the user's natural-language request (session tool if available, otherwise call Ask MCP via HTTP JSON-RPC). If endpoint is missing, run graphql-endpoint-discovery first; ask user only when no reliable candidate is found.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",67,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsn-hermes\u002Fask-graphql-mcp\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"ask","ask graphql mcp","MCP","GraphQL","blockchain","web3","metrics","endpoint","analysis","discovery","run","only","default","query","token","trigger","chain","ask user","activity","debugging","2026-11-10 10:12:30",false,"---\nname: ask-graphql-mcp\ndescription: Use Ask GraphQL MCP to handle Web3 and on-chain questions through GraphQL endpoints (especially SubQuery\u002FSubGraph). Trigger by default for blockchain\u002FWeb3-related user requests (metrics, protocol activity, token\u002Fpool\u002Fstaking\u002Fgovernance analysis, query debugging). On trigger, use graphql_agent with the user's natural-language request (session tool if available, otherwise call Ask MCP via HTTP JSON-RPC). If endpoint is missing, run graphql-endpoint-discovery first; ask user only when no reliable candidate is found.\n---\n\n# Ask GraphQL MCP\n\nUse this skill to solve Web3\u002Fon-chain questions via Ask GraphQL MCP and a target GraphQL endpoint.\n\n## Primary goal\n\nUse MCP tools by forwarding natural-language tasks and returning endpoint-specific answers.\n\nDo not use direct GraphQL calls as default behavior. Use MCP first.\n\n## Hard constraint: no direct-query bypass\n\nWhen this skill is triggered, always execute through Ask GraphQL MCP (`graphql_agent` or MCP JSON-RPC path), even if the model can compose GraphQL queries by itself.\n\nDirect GraphQL execution is allowed only when user explicitly requests bypassing Ask MCP.\n\n## Required inputs\n\nCollect these inputs before analysis:\n- User question or task (required)\n- GraphQL endpoint URL (required for execution; can be discovered via `graphql-endpoint-discovery`)\n- Plan mode: default `free`; switch to `paid` only when free-tier limit is reached or user explicitly asks\n- API key (required for paid mode)\n- Optional `X-ENDPOINT-AUTHORIZATION` when upstream endpoint is private\n\nWhen endpoint URL is missing:\n1. Run pre-skill `graphql-endpoint-discovery`\n2. If high-confidence endpoint candidate exists, continue automatically\n3. If ambiguous, ask user to confirm among top candidates\n4. If no candidate, ask user for endpoint directly\n\n## Deterministic invocation rules\n\nUse this exact routing logic:\n1. If task is Web3\u002Fon-chain related and user message includes explicit endpoint URL (`http:\u002F\u002F` or `https:\u002F\u002F`) -> call this skill directly.\n2. If task is Web3\u002Fon-chain related but endpoint URL is missing -> call `graphql-endpoint-discovery` first, then return here only when endpoint is resolved.\n3. If task is clearly non-Web3 and non-on-chain -> do not call this skill.\n4. In one user turn, at most one execution path is allowed:\n- direct `ask-graphql-mcp`, or\n- `graphql-endpoint-discovery` then `ask-graphql-mcp`\n\nNever ask user for endpoint before running `graphql-endpoint-discovery` once.\nNever replace `ask-graphql-mcp` with hand-written direct GraphQL execution unless user explicitly asks to bypass MCP.\n\n## MCP connection policy\n\n1. Default to free gateway: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp\u002Fgraphql-agent`\n2. Use paid gateway only when needed: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp`\n3. Always set `X-ENDPOINT` to the user endpoint\n4. Set `X-ENDPOINT-AUTHORIZATION` only when upstream endpoint requires auth\n5. In paid mode, include `X-API-KEY`\n\nUse templates from `references\u002Fconfig-templates.md` when you need to emit copy-ready JSON.\n\n## Agent execution workflow\n\n1. Confirm endpoint and user objective. If endpoint is missing, run `graphql-endpoint-discovery` first.\n2. Prefer session tool path: if `graphql_agent` is available in current session tool list, use it.\n3. If session tool is unavailable, use HTTP JSON-RPC path to Ask MCP gateway with required headers (`X-ENDPOINT`, optional `X-ENDPOINT-AUTHORIZATION`, and `X-API-KEY` in paid mode).\n4. Send the user task to MCP in natural language.\n5. Timeout policy: when question complexity is high, allow MCP\u002Fagent call timeout up to 2 minutes (120s) before treating it as failed.\n6. If needed, send one follow-up clarification prompt to MCP.\n7. Return MCP result with concise interpretation for the user.\n\n## HTTP JSON-RPC path (when session tool is unavailable)\n\nUse MCP gateway endpoint:\n- Free: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp\u002Fgraphql-agent`\n- Paid: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp`\n\nCall sequence:\n1. `tools\u002Flist` to verify `graphql_agent` is exposed by gateway\n2. `tools\u002Fcall` with:\n- `name: \"graphql_agent\"`\n- `arguments.question: \u003Cuser natural-language request>`\n\nThis path still uses MCP, not direct GraphQL querying.\n\n## Fallback workflow\n\nIf the task fails:\n1. Validate gateway URL matches current mode (free\u002Fpaid).\n2. Validate `X-ENDPOINT` format and reachability.\n3. Validate `X-ENDPOINT-AUTHORIZATION` for private endpoints.\n4. Validate `X-API-KEY` in paid mode.\n5. Retry with minimal known-good config.\n\nIf MCP returns free-tier rate limit\u002Fquota errors:\n- Guide user to create API key at `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002Fapi-keys\u002F`\n- Switch user to paid gateway `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp` with `X-API-KEY`\n- Explicitly ask user to provide API key now so execution can continue immediately\n- Provide a copy-ready paid config snippet with `X-API-KEY` placeholder in the same response\n- Do not end with only \"retry later\" or \"wait for reset\"; API key request must come first\n\nIf paid API key quota is exceeded:\n- Guide user to check usage\u002Fquota at `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002F`\n\n## Response standard\n\nFor endpoint analysis requests, structure responses as:\n1. Assumptions\n2. MCP answer summary\n3. Optional query\u002Fdetails provided by MCP\n4. Next step (run\u002Fverify\u002Fdebug)\n\nFor pure setup requests, provide one copy-ready JSON block plus a short verification checklist.\n\nWhen mentioning quota\u002Frate-limit failures, always include the correct billing link:\n- API key creation: `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002Fapi-keys\u002F`\n- Usage\u002Fquota check: `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002F`\n\nFor free-tier limit errors, treat API key guidance as highest-priority next action:\n- First line should clearly request API key from user\n- Include API key creation link in the same message\n- Include paid-mode gateway and required header keys\n\n## Rate-limit detection and mandatory wording\n\nTreat these as free-tier limit signals:\n- `rate limit exceeded`\n- `quota exceeded`\n- `too many requests`\n- `retryAfter`\n- `429`\n\nWhen any signal appears, reply with this mandatory first sentence pattern:\n- `Free quota reached. Please create an API key at https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002Fapi-keys\u002F and send it here so I can continue now.`\n\nThen include:\n1. Paid gateway URL: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp`\n2. Required paid header: `X-API-KEY`\n3. If relevant, quota page: `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002F`\n\nFor practical prompt patterns, read `references\u002Ftools-and-prompts.md`.\n","# Ask GraphQL MCP\n\nUse this skill to solve Web3\u002Fon-chain questions via Ask GraphQL MCP and a target GraphQL endpoint.\n\n## Primary goal\n\nUse MCP tools by forwarding natural-language tasks and returning endpoint-specific answers.\n\nDo not use direct GraphQL calls as default behavior. Use MCP first.\n\n## Hard constraint: no direct-query bypass\n\nWhen this skill is triggered, always execute through Ask GraphQL MCP (`graphql_agent` or MCP JSON-RPC path), even if the model can compose GraphQL queries by itself.\n\nDirect GraphQL execution is allowed only when user explicitly requests bypassing Ask MCP.\n\n## Required inputs\n\nCollect these inputs before analysis:\n- User question or task (required)\n- GraphQL endpoint URL (required for execution; can be discovered via `graphql-endpoint-discovery`)\n- Plan mode: default `free`; switch to `paid` only when free-tier limit is reached or user explicitly asks\n- API key (required for paid mode)\n- Optional `X-ENDPOINT-AUTHORIZATION` when upstream endpoint is private\n\nWhen endpoint URL is missing:\n1. Run pre-skill `graphql-endpoint-discovery`\n2. If high-confidence endpoint candidate exists, continue automatically\n3. If ambiguous, ask user to confirm among top candidates\n4. If no candidate, ask user for endpoint directly\n\n## Deterministic invocation rules\n\nUse this exact routing logic:\n1. If task is Web3\u002Fon-chain related and user message includes explicit endpoint URL (`http:\u002F\u002F` or `https:\u002F\u002F`) -> call this skill directly.\n2. If task is Web3\u002Fon-chain related but endpoint URL is missing -> call `graphql-endpoint-discovery` first, then return here only when endpoint is resolved.\n3. If task is clearly non-Web3 and non-on-chain -> do not call this skill.\n4. In one user turn, at most one execution path is allowed:\n- direct `ask-graphql-mcp`, or\n- `graphql-endpoint-discovery` then `ask-graphql-mcp`\n\nNever ask user for endpoint before running `graphql-endpoint-discovery` once.\nNever replace `ask-graphql-mcp` with hand-written direct GraphQL execution unless user explicitly asks to bypass MCP.\n\n## MCP connection policy\n\n1. Default to free gateway: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp\u002Fgraphql-agent`\n2. Use paid gateway only when needed: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp`\n3. Always set `X-ENDPOINT` to the user endpoint\n4. Set `X-ENDPOINT-AUTHORIZATION` only when upstream endpoint requires auth\n5. In paid mode, include `X-API-KEY`\n\nUse templates from `references\u002Fconfig-templates.md` when you need to emit copy-ready JSON.\n\n## Agent execution workflow\n\n1. Confirm endpoint and user objective. If endpoint is missing, run `graphql-endpoint-discovery` first.\n2. Prefer session tool path: if `graphql_agent` is available in current session tool list, use it.\n3. If session tool is unavailable, use HTTP JSON-RPC path to Ask MCP gateway with required headers (`X-ENDPOINT`, optional `X-ENDPOINT-AUTHORIZATION`, and `X-API-KEY` in paid mode).\n4. Send the user task to MCP in natural language.\n5. Timeout policy: when question complexity is high, allow MCP\u002Fagent call timeout up to 2 minutes (120s) before treating it as failed.\n6. If needed, send one follow-up clarification prompt to MCP.\n7. Return MCP result with concise interpretation for the user.\n\n## HTTP JSON-RPC path (when session tool is unavailable)\n\nUse MCP gateway endpoint:\n- Free: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp\u002Fgraphql-agent`\n- Paid: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp`\n\nCall sequence:\n1. `tools\u002Flist` to verify `graphql_agent` is exposed by gateway\n2. `tools\u002Fcall` with:\n- `name: \"graphql_agent\"`\n- `arguments.question: \u003Cuser natural-language request>`\n\nThis path still uses MCP, not direct GraphQL querying.\n\n## Fallback workflow\n\nIf the task fails:\n1. Validate gateway URL matches current mode (free\u002Fpaid).\n2. Validate `X-ENDPOINT` format and reachability.\n3. Validate `X-ENDPOINT-AUTHORIZATION` for private endpoints.\n4. Validate `X-API-KEY` in paid mode.\n5. Retry with minimal known-good config.\n\nIf MCP returns free-tier rate limit\u002Fquota errors:\n- Guide user to create API key at `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002Fapi-keys\u002F`\n- Switch user to paid gateway `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp` with `X-API-KEY`\n- Explicitly ask user to provide API key now so execution can continue immediately\n- Provide a copy-ready paid config snippet with `X-API-KEY` placeholder in the same response\n- Do not end with only \"retry later\" or \"wait for reset\"; API key request must come first\n\nIf paid API key quota is exceeded:\n- Guide user to check usage\u002Fquota at `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002F`\n\n## Response standard\n\nFor endpoint analysis requests, structure responses as:\n1. Assumptions\n2. MCP answer summary\n3. Optional query\u002Fdetails provided by MCP\n4. Next step (run\u002Fverify\u002Fdebug)\n\nFor pure setup requests, provide one copy-ready JSON block plus a short verification checklist.\n\nWhen mentioning quota\u002Frate-limit failures, always include the correct billing link:\n- API key creation: `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002Fapi-keys\u002F`\n- Usage\u002Fquota check: `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002F`\n\nFor free-tier limit errors, treat API key guidance as highest-priority next action:\n- First line should clearly request API key from user\n- Include API key creation link in the same message\n- Include paid-mode gateway and required header keys\n\n## Rate-limit detection and mandatory wording\n\nTreat these as free-tier limit signals:\n- `rate limit exceeded`\n- `quota exceeded`\n- `too many requests`\n- `retryAfter`\n- `429`\n\nWhen any signal appears, reply with this mandatory first sentence pattern:\n- `Free quota reached. Please create an API key at https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002Fapi-keys\u002F and send it here so I can continue now.`\n\nThen include:\n1. Paid gateway URL: `https:\u002F\u002Fask-api.hermes-subnet.ai\u002Fmcp`\n2. Required paid header: `X-API-KEY`\n3. If relevant, quota page: `https:\u002F\u002Fask.hermes-subnet.ai\u002Fbilling\u002F`\n\nFor practical prompt patterns, read `references\u002Ftools-and-prompts.md`.\n",{"name":5,"description":7},"main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fsn-hermes\u002Fask-graphql-mcp",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill ask-graphql-mcp",{"tool":64,"command":65},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill ask-graphql-mcp",{"tool":67,"command":68},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill ask-graphql-mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsn-hermes\u002Fask-graphql-mcp\u002FSKILL.md",true,[72,78,82,86],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"agents\u002Fopenai.yaml","REFERENCE","参考文档",942,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsn-hermes\u002Fask-graphql-mcp\u002Fagents\u002Fopenai.yaml",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fconfig-templates.md",2964,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsn-hermes\u002Fask-graphql-mcp\u002Freferences\u002Fconfig-templates.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Ftools-and-prompts.md",2104,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsn-hermes\u002Fask-graphql-mcp\u002Freferences\u002Ftools-and-prompts.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"skill-report.json",10231,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsn-hermes\u002Fask-graphql-mcp\u002Fskill-report.json",[91,101,110,119,125,132],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":97,"publishedAt":44},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[96],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[98,99,100],"model","model hierarchy","model hierarchy skill",{"skillNo":102,"name":103,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":44},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[106],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[26,108,109],"zoom","zoom mcp",{"skillNo":111,"name":112,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":44},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[116,117,118,108],"sdk","zoom apps sdk","apps",{"skillNo":120,"name":121,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":44},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[121],{"skillNo":126,"name":127,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":44},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[130],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[127],{"skillNo":133,"name":134,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":44},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[134]]