[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71895KCS8K44E1JFJTAX372":3,"skill-same:01M71895KCS8K44E1JFJTAX372":160},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":26,"linkOnly":27,"markdownContent":28,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M71895KCS8K44E1JFJTAX372","knowledge-wiki",null,"anthropics\u002Fclaude-quickstarts","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7188R62QSTJZJJ3DFX7XFT5",20861,"MIT","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fskill.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[23,24,25],"wiki","knowledge","knowledge wiki","2026-11-10 10:12:30",false,"# Setting up the knowledge-wiki quickstart\n\nFollow these steps in order when the user asks you to set up or run\nthis quickstart. Confirm each step's output before moving to the next.\n\n## 0. Check access\n\nEverything runs on **Managed Agents** (beta) — memory stores, agents, sessions\nand dynamic workflows — which is enabled by default for API organizations; the\nSDK sends the beta headers itself. If `client.beta.memory_stores.create` or\n`client.beta.agents.create` returns a permission error later, the user should ask their organization's\nadmin whether it was turned off or the key restricted. Python 3.11 or later is\nrequired.\n\n## 1. Install dependencies\n\n```bash\npip install -r requirements.txt\n```\n\n`requirements.txt` pins the `anthropic` Python SDK at `>=2.0.0,\u003C3`. If the user already\nhad an older version in the environment, confirm the upgrade took:\n\n```bash\npython3 -c \"import anthropic; print(anthropic.__version__)\"\n```\n\nIf that prints a version below 2.0, run `pip install -U \"anthropic>=2.0.0,\u003C3\"`.\n\n## 2. Authentication and environment\n\nThe notebook constructs `Anthropic()` with no credential arguments, so it resolves\ncredentials through the standard chain and uses the first one it finds:\n`ANTHROPIC_API_KEY`, then `ANTHROPIC_AUTH_TOKEN`, then the profile\n`ANTHROPIC_PROFILE` names, then Workload Identity Federation, then the\nactive `ant auth login` profile. Pick whichever the user's org uses:\n\n```bash\n# Either an API key…\nexport ANTHROPIC_API_KEY=...\n\n# …or an interactive login with the ant CLI, version 2.0 or later (ant --version prints it),\n# which stores a profile the SDK finds on its own.\nant auth login\n```\n\nDo not set `ANTHROPIC_API_KEY` alongside a profile — a stale exported key\nsilently shadows the profile. A key set next to `ANTHROPIC_AUTH_TOKEN` wins\ntoo (the SDK logs a warning and uses the key). `ant auth status` shows\nwhich credential source won.\n\nOne more variable is required regardless:\n\n```bash\nexport EDGAR_USER_AGENT=\"your-name your-email\"  # SEC policy\n```\n\nIf `EDGAR_USER_AGENT` is missing, the scripts send a placeholder contact,\nwhich SEC may throttle or refuse.\n\n## 3. Pick a tier and set the cost expectation\n\nBefore fetching, tell the user what the `core` run cost. For other tiers, say no\nfigure was recorded, and that the notebook prints an estimate before the build\nand stops if it is over budget.\n\n| Tier | Docs | Use when |\n|---|---|---|\n| `core` (default) | 8 filings (annual reports, proxies, a 10-Q, the deal's 8-Ks), 2.8 MB text | the recorded run, 23 min and ≈ $16 at list price on the default models: the demo questions and the measured comparison are written for it |\n| `quickstart` | 8 short deal-window filings | a first look at the mechanics on short filings |\n| `mini` | 26: the smaller deal-window filings | more documents, less text than core |\n| `standard` | 37 | the larger room |\n| `full` | all 42 deal-window filings | every filing in the deal window; it leaves out core's FY2022 annual report |\n\nOnly `core` was recorded (Claude Haiku 5.5 for the agents that read, Claude\nSonnet 5.5 for the lead agent and the raw-documents baseline, thinking at the\nplatform's default); the user's run will vary with model choice and API pricing\nat the time. For any tier the notebook prints its own list-price estimate for\nthe chosen corpus before the build (the cell that creates the agents) and stops\nif it is over `BUDGET_USD`; the build session also carries that budget as a cap\n(the platform stops new work there, to within one model request per working\nagent). Empty `data_room\u002Fdocs` before fetching a different tier: the build\nreads whatever is in the folder, and the fetch script stops if it finds\nanother tier's files there.\n\n## 4. Fetch the corpus\n\nRun in this order (network required):\n\n```bash\npython3 fetch_data_room.py --tier=core    # or the tier chosen in step 3\npython3 fetch_real_deck.py                # optional: 6 slides of a real board deck (~1 MB)\npython3 make_analyst_docx.py              # optional: regenerates the Word note that ships in example_data\u002F\n```\n\nAll five manifests ship with the folder, so nothing else is needed before the\nfetch. `build_manifest.py` is an optional refresh from EDGAR: it rewrites the\nquickstart, mini, standard and full manifests (never core), so run it before\n`fetch_data_room.py` if at all, not after. Expected after this:\n`data_room\u002Fdocs\u002F` contains one `.txt` file per document in the chosen tier\n— 8 files for `core` (about 2.8 MB) or `quickstart`, 26 for `mini` — and\nthe notebook's normalize step adds the two synthetic files, plus the deck if it was\nfetched.\n\n## 5. Open the notebook\n\n```bash\njupyter lab distill_documents_into_knowledge_wiki.ipynb\n```\n\nRecommend the user reads `README.md` §\"How it works\" before running cells\n— the pipeline has a few non-obvious steps (the schema seeded into the\nstore, one message stating the goal and naming the agents, the checks on what ran, the\nread-only analyst attach).\n\n## Gotchas to warn about\n\n- The build is one long cell (Run the build): it prints each phase and thread as it\n  starts; tell the user to kick it off and check back rather than watching\n  it. If the kernel is interrupted, the cell's `finally` asks the agent to\n  stop the run, waits for it to end, then saves the records and archives the\n  session; the wiki store keeps what was written. If it prints that a\n  session was not archived, archive it by hand: an open run keeps spending\n  until it reaches the budget.\n- The message states the goal and names the agents, and the lead agent writes\n  the workflow; after the run the notebook asks the lead agent to print the\n  workflow it wrote and sets that beside the platform's records (Check what ran). The reprint is the\n  lead agent's account; if it and the records disagree, the records win.\n- Model choice: by default the agents that read (extractors, resolver,\n  analyzers, organizer, analysts) run on `claude-haiku-5-5` and the lead agent\n  and the raw-documents baseline on `claude-sonnet-5-5`. `COOKBOOK_MODEL` sets\n  every stage; `COOKBOOK_BUILD_MODEL` (extractors, resolver),\n  `COOKBOOK_CONSOLIDATE_MODEL` (analyzers, organizer), `COOKBOOK_QUERY_MODEL`\n  (analysts), `COOKBOOK_LEAD_MODEL` (the lead agent) and\n  `COOKBOOK_BASELINE_MODEL` (the baseline in \"What it costs\") override one\n  stage each. The extractors and analyzers read the whole corpus and are most\n  of the cost.\n- Run records go under the system's temporary directory (`\u002Ftmp\u002Fknowledge_wiki-\u003Cuid>\u002Fruns\u002F`,\n  readable only by the user; or `COOKBOOK_RECORDS_DIR`), never into the repository: they\n  hold the documents' contents.\n- If the user hits a permission error on `client.beta.memory_stores.create`,\n  see step 0.\n",{},"main","4a4224bdf0e9cfb3332167b69c90457403813625","managed-agents\u002Fknowledge-wiki",3490,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-07 03:37:57",{"source":7,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add anthropics\u002Fclaude-quickstarts --skill knowledge-wiki",{"tool":44,"command":45},"bunx","bunx skills add anthropics\u002Fclaude-quickstarts --skill knowledge-wiki",{"tool":47,"command":48},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-quickstarts --skill knowledge-wiki","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fskill.md",true,[52,58,64,68,72,78,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152,156],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},".gitignore","OTHER","其他",72,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002F.gitignore",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"assets\u002Fwiki_benchmark.png","ASSET","资产文件",225799,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fassets\u002Fwiki_benchmark.png",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"assets\u002Fwiki_flow.png",211765,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fassets\u002Fwiki_flow.png",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"assets\u002Fwiki_how_it_works.png",116841,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fassets\u002Fwiki_how_it_works.png",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"build_manifest.py","SCRIPT","脚本",6221,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fbuild_manifest.py",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"CLAUDE.md","REFERENCE","参考文档",1041,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002FCLAUDE.md",{"path":85,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":86,"sourceHtmlUrl":87},"distill_documents_into_knowledge_wiki.ipynb",176806,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fdistill_documents_into_knowledge_wiki.ipynb",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"example_data\u002Fanalyst_note_synthetic.md",1160,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fexample_data\u002Fanalyst_note_synthetic.md",{"path":93,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":94,"sourceHtmlUrl":95},"example_data\u002Fanalyst_note.docx",37448,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fexample_data\u002Fanalyst_note.docx",{"path":97,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":98,"sourceHtmlUrl":99},"example_data\u002Fdata_provider_extract.csv",787,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fexample_data\u002Fdata_provider_extract.csv",{"path":101,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":102,"sourceHtmlUrl":103},"fetch_data_room.py",6627,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Ffetch_data_room.py",{"path":105,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":106,"sourceHtmlUrl":107},"fetch_real_deck.py",1783,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Ffetch_real_deck.py",{"path":109,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":110,"sourceHtmlUrl":111},"make_analyst_docx.py",2570,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fmake_analyst_docx.py",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"manifest_core.json",2428,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fmanifest_core.json",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"manifest_full.json",11428,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fmanifest_full.json",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"manifest_mini.json",7083,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fmanifest_mini.json",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"manifest_quickstart.json",2241,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fmanifest_quickstart.json",{"path":129,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":130,"sourceHtmlUrl":131},"manifest_standard.json",10095,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fmanifest_standard.json",{"path":133,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":134,"sourceHtmlUrl":135},"prompts\u002Fanalyzer_system.md",10735,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fprompts\u002Fanalyzer_system.md",{"path":137,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":138,"sourceHtmlUrl":139},"prompts\u002Fbaseline_system.md",982,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fprompts\u002Fbaseline_system.md",{"path":141,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":142,"sourceHtmlUrl":143},"prompts\u002Flead_system.md",2385,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fprompts\u002Flead_system.md",{"path":145,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":146,"sourceHtmlUrl":147},"prompts\u002Forganizer_system.md",5659,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Fprompts\u002Forganizer_system.md",{"path":149,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":150,"sourceHtmlUrl":151},"README.md",7747,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002FREADME.md",{"path":153,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":154,"sourceHtmlUrl":155},"requirements.txt",255,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Frequirements.txt",{"path":157,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":158,"sourceHtmlUrl":159},"utilities.py",146196,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fknowledge-wiki\u002Futilities.py",[161,170,179,197,205,223],{"skillNo":162,"name":163,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":169,"publishedAt":26},"01M7189FFG0GVY39QBCTSYS5AZ","slack","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fslack\u002Fskill.md",[166],{"categoryNo":167,"categoryName":168,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通",[163],{"skillNo":171,"name":172,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":178,"publishedAt":26},"01M7189D8D3CX3FPQEWYRH9D95","sentry","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fsentry\u002Fskill.md",[175],{"categoryNo":176,"categoryName":177,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[172],{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":26},"01M7189B12649K1GD9TGXK7DBY","openshell-policy-advisor","Use when an OpenShell sandbox returns policy_denied, mentions policy.local, or needs a narrow network policy proposal.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fself-hosted-sandboxes\u002Fopenshell-policy\u002Fsandbox\u002Fopenshell-skills\u002Fpolicy-advisor\u002FSKILL.md",[],[186,187,188,189,190,191,192,193,194,195,196],"policy","advisor","openshell policy advisor","local","returns","when","use","proposal","denied","sandbox","network",{"skillNo":198,"name":199,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":202,"publishedAt":26},"01M71899E0V3MWC8B65EWJ5P5W","roadtrip-planner","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Froadtrip-planner\u002Fskill.md",[],[203,204],"planner","roadtrip planner",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":26},"01M71893K7X8AS2JDBAMGG4HPX","verify","Build and drive the copilot-kit-ag-ui demo to verify changes end-to-end.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fcopilot-kit-ag-ui\u002F.claude\u002Fskills\u002Fverify\u002FSKILL.md",[],[207,212,213,214,215,216,217,218,219,220,221,222],"kit","ui","ui demo","copilot","changes","build","Verify Changes","end","demo","ag","drive",{"skillNo":224,"name":225,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":228,"publishedAt":26},"01M718919ZDN6X8YK4K8RWGMAW","chat-sdk","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-quickstarts\u002Fblob\u002Fmain\u002Fmanaged-agents\u002Fchat-sdk\u002Fskill.md",[],[229,230,231],"chat sdk","chat","sdk"]