[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AB5AF2SC515JF3VXTH90Y":3,"skill-same:01M69AB5AF2SC515JF3VXTH90Y":58},{"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":18,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M69AB5AF2SC515JF3VXTH90Y","sharepoint-file-creation",null,"Source\u002Fgenerate the requested file using whatever content rules apply to the use case, gate it against an evidence-based pre-upload size threshold using the filesystem API, and upload it to SharePoint via the Create file tool's confirmed \u002Fapp\u002Fcreated\u002F path-reference mechanism — without ever streaming raw file bytes through the LLM. Use this skill whenever a request asks for a file to be produced and uploaded to SharePoint, whether or not the user specifies a path, filename, format, or content source.","microsoft\u002Fcat-agent-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69A1AHE1MABT7GVP5143M5Z",103,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsharepoint-file-creation\u002FSKILL.md",[],[19],"sharepoint file creation","2026-11-10 10:12:30",false,"---\nname: sharepoint-file-creation\ndescription: Source\u002Fgenerate the requested file using whatever content rules apply to the use case, gate it against an evidence-based pre-upload size threshold using the filesystem API, and upload it to SharePoint via the Create file tool's confirmed \u002Fapp\u002Fcreated\u002F path-reference mechanism — without ever streaming raw file bytes through the LLM. Use this skill whenever a request asks for a file to be produced and uploaded to SharePoint, whether or not the user specifies a path, filename, format, or content source.\n---\n\n## Quick reference — the fixed sequence\n\n1. Determine what content\u002Fformat is being asked for and source it (Section 0).\n2. Write the complete file under `\u002Fapp\u002Fcreated\u002F` only, with a descriptive unique name.\n3. Re-measure the final file's size with the filesystem API. Proceed only if\n   `0 \u003C size_bytes \u003C 4,000,000`; otherwise stop and offer options.\n4. Call Create file with the `\u002Fapp\u002Fcreated\u002F\u003Cname>` path bound directly as the content input.\n   Never read bytes into the model to populate it or target another directory.\n5. Report: content source, destination, measured size, and upload result.\n\nTreat steps 2–5 as fixed; only step 1 is meant to flex per use case.\n\n## 0. Determine and source the content\n\nApply any configured content-generation rules first, including required templates,\nknowledge sources, data sources, report structures, schemas, or style guides.\n\nWhen no more specific rules are configured:\n- Identify the requested file format and use the appropriate runtime library. Do not default\n  to plain text unless plain text is requested.\n- Ground the content in the user's request, available retrieval\u002Fknowledge tools, or prior\n  conversation context.\n- If a named source cannot be located, or no source can be identified, ask rather than\n  fabricating content.\n\nProduce a complete, correct file before continuing.\n\n## 1. Generate the file in \u002Fapp\u002Fcreated\u002F only\n\nWrite the complete file beneath `\u002Fapp\u002Fcreated\u002F` using a SharePoint-safe, sanitized\nbasename-only, collision-resistant filename. Retain `[A-Za-z0-9_-]` in the stem, replace\nother runs with `_`, trim separators, and preserve one valid extension. Reject path\nseparators, `..`, and control characters; resolve the candidate path and verify it remains\nunder `\u002Fapp\u002Fcreated\u002F` before writing or uploading.\n\nUse `\u002Fapp\u002Fcreated\u002F` because it is the confirmed path-reference location for Create file.\nOther paths may be uploaded as literal path text instead of file content, causing silent\ncorruption.\n\nKeep bytes inside the runtime: never print, preview, or return generated content through the\nmodel. Track the validated path, filename, and byte count internally for upload, but do not\nexpose the sandbox path in normal user-facing responses.\n\n## 2. Measure and gate the size — always on the final written file\n\nAfter the file is fully written and closed, measure it with the runtime filesystem API\n(`os.path.getsize`, `os.stat().st_size`, or equivalent). Never estimate from text length,\nrow counts, token counts, or a measurement taken before the final write.\n\nProceed only when `0 \u003C size_bytes \u003C 4,000,000`. This conservative gate addresses the current\ninline connector\u002Ftool upload boundary; it is not a SharePoint file-size limit or a platform\nguarantee.\n\nIf the file is empty, unreadable, or at least 4,000,000 bytes, do not call Create file.\nReport the measured size and offer to reduce the content or split it into multiple files.\nDo not truncate, regenerate, or split automatically without the user's approval.\n\n## 3. Hand the reference to SharePoint Create file\n\nUse the configured Create file tool's existing input schema. Site and folder come from\nwhatever is already fixed\u002Fconfigured for this tool; do not ask the user to restate config\nthat is pre-set, only ask if the destination is genuinely undetermined.\n\nBind the validated `\u002Fapp\u002Fcreated\u002F` path as the tool's content input directly (e.g. the file\ninput value is the absolute `\u002Fapp\u002Fcreated\u002F\u003Cname>` path). Do not wrap it in JSON, do not\nbase64-encode it, do not read it into the model to populate the argument — the runtime\u002Ftool\nresolves that path to real bytes server-side. This is the confirmed mechanism, not a\nhypothesis: verified across two connectors, two sessions, and re-verified with byte-for-byte\nhash matches on 1 MB and 2 MB files.\n\n**Authorization model:** when the user's original request already asks for both generation\nand upload in one instruction, treat that as authorization to proceed through the upload\nwithout a second blocking confirmation round-trip. Still surface the destination, filename,\nmeasured size, and content source in the final report for transparency. Fall back to an\nexplicit pre-upload confirmation step only when the request is ambiguous about whether upload\nwas actually wanted, the destination is not already fixed\u002Fconfigured, or the content touches\nanything sensitive.\n\n## 4. Report\n\nState clearly: what was generated (type and content source), the destination in SharePoint\n(site\u002Flibrary\u002Ffolder path or URL and filename), the measured size, and the upload result.\nNever claim an upload succeeded without tool evidence.\n\n**Do not surface the internal sandbox path** (e.g. `\u002Fapp\u002Fcreated\u002F\u003Cname>`) in a normal\nuser-facing report — it is a runtime implementation detail, not something a user asking to\n\"generate and upload a file\" needs or expects to see. Refer to the file by its name only,\nplus where it landed in SharePoint. Only include the raw sandbox path when the user is\nexplicitly debugging or testing the skill itself, and say so if asked directly.\n\n## 5. Failure handling\n\n- Permission\u002FDLP\u002Fauthentication\u002Funsupported-operation errors: stop and report; these are not\n  sizing issues, so do not reinterpret them as such.\n- Size-boundary errors even under the 4,000,000-byte gate: stop and report the exact error\n  text and byte count. Treat this as evidence that the threshold may need tightening; do not\n  retry with a slightly smaller guess. Tell the user to contact the agent owner to report the\n  limitation.\n- Ambiguous or timeout outcomes: report the upload result as unknown. Never blindly retry a\n  write whose outcome is unclear.\n","## Quick reference — the fixed sequence\n\n1. Determine what content\u002Fformat is being asked for and source it (Section 0).\n2. Write the complete file under `\u002Fapp\u002Fcreated\u002F` only, with a descriptive unique name.\n3. Re-measure the final file's size with the filesystem API. Proceed only if\n   `0 \u003C size_bytes \u003C 4,000,000`; otherwise stop and offer options.\n4. Call Create file with the `\u002Fapp\u002Fcreated\u002F\u003Cname>` path bound directly as the content input.\n   Never read bytes into the model to populate it or target another directory.\n5. Report: content source, destination, measured size, and upload result.\n\nTreat steps 2–5 as fixed; only step 1 is meant to flex per use case.\n\n## 0. Determine and source the content\n\nApply any configured content-generation rules first, including required templates,\nknowledge sources, data sources, report structures, schemas, or style guides.\n\nWhen no more specific rules are configured:\n- Identify the requested file format and use the appropriate runtime library. Do not default\n  to plain text unless plain text is requested.\n- Ground the content in the user's request, available retrieval\u002Fknowledge tools, or prior\n  conversation context.\n- If a named source cannot be located, or no source can be identified, ask rather than\n  fabricating content.\n\nProduce a complete, correct file before continuing.\n\n## 1. Generate the file in \u002Fapp\u002Fcreated\u002F only\n\nWrite the complete file beneath `\u002Fapp\u002Fcreated\u002F` using a SharePoint-safe, sanitized\nbasename-only, collision-resistant filename. Retain `[A-Za-z0-9_-]` in the stem, replace\nother runs with `_`, trim separators, and preserve one valid extension. Reject path\nseparators, `..`, and control characters; resolve the candidate path and verify it remains\nunder `\u002Fapp\u002Fcreated\u002F` before writing or uploading.\n\nUse `\u002Fapp\u002Fcreated\u002F` because it is the confirmed path-reference location for Create file.\nOther paths may be uploaded as literal path text instead of file content, causing silent\ncorruption.\n\nKeep bytes inside the runtime: never print, preview, or return generated content through the\nmodel. Track the validated path, filename, and byte count internally for upload, but do not\nexpose the sandbox path in normal user-facing responses.\n\n## 2. Measure and gate the size — always on the final written file\n\nAfter the file is fully written and closed, measure it with the runtime filesystem API\n(`os.path.getsize`, `os.stat().st_size`, or equivalent). Never estimate from text length,\nrow counts, token counts, or a measurement taken before the final write.\n\nProceed only when `0 \u003C size_bytes \u003C 4,000,000`. This conservative gate addresses the current\ninline connector\u002Ftool upload boundary; it is not a SharePoint file-size limit or a platform\nguarantee.\n\nIf the file is empty, unreadable, or at least 4,000,000 bytes, do not call Create file.\nReport the measured size and offer to reduce the content or split it into multiple files.\nDo not truncate, regenerate, or split automatically without the user's approval.\n\n## 3. Hand the reference to SharePoint Create file\n\nUse the configured Create file tool's existing input schema. Site and folder come from\nwhatever is already fixed\u002Fconfigured for this tool; do not ask the user to restate config\nthat is pre-set, only ask if the destination is genuinely undetermined.\n\nBind the validated `\u002Fapp\u002Fcreated\u002F` path as the tool's content input directly (e.g. the file\ninput value is the absolute `\u002Fapp\u002Fcreated\u002F\u003Cname>` path). Do not wrap it in JSON, do not\nbase64-encode it, do not read it into the model to populate the argument — the runtime\u002Ftool\nresolves that path to real bytes server-side. This is the confirmed mechanism, not a\nhypothesis: verified across two connectors, two sessions, and re-verified with byte-for-byte\nhash matches on 1 MB and 2 MB files.\n\n**Authorization model:** when the user's original request already asks for both generation\nand upload in one instruction, treat that as authorization to proceed through the upload\nwithout a second blocking confirmation round-trip. Still surface the destination, filename,\nmeasured size, and content source in the final report for transparency. Fall back to an\nexplicit pre-upload confirmation step only when the request is ambiguous about whether upload\nwas actually wanted, the destination is not already fixed\u002Fconfigured, or the content touches\nanything sensitive.\n\n## 4. Report\n\nState clearly: what was generated (type and content source), the destination in SharePoint\n(site\u002Flibrary\u002Ffolder path or URL and filename), the measured size, and the upload result.\nNever claim an upload succeeded without tool evidence.\n\n**Do not surface the internal sandbox path** (e.g. `\u002Fapp\u002Fcreated\u002F\u003Cname>`) in a normal\nuser-facing report — it is a runtime implementation detail, not something a user asking to\n\"generate and upload a file\" needs or expects to see. Refer to the file by its name only,\nplus where it landed in SharePoint. Only include the raw sandbox path when the user is\nexplicitly debugging or testing the skill itself, and say so if asked directly.\n\n## 5. Failure handling\n\n- Permission\u002FDLP\u002Fauthentication\u002Funsupported-operation errors: stop and report; these are not\n  sizing issues, so do not reinterpret them as such.\n- Size-boundary errors even under the 4,000,000-byte gate: stop and report the exact error\n  text and byte count. Treat this as evidence that the threshold may need tightening; do not\n  retry with a slightly smaller guess. Tell the user to contact the agent owner to report the\n  limitation.\n- Ambiguous or timeout outcomes: report the upload result as unknown. Never blindly retry a\n  write whose outcome is unclear.\n",{"name":5,"description":7},"main","3678d23ad8fb8d098c428302a98044ac9514d5a1","submissions\u002Fsharepoint-file-creation",118,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-07 09:09:13",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add microsoft\u002Fcat-agent-skills --skill sharepoint-file-creation",{"tool":40,"command":41},"bunx","bunx skills add microsoft\u002Fcat-agent-skills --skill sharepoint-file-creation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add microsoft\u002Fcat-agent-skills --skill sharepoint-file-creation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsharepoint-file-creation\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"metadata.json","REFERENCE","参考文档",452,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsharepoint-file-creation\u002Fmetadata.json",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"README.md",2299,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsharepoint-file-creation\u002FREADME.md",[59,86,111,149,167,183],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":20},"01M6X3P09R8SJH3QJGMTAA5N90","stakeholder-and-decision-map","Mines customer interactions to identify stakeholders, infer their likely roles and engagement, map the decision process, and highlight who or what may be missing. Use when asked to \"map a deal's buying group\", identify influential or missing stakeholders, \"assess who has gone quiet\", or \"explain how the customer will decide\". Do not use for phased engagement plans, contact sequences, choosing or drafting outreach to the single next contact, seller or team performance reviews, or contacting, scheduling, or changing records.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fstakeholder-and-decision-map\u002FSKILL.md",[],[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85],"decision","map","decision map","stakeholder and decision map","performance","customer","team","how","decide","do","next","infer","missing","records","assess","reviews","for","single","when","sequences",{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":20},"01M6X3NRES2XSZQCH015WD4JN6","sales-progress-update","Creates or refreshes a sales progress update for a manager or team about work done, deal movement, pending outcomes, supported forecast position, and help needed. Use when asked to \"create my weekly sales update\", \"refresh my sales progress deck\", \"report my forecast position\", \"where do I stand against my quarter forecast\", or \"catch my manager up on committed deals\". Do NOT use for non-sales project updates, a since-date deal change digest, momentum or blocker analysis, meeting prep, or outreach drafting.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsales-progress-update\u002FSKILL.md",[],[93,94,95,96,97,98,99,100,72,101,102,103,104,105,106,107,108,109,110,84],"update","sales","progress","sales progress update","change","create","meeting prep","analysis","work","up","done","digest","project","my","updates","manager","weekly","catch",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":130,"publishedAt":20},"01M6X3MSDTB1E5H6DQAFAY41YP","submission-assemble","Put the checked CSR or 510(k) sections together in template order with a reviewer-facing open-items register, as a draft package for human sign-off. Use when the user asks \"assemble the CSR draft\", \"put the module together for review\", \"build the review package with the open items on top\", \"compile the 510(k) sections in order\" or \"package this up for the submission lead\". Do NOT use for assembling an unchecked draft - use consistency-check instead. Do NOT use for loading protocol, SAP or TLF sources - use source-ingest instead. Do NOT use for compiling general documents or slide decks - use the built-in docx or pptx skill instead. Do NOT use for filing or submitting to a regulator - use the sponsor's validated gateway, operated by a human, instead. Guardrail: draft for human approval only (L1); status is draft_clean or draft_open_items, never submitted.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Freg-submission-authoring\u002Fsubmission-assemble\u002FSKILL.md",[117,122,125],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":123,"categoryName":124,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[131,132,133,134,135,136,137,138,139,140,141,142,102,143,144,145,146,147,148,84],"assemble","submission","submission assemble","docx","pptx","writing","documents","healthcare","open","reviewer","never","only","clean","guardrail","slide decks","sources","filing","loading",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":20},"01M6X3MM9TVWDQ716QGNV4DS25","source-ingest","Pull every number, date and population definition out of a study's protocol, SAP, TLF tables, investigator brochure and prior approved text into one cited fact map, keyed per config\u002Ffield-dictionary.json, before any CSR or 510(k) section is written. Use when the user asks \"here's the locked TLF set and SAP, set up the CSR\", \"load the protocol and tables before we start drafting\", \"what figures do we have from the database lock?\", \"pull the disposition counts out of Table 14.1.1\" or \"ingest the IB for the 510(k)\". Do NOT use for drafting or assembling submission sections - use section-draft or submission-assemble instead. Do NOT use for reconciling a patient's medications - use the discharge-care-transition plugin instead. Guardrail: reads and cites sources only; never estimates, rounds or invents a fact.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Freg-submission-authoring\u002Fsource-ingest\u002FSKILL.md",[],[156,157,158,159,160,100,138,161,141,142,102,67,162,144,146,163,164,165,166,84],"source ingest","ingest","source","database","SET","text","patient","number","lock","definition","transition",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":174,"publishedAt":20},"01M6X3M7ZH5ZNEHP56BQ74HAJR","section-plan","Work out which sections a CSR or 510(k) requires, from the templates in config, check each one against the cited fact map, and name what is missing before a word is drafted. Use when the user asks \"what do we still need before we can draft the CSR?\", \"which sections are ready to start?\", \"what's blocking the performance data section?\", \"do we have everything for the synopsis?\" or \"map our tables to the E3 structure\". Do NOT use for writing section language - use section-draft instead. Do NOT use for cross-checking a finished draft - use consistency-check instead. Do NOT use for outlining general Word documents or business reports - use the built-in docx skill instead. Only structures with a template in config are supported. Guardrail: plans only; never marks a section ready on a missing fact and never invents a structure.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Freg-submission-authoring\u002Fsection-plan\u002FSKILL.md",[173],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},[175,176,177,134,136,70,137,100,138,101,141,142,178,179,180,67,144,181,182,84],"plan","section","section plan","ready","reports","structure","word documents","which",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":20},"01M6X3M0V1MJNCR653ES9XGVMS","section-draft","Write or revise the language for one planned CSR or 510(k) section - synopsis, efficacy, safety, discussion, device description - using only figures already in the cited fact map, each with its TLF or SAP citation. Use when the user asks \"draft the Synopsis from our locked tables\", \"write up safety from Table 14.3.1\", \"give me a first pass at the discussion\", \"draft the device description for the 510(k)\" or \"tighten the wording of the Discussion section\". Do NOT use for supplying a number not already in source_facts - use source-ingest instead. Do NOT use for verifying a draft's figures - use consistency-check instead. Do NOT use for appeal letters, clinical notes or discharge summaries - use the matching HLS plugin instead. Guardrail: drafts for human approval only (L1); never asserts an unsourced number or harmonises two figures.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Freg-submission-authoring\u002Fsection-draft\u002FSKILL.md",[],[190,176,191,136,192,138,193,141,142,102,194,67,195,196,197,144,198,163,199,84],"draft","section draft","notes","write","me","human","life","clinical","drafts","at"]