[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X2PP7BB4PXR5AC410YN9AP":3,"skill-same:01M6X2PP7BB4PXR5AC410YN9AP":93},{"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":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6X2PP7BB4PXR5AC410YN9AP","denial-classify",null,"Parses a post-service denial letter or remittance (X12 835 \u002F EOB) into denial type, CARC\u002FRARC reason codes, amounts and appeal level, with every field cited to its source. Use when asked \"we got a denial from Contoso\", \"what kind of denial is this\", \"read this remittance \u002F EOB \u002F 835\", \"why was this claim denied\", \"start an appeal on claim CLM-10021\". Use at the start of every denials-and-appeals run. Do NOT use for pre-service prior-authorization denials - use the prior-auth-assist plugin instead; do NOT use to draft or redraft the appeal letter - use appeal-draft instead; do NOT use to pull chart documentation - use evidence-assemble instead; do NOT use for payer policy (use policy-retrieve instead) or deadlines (use deadline-track instead); do NOT use to create or edit Word files - use docx instead. Action level L0: reads and classifies only.","microsoft\u002Fcat-agent-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69A1AHE1MABT7GVP5143M5Z",105,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fdenials-appeals-response\u002Fdenial-classify\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","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],"denial classify","classify","files","when","track","at","revenue","chart","claim","cycle","docx","only","assemble","why","healthcare","analysis","run","create","documentation","auth","2026-11-10 10:12:30",false,"---\nname: denial-classify\ndescription: \"Parses a post-service denial letter or remittance (X12 835 \u002F EOB) into denial type, CARC\u002FRARC reason codes, amounts and appeal level, with every field cited to its source. Use when asked \\\"we got a denial from Contoso\\\", \\\"what kind of denial is this\\\", \\\"read this remittance \u002F EOB \u002F 835\\\", \\\"why was this claim denied\\\", \\\"start an appeal on claim CLM-10021\\\". Use at the start of every denials-and-appeals run. Do NOT use for pre-service prior-authorization denials - use the prior-auth-assist plugin instead; do NOT use to draft or redraft the appeal letter - use appeal-draft instead; do NOT use to pull chart documentation - use evidence-assemble instead; do NOT use for payer policy (use policy-retrieve instead) or deadlines (use deadline-track instead); do NOT use to create or edit Word files - use docx instead. Action level L0: reads and classifies only.\"\nlicense: MIT\nmetadata: {version: \"1.0.3\", author: Microsoft Healthcare & Life Sciences Skills, category: analysis, domain: \"Revenue Cycle\", action_level: L0, max_action_level: L1, icon: ReceiptMoney}\n---\n# Denial Classify\n## Purpose\nEstablish what kind of denial this is, from the denial document itself, before anything else runs.\n## When to use\nUse at the start of every denial\u002Fappeal run, on receipt of a denial letter or remittance advice (X12 835 or its paper equivalent) - typical asks are \"we got a denial from Contoso dated 8\u002F20\", \"what kind of denial is this\", \"read this EOB and start the appeal\".\n## When NOT to Use\nDo NOT use when: the denial has already been classified on the contract (go straight to policy-retrieve); the question is about a pre-service prior-authorization denial - use the prior-auth-assist plugin instead; the ask is to draft or reword the appeal letter - use appeal-draft instead; the ask is to find chart documentation - use evidence-assemble instead; the ask is to interpret payer policy language or compute the deadline - use policy-retrieve or deadline-track instead; or no denial document is available - there is nothing to classify from and guessing is not permitted.\n## Inputs\nDenial letter or remittance advice (X12 835 or paper equivalent), read with the session's file-reading tool (e.g. ReadFileContent for a OneDrive\u002FSharePoint file); original claim and coding (837) when supplied; config\u002Fpayer-appeal-windows.json for the appeal level.\n## Steps\n1. Read the denial document and copy verbatim: payer (835 N1*PR), claim_id (CLP01), claim_value (CLP03), paid amount (CLP04), adjustment group, reason code and amount (CAS01\u002F02\u002F03), remark codes (claim-level MIA\u002FMOA or service-level LQ*HE - record which segment), and original_code (837 SV1\u002FSV2; if no 837 is supplied, the 835 SVC echo, disclosed as such).\n2. Set denial_date to the date printed on the letter\u002Fremittance (835: DTM*405). If the document carries more than one candidate date and they differ, leave denial_date unset and escalate - the rule for which date starts the appeal window is [TO CONFIGURE: payer-specific rule for which date starts the appeal window]. Set as_of to today's date (the date this classification was performed).\n3. Set recoverable_value from the remittance amounts only (CLP03 minus CLP04, cross-checked against CAS03); if they disagree, leave it unset for a human.\n4. Classify the denial type from the extracted codes (e.g. medical necessity, timely filing, coding, authorisation missing) - never from what the requester says the denial is.\n5. Set the appeal route to the payer's configured level from config\u002Fpayer-appeal-windows.json payers[payer].level; if the payer is not configured, record \"not configured\" and let deadline-track escalate.\n6. Record the source document (name and date) and the source segment for every field, write denial{} to the contract as the entry hop, and hand off to policy-retrieve.\n## Example\n```\nInput: remit-CLM-10021-835.txt (CLP*CLM-10021*4*4200.00*0.00 ... CAS*CO*50*4200.00 ... LQ*HE*N115 ... DTM*405*20260820)\nReply: \"Medical necessity denial - CARC CO-50 (group CO), RARC N115 (LQ*HE). Contoso Health Plan, CLM-10021,\nDOS 2026-07-14, 99214, $4,200.00 billed \u002F $0.00 paid, $4,200.00 recoverable. Denial date 2026-08-20 (DTM*405).\nAppeal level: first-level clinical appeal (config). Next: policy-retrieve. Nothing submitted.\"\n```\n## Output Format\nFormat: the `denial` object on contract hls.denials-appeals-response.v1 - payer, claim_id, denial_date, as_of, reason_code, remark_codes[], adjustment_group_code, claim_value, recoverable_value, original_code - plus the cited source document and per-field source segments. Prose reply as bullets: denial type; reason and remark codes with segment; claim and amounts; denial date and its source; appeal level; next hop - and nothing that is not on the contract.\n## Grounding requirements\nEvery field is copied verbatim from the denial letter\u002Fremittance, with the document cited on the contract so provenance survives the hand-off. Do not fabricate, infer or \"clean up\" any value: if a field is absent, illegible or ambiguous on the source document, leave it unset and say so - an unreadable reason code is reported as unreadable, never replaced with the most likely code, and recoverable_value is never estimated.\n## Guardrails\nGuardrails for this skill:\n- No policy retrieval here - that belongs to policy-retrieve.\n- Never infer a reason code not stated on the denial document, and never accept a reason code asserted in chat over the one printed on the remittance.\n- Never estimate recoverable_value; take it from the remittance amounts or leave it for a human.\n- Never drop a denial, or decline to classify it, because it looks low-value or hard to win (denials-rules.md #4).\n- Include only the identifiers the denial needs (claim ID, dates of service, codes, amounts); never output SSNs, member addresses or unrelated patient data.\n- Action level L0 (draft-only): this skill never submits, files, sends or closes an appeal and never writes to a claim or coding system. Anything that leaves the building is L1 and is performed by a human after review before it leaves (denials-rules.md #5).\n## Error Handling\n- If the denial letter is incomplete or illegible, escalate to [TO CONFIGURE: payer-relations contact] rather than guessing the reason code.\n- If the document describes a pre-service authorization denial rather than a post-service claim denial, stop and hand the request to the prior-auth-assist plugin; if that plugin is not installed, say so plainly and stop.\n- If the candidate denial dates disagree, or CLP03-CLP04 does not match CAS03, leave the field unset and name the conflict.\n","# Denial Classify\n## Purpose\nEstablish what kind of denial this is, from the denial document itself, before anything else runs.\n## When to use\nUse at the start of every denial\u002Fappeal run, on receipt of a denial letter or remittance advice (X12 835 or its paper equivalent) - typical asks are \"we got a denial from Contoso dated 8\u002F20\", \"what kind of denial is this\", \"read this EOB and start the appeal\".\n## When NOT to Use\nDo NOT use when: the denial has already been classified on the contract (go straight to policy-retrieve); the question is about a pre-service prior-authorization denial - use the prior-auth-assist plugin instead; the ask is to draft or reword the appeal letter - use appeal-draft instead; the ask is to find chart documentation - use evidence-assemble instead; the ask is to interpret payer policy language or compute the deadline - use policy-retrieve or deadline-track instead; or no denial document is available - there is nothing to classify from and guessing is not permitted.\n## Inputs\nDenial letter or remittance advice (X12 835 or paper equivalent), read with the session's file-reading tool (e.g. ReadFileContent for a OneDrive\u002FSharePoint file); original claim and coding (837) when supplied; config\u002Fpayer-appeal-windows.json for the appeal level.\n## Steps\n1. Read the denial document and copy verbatim: payer (835 N1*PR), claim_id (CLP01), claim_value (CLP03), paid amount (CLP04), adjustment group, reason code and amount (CAS01\u002F02\u002F03), remark codes (claim-level MIA\u002FMOA or service-level LQ*HE - record which segment), and original_code (837 SV1\u002FSV2; if no 837 is supplied, the 835 SVC echo, disclosed as such).\n2. Set denial_date to the date printed on the letter\u002Fremittance (835: DTM*405). If the document carries more than one candidate date and they differ, leave denial_date unset and escalate - the rule for which date starts the appeal window is [TO CONFIGURE: payer-specific rule for which date starts the appeal window]. Set as_of to today's date (the date this classification was performed).\n3. Set recoverable_value from the remittance amounts only (CLP03 minus CLP04, cross-checked against CAS03); if they disagree, leave it unset for a human.\n4. Classify the denial type from the extracted codes (e.g. medical necessity, timely filing, coding, authorisation missing) - never from what the requester says the denial is.\n5. Set the appeal route to the payer's configured level from config\u002Fpayer-appeal-windows.json payers[payer].level; if the payer is not configured, record \"not configured\" and let deadline-track escalate.\n6. Record the source document (name and date) and the source segment for every field, write denial{} to the contract as the entry hop, and hand off to policy-retrieve.\n## Example\n```\nInput: remit-CLM-10021-835.txt (CLP*CLM-10021*4*4200.00*0.00 ... CAS*CO*50*4200.00 ... LQ*HE*N115 ... DTM*405*20260820)\nReply: \"Medical necessity denial - CARC CO-50 (group CO), RARC N115 (LQ*HE). Contoso Health Plan, CLM-10021,\nDOS 2026-07-14, 99214, $4,200.00 billed \u002F $0.00 paid, $4,200.00 recoverable. Denial date 2026-08-20 (DTM*405).\nAppeal level: first-level clinical appeal (config). Next: policy-retrieve. Nothing submitted.\"\n```\n## Output Format\nFormat: the `denial` object on contract hls.denials-appeals-response.v1 - payer, claim_id, denial_date, as_of, reason_code, remark_codes[], adjustment_group_code, claim_value, recoverable_value, original_code - plus the cited source document and per-field source segments. Prose reply as bullets: denial type; reason and remark codes with segment; claim and amounts; denial date and its source; appeal level; next hop - and nothing that is not on the contract.\n## Grounding requirements\nEvery field is copied verbatim from the denial letter\u002Fremittance, with the document cited on the contract so provenance survives the hand-off. Do not fabricate, infer or \"clean up\" any value: if a field is absent, illegible or ambiguous on the source document, leave it unset and say so - an unreadable reason code is reported as unreadable, never replaced with the most likely code, and recoverable_value is never estimated.\n## Guardrails\nGuardrails for this skill:\n- No policy retrieval here - that belongs to policy-retrieve.\n- Never infer a reason code not stated on the denial document, and never accept a reason code asserted in chat over the one printed on the remittance.\n- Never estimate recoverable_value; take it from the remittance amounts or leave it for a human.\n- Never drop a denial, or decline to classify it, because it looks low-value or hard to win (denials-rules.md #4).\n- Include only the identifiers the denial needs (claim ID, dates of service, codes, amounts); never output SSNs, member addresses or unrelated patient data.\n- Action level L0 (draft-only): this skill never submits, files, sends or closes an appeal and never writes to a claim or coding system. Anything that leaves the building is L1 and is performed by a human after review before it leaves (denials-rules.md #5).\n## Error Handling\n- If the denial letter is incomplete or illegible, escalate to [TO CONFIGURE: payer-relations contact] rather than guessing the reason code.\n- If the document describes a pre-service authorization denial rather than a post-service claim denial, stop and hand the request to the prior-auth-assist plugin; if that plugin is not installed, say so plainly and stop.\n- If the candidate denial dates disagree, or CLP03-CLP04 does not match CAS03, leave the field unset and name the conflict.\n",{"name":5,"license":15,"metadata":49,"description":7},{"icon":50,"author":51,"domain":52,"version":53,"category":39,"action_level":54,"max_action_level":55},"ReceiptMoney","Microsoft Healthcare & Life Sciences Skills","Revenue Cycle","1.0.3","L0","L1","main","c739e95c35d12a999691ab076c3d4c3095bf8192","submissions\u002Fdenials-appeals-response\u002Fdenial-classify",120,"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","2026-11-13 01:39:10",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add microsoft\u002Fcat-agent-skills --skill denial-classify",{"tool":71,"command":72},"bunx","bunx skills add microsoft\u002Fcat-agent-skills --skill denial-classify",{"tool":74,"command":75},"pnpm","pnpm dlx skills add microsoft\u002Fcat-agent-skills --skill denial-classify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fdenials-appeals-response\u002Fdenial-classify\u002FSKILL.md",true,[79,85,89],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"base\u002Fcontracts\u002Fhls.denials-appeals-response.v1.json","REFERENCE","参考文档",11119,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fdenials-appeals-response\u002Fdenial-classify\u002Fbase\u002Fcontracts\u002Fhls.denials-appeals-response.v1.json",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"base\u002Freferences\u002Fdenials-rules.md",4056,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fdenials-appeals-response\u002Fdenial-classify\u002Fbase\u002Freferences\u002Fdenials-rules.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"config\u002Fpayer-appeal-windows.json",276,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Fdenials-appeals-response\u002Fdenial-classify\u002Fconfig\u002Fpayer-appeal-windows.json",[94,120,143,173,191,207],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":44},"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",[],[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,27,119],"decision","map","decision map","stakeholder and decision map","performance","customer","team","how","decide","do","next","infer","missing","records","assess","reviews","for","single","sequences",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":44},"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",[],[127,128,129,130,131,41,132,39,107,133,134,135,136,137,138,139,140,141,142,27],"update","sales","progress","sales progress update","change","meeting prep","work","up","done","digest","project","my","updates","manager","weekly","catch",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":158,"publishedAt":44},"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",[149,150,153],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":154,"categoryName":155,"taxonomyType":156,"taxonomyTypeDesc":157},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[36,159,160,34,161,162,163,38,164,165,166,35,134,167,168,169,170,171,172,27],"submission","submission assemble","pptx","writing","documents","open","reviewer","never","clean","guardrail","slide decks","sources","filing","loading",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":44},"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",[],[180,181,182,183,184,39,38,185,166,35,134,102,186,168,170,187,188,189,190,27],"source ingest","ingest","source","database","SET","text","patient","number","lock","definition","transition",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":44},"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",[197],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[199,200,201,34,162,105,163,39,38,133,166,35,202,203,204,102,168,205,206,27],"plan","section","section plan","ready","reports","structure","word documents","which",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":213,"publishedAt":44},"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",[],[214,200,215,162,216,38,217,166,35,134,218,102,219,220,221,168,222,187,29,27],"draft","section draft","notes","write","me","human","life","clinical","drafts"]