[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X3DJV4YHTMRAAF8MDRHKP0":3,"skill-same:01M6X3DJV4YHTMRAAF8MDRHKP0":81},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6X3DJV4YHTMRAAF8MDRHKP0","improve-legal-prompt",null,"Turns a rough request or an existing draft into one ready-to-use Cowork prompt, preserving the user's original legal objective while making document scope, party perspective, constraints, missing information handling and expected output explicit. Returns the prompt plus two or three improvement notes, and never runs it. Use when the user asks to \"optimize my prompt\", \"rewrite my prompt for reviewing this agreement\", \"improve this prompt\", \"how should I ask Cowork to revise the termination clause\", \"clarify this instruction before I run it\", or \"why isn't my prompt working\". Do NOT use for the legal work itself — \"rewrite this clause\" or \"make this paragraph clearer\" is edit-contract, a reasoned answer on a legal question is legal-reasoning, and reviewing an agreement is review-contract.","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\u002Flegal-for-cowork\u002Fskills\u002Fimprove-legal-prompt\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"improve legal prompt","improve","prompt","legal","question","when","request","information","scope","optimize","ready","never","review","ask","clarify","work","why","how","run","notes","2026-11-10 10:12:30",false,"---\nname: improve-legal-prompt\ndescription: >-\n  Turns a rough request or an existing draft into one ready-to-use Cowork\n  prompt, preserving the user's original legal objective while making document\n  scope, party perspective, constraints, missing information handling and\n  expected output explicit. Returns the prompt plus two or three improvement\n  notes, and never runs it. Use when the user asks to \"optimize my prompt\",\n  \"rewrite my prompt for reviewing this agreement\", \"improve this prompt\", \"how\n  should I ask Cowork to revise the termination clause\", \"clarify this\n  instruction before I run it\", or \"why isn't my prompt working\". Do NOT use for\n  the legal work itself — \"rewrite this clause\" or \"make this paragraph clearer\"\n  is edit-contract, a reasoned answer on a legal question is legal-reasoning,\n  and reviewing an agreement is review-contract.\nmetadata:\n  displayName: Improve legal prompt\n  category: productivity\n  icon: Scales\n---\n\n# Improve legal prompt\n\nConvert the user's rough request or existing prompt into one ready-to-use prompt for\nCowork. Preserve the original objective while clarifying the intended legal outcome,\ndocument scope, constraints, required inputs, handling of missing information, and\nexpected response format.\n\nThis skill optimizes the prompt. It does not perform the legal analysis, review,\ndrafting or editing the prompt describes, and it never guarantees a legal outcome.\n\n## When NOT to Use\n\nUse this skill **only** when the user explicitly asks to create, improve, clarify,\ndiagnose or rewrite a prompt, instruction or request for Cowork.\n\n- `Rewrite my prompt for reviewing this agreement` — prompt optimization. In scope.\n- `How should I ask Cowork to revise the termination clause?` — prompt optimization.\n  In scope.\n- `Rewrite this clause`, `make this paragraph clearer`, `improve the termination\n  provision` — document editing. Use `edit-contract`.\n- `Is this clause enforceable?`, `what does this mean for us?` — use\n  `legal-reasoning`, or `explain-legal-concepts` for a plain language explanation.\n- `Review this agreement` — use `review-contract`.\n- A vague legal request does not become a prompt-optimization request merely because\n  a better prompt might improve the result.\n\n**Hand-off rule.** If a request, or part of one, matches an item above that names\nanother skill, do not do that part here — even when the documents are already open\nand the work looks quick. Name the skill that handles it (for example, \"That part\nis a job for `edit-contract`\") and stop that part; finish only what belongs to\nthis skill. If the named skill is not installed, say so plainly and do not attempt\nit here.\n\n## Step 1: Identify the source request\n\n- Treat text the user pastes, quotes, labels as a prompt, or describes as their\n  instruction as the source.\n- Where the turn refers to a prompt from the recent conversation, use the most recent\n  unambiguous prompt under discussion.\n- If the user gives a target task but no draft prompt, write the prompt from scratch.\n- If neither a source prompt nor a target task is identifiable, ask exactly:\n  `What prompt would you like me to optimize?`\n- Preserve exact values, defined labels, clause numbers, field names, schemas,\n  allowed values, word limits, exceptions and formatting requirements unless the user\n  asks to change them. Never carry a personal identifier through into the optimized\n  prompt: an optimized prompt is re-run downstream, so a national insurance or social\n  security number, bank or payment card detail, home address, date of birth, salary or\n  health datum copied out of the source request or a supplied document propagates into\n  every later run. Replace it with a role or a neutral placeholder, keep the\n  instruction intact, and say what you replaced and why; where the source prompt asks\n  for such a field as an output, drop that field from the optimized prompt and say so.\n  See **Personal data minimisation** in Guardrails.\n\n## Step 2: Use the supplied documents only to resolve context\n\nRead only what is needed to make the prompt accurate. Use `Glob` over `input\u002F**\u002F*`\nand `grounding\u002F**\u002F*`, check for an attached OneDrive folder, and\nread it in full. When opening a document, use a method that shows tracked changes and comments, and check whether any are present before relying on the text. Refer to\neach file by its exact filename.\n\n- Use available context directly when it clearly resolves document type, party names,\n  clause names, defined terms, or the location the user means.\n- Read the specific file the user points at; read further files, or more of a long\n  one, only to resolve an otherwise ambiguous reference or verify exact terminology.\n- Include specific document terms in the optimized prompt where they materially\n  improve precision.\n- Do not broaden the optimization into a document review, and never infer which party\n  the user represents or invent a legal or commercial position from the document.\n\n## Step 3: Decide whether clarification is essential\n\nPause before optimizing when an ambiguity could materially change the legal outcome\nor cause Cowork to act on the wrong text. Ask only for the material gaps that apply,\nusing a question card:\n\n- which party the user represents, or whose position the prompt should advance;\n- which clause, section, document, attachment or passage is in scope;\n- what outcome words such as `better`, `stronger`, `fairer` or `market standard` are\n  intended to achieve;\n- which jurisdiction applies, where the task depends on jurisdiction-specific law or\n  execution requirements;\n- which required commercial value, drafting position, remedy, fallback or source\n  precedent should be used.\n\nDo not ask about preferences a sensible default covers, such as minor formatting or\nwhether the explanation runs to two or three bullets. Ask the smallest set of\nquestions needed, group related ones, and never repeat what the user already supplied\nor the document already establishes. When clarification is essential, ask and **stop**\n— do not also supply a knowingly unreliable prompt in the same answer.\n\n## Step 4: Build the Cowork prompt\n\n- Lead with the outcome the user wants Cowork to achieve.\n- State the document scope precisely: a complete supplied document named by filename,\n  a named provision, a quoted passage, specified attachments or precedents, or a\n  general legal question.\n- Include party perspective, legal or commercial objective, jurisdiction, audience,\n  constraints and source material, where supplied or clarified.\n- Separate hard requirements from preferences, so Cowork does not treat a stylistic\n  preference as an inviolable legal constraint.\n- State what Cowork must do when information is missing, inconsistent, ambiguous or\n  requires judgement: identify the gap or ask, never guess.\n- Make the expected response explicit — analysis, cited answer, issue table, proposed\n  edits, questions for the user, draft language, or another named deliverable.\n- For analysis or review, require conclusions grounded in the document text, with\n  findings distinguished from assumptions and matters requiring judgement.\n- For editing, state the intended legal effect and require the smallest necessary\n  change, preserving unaffected wording, defined terms, numbering, formatting and\n  substantive meaning.\n- For drafting, identify what to create, the source material to follow, the intended\n  position, and the facts Cowork must obtain rather than invent.\n\n## Step 5: Preserve the objective, then audit\n\nKeep every meaningful requirement from the source unless it conflicts with the user's\nclarified goal. Remove repetition, vague filler and contradictions without changing\nthe legal position, ambition or scope. Do not add role-play, unnecessary disclaimers,\nelaborate process, or deliverables the user did not request. If the user asked only\nfor clarity, improve clarity without turning the request into a different legal task.\n\nBefore answering, check that: Cowork can tell what to do, what material to use, what\nnot to assume or change, and what to return; the prompt cannot reasonably be misread\nas edit-when-analysis-was-wanted, analyse-when-edits-were-wanted, whole-document-when\none provision is in scope, or ask-the-user when an internal assessment was intended;\nand no meaningful requirement, exact value, exception or output constraint was lost\nagainst the source.\n\n## Step 6: Output format\n\nWhen essential information is missing, reply with exactly:\n\n```text\n### Clarification needed\n\n[one to three concise, targeted questions]\n```\n\nand include no optimized prompt until the user answers. Otherwise reply with exactly\nthese two sections:\n\n```text\n### Optimized prompt\n\n[complete ready-to-copy prompt for Cowork]\n\n### Improvements made\n\n- [specific improvement]\n- [specific improvement]\n- [optional third specific improvement]\n```\n\nKeep the explanation to two or three bullets explaining how the optimization\nclarified behavior, scope, required inputs, missing information handling or output\nshape — not generic prompt writing advice. Do not answer or execute the optimized\nprompt, do not offer multiple variants unless asked, and stop after the improvement\nbullets rather than offering to run it.\n\n## Guardrails\n\n- **Read-only, context only.** Inspect documents solely to resolve prompt context,\n  reading only supplied files and only when necessary.\n- **Never write to a document.** Do not edit, comment on or otherwise modify any\n  document; optimizing a prompt must not change the document.\n- **Not a legal answer.** Do not produce citations, answer metadata or a\n  document-grounded legal conclusion — the output is a prompt.\n- **No downstream execution.** Do not hand off to a review, relevance-generation or\n  playbook-extraction workflow, and do not open progress tasks to run the downstream work.\n- **Personal data minimisation.** Report what the documents say, not who people are.\n  Never carry national insurance or social security numbers, bank or payment card\n  details, home addresses, dates of birth, salary or health data into an answer, a\n  table, a cell, a quotation, a summary, a draft or a suggested wording — including\n  the optimized prompt itself and any example it embeds — even where they sit inside\n  a matter document and even when the user names the field or asks for the column.\n  Refer to individuals by name and role only. If such a detail is material to a\n  finding, say that the source contains it and cite the provision rather than\n  reproducing it; leave the requested field out and deliver the rest.\n- **No assumed perspective.** Never infer the represented party merely because the\n  document names the parties.\n- **No guarantees.** Never claim the optimized prompt assures a correct legal\n  outcome.\n\n## Worked examples\n\n**Essential party perspective is missing.** Source:\n`Rewrite my prompt: review this agreement and tell me which clauses I should push\nback on.` The agreement identifies a Customer and a Supplier, which does not\nestablish whom the user represents. Reply with `### Clarification needed` and the\nsingle question \"Which party do you represent in this agreement: the Customer or the\nSupplier?\", and do not optimize until answered.\n\n**Clear, document-aware editing prompt.** Source: `Improve my prompt: revise clause\n12 so the Customer gets 30 days to cure a payment breach. Keep everything else the\nsame.` The optimized prompt reads: \"Revise clause 12 of the supplied agreement so\nthat the Customer has 30 days to cure a payment breach before the Supplier may\nexercise the termination right addressed in that clause. Make only the minimum\nchanges needed to implement that cure period. Preserve all unaffected wording,\ndefined terms, numbering, formatting, and the clause's other legal effects. If clause\n12 does not contain the relevant payment breach termination right, or the requested\nchange conflicts with another provision, identify the issue rather than guessing or\nediting unrelated text. Return the proposed change as a reviewable edit.\" The\nimprovement bullets then note that the optimization fixed the target provision, the\nexact legal outcome, the preservation requirements, conflict handling and the\nexpected edit output.\n","# Improve legal prompt\n\nConvert the user's rough request or existing prompt into one ready-to-use prompt for\nCowork. Preserve the original objective while clarifying the intended legal outcome,\ndocument scope, constraints, required inputs, handling of missing information, and\nexpected response format.\n\nThis skill optimizes the prompt. It does not perform the legal analysis, review,\ndrafting or editing the prompt describes, and it never guarantees a legal outcome.\n\n## When NOT to Use\n\nUse this skill **only** when the user explicitly asks to create, improve, clarify,\ndiagnose or rewrite a prompt, instruction or request for Cowork.\n\n- `Rewrite my prompt for reviewing this agreement` — prompt optimization. In scope.\n- `How should I ask Cowork to revise the termination clause?` — prompt optimization.\n  In scope.\n- `Rewrite this clause`, `make this paragraph clearer`, `improve the termination\n  provision` — document editing. Use `edit-contract`.\n- `Is this clause enforceable?`, `what does this mean for us?` — use\n  `legal-reasoning`, or `explain-legal-concepts` for a plain language explanation.\n- `Review this agreement` — use `review-contract`.\n- A vague legal request does not become a prompt-optimization request merely because\n  a better prompt might improve the result.\n\n**Hand-off rule.** If a request, or part of one, matches an item above that names\nanother skill, do not do that part here — even when the documents are already open\nand the work looks quick. Name the skill that handles it (for example, \"That part\nis a job for `edit-contract`\") and stop that part; finish only what belongs to\nthis skill. If the named skill is not installed, say so plainly and do not attempt\nit here.\n\n## Step 1: Identify the source request\n\n- Treat text the user pastes, quotes, labels as a prompt, or describes as their\n  instruction as the source.\n- Where the turn refers to a prompt from the recent conversation, use the most recent\n  unambiguous prompt under discussion.\n- If the user gives a target task but no draft prompt, write the prompt from scratch.\n- If neither a source prompt nor a target task is identifiable, ask exactly:\n  `What prompt would you like me to optimize?`\n- Preserve exact values, defined labels, clause numbers, field names, schemas,\n  allowed values, word limits, exceptions and formatting requirements unless the user\n  asks to change them. Never carry a personal identifier through into the optimized\n  prompt: an optimized prompt is re-run downstream, so a national insurance or social\n  security number, bank or payment card detail, home address, date of birth, salary or\n  health datum copied out of the source request or a supplied document propagates into\n  every later run. Replace it with a role or a neutral placeholder, keep the\n  instruction intact, and say what you replaced and why; where the source prompt asks\n  for such a field as an output, drop that field from the optimized prompt and say so.\n  See **Personal data minimisation** in Guardrails.\n\n## Step 2: Use the supplied documents only to resolve context\n\nRead only what is needed to make the prompt accurate. Use `Glob` over `input\u002F**\u002F*`\nand `grounding\u002F**\u002F*`, check for an attached OneDrive folder, and\nread it in full. When opening a document, use a method that shows tracked changes and comments, and check whether any are present before relying on the text. Refer to\neach file by its exact filename.\n\n- Use available context directly when it clearly resolves document type, party names,\n  clause names, defined terms, or the location the user means.\n- Read the specific file the user points at; read further files, or more of a long\n  one, only to resolve an otherwise ambiguous reference or verify exact terminology.\n- Include specific document terms in the optimized prompt where they materially\n  improve precision.\n- Do not broaden the optimization into a document review, and never infer which party\n  the user represents or invent a legal or commercial position from the document.\n\n## Step 3: Decide whether clarification is essential\n\nPause before optimizing when an ambiguity could materially change the legal outcome\nor cause Cowork to act on the wrong text. Ask only for the material gaps that apply,\nusing a question card:\n\n- which party the user represents, or whose position the prompt should advance;\n- which clause, section, document, attachment or passage is in scope;\n- what outcome words such as `better`, `stronger`, `fairer` or `market standard` are\n  intended to achieve;\n- which jurisdiction applies, where the task depends on jurisdiction-specific law or\n  execution requirements;\n- which required commercial value, drafting position, remedy, fallback or source\n  precedent should be used.\n\nDo not ask about preferences a sensible default covers, such as minor formatting or\nwhether the explanation runs to two or three bullets. Ask the smallest set of\nquestions needed, group related ones, and never repeat what the user already supplied\nor the document already establishes. When clarification is essential, ask and **stop**\n— do not also supply a knowingly unreliable prompt in the same answer.\n\n## Step 4: Build the Cowork prompt\n\n- Lead with the outcome the user wants Cowork to achieve.\n- State the document scope precisely: a complete supplied document named by filename,\n  a named provision, a quoted passage, specified attachments or precedents, or a\n  general legal question.\n- Include party perspective, legal or commercial objective, jurisdiction, audience,\n  constraints and source material, where supplied or clarified.\n- Separate hard requirements from preferences, so Cowork does not treat a stylistic\n  preference as an inviolable legal constraint.\n- State what Cowork must do when information is missing, inconsistent, ambiguous or\n  requires judgement: identify the gap or ask, never guess.\n- Make the expected response explicit — analysis, cited answer, issue table, proposed\n  edits, questions for the user, draft language, or another named deliverable.\n- For analysis or review, require conclusions grounded in the document text, with\n  findings distinguished from assumptions and matters requiring judgement.\n- For editing, state the intended legal effect and require the smallest necessary\n  change, preserving unaffected wording, defined terms, numbering, formatting and\n  substantive meaning.\n- For drafting, identify what to create, the source material to follow, the intended\n  position, and the facts Cowork must obtain rather than invent.\n\n## Step 5: Preserve the objective, then audit\n\nKeep every meaningful requirement from the source unless it conflicts with the user's\nclarified goal. Remove repetition, vague filler and contradictions without changing\nthe legal position, ambition or scope. Do not add role-play, unnecessary disclaimers,\nelaborate process, or deliverables the user did not request. If the user asked only\nfor clarity, improve clarity without turning the request into a different legal task.\n\nBefore answering, check that: Cowork can tell what to do, what material to use, what\nnot to assume or change, and what to return; the prompt cannot reasonably be misread\nas edit-when-analysis-was-wanted, analyse-when-edits-were-wanted, whole-document-when\none provision is in scope, or ask-the-user when an internal assessment was intended;\nand no meaningful requirement, exact value, exception or output constraint was lost\nagainst the source.\n\n## Step 6: Output format\n\nWhen essential information is missing, reply with exactly:\n\n```text\n### Clarification needed\n\n[one to three concise, targeted questions]\n```\n\nand include no optimized prompt until the user answers. Otherwise reply with exactly\nthese two sections:\n\n```text\n### Optimized prompt\n\n[complete ready-to-copy prompt for Cowork]\n\n### Improvements made\n\n- [specific improvement]\n- [specific improvement]\n- [optional third specific improvement]\n```\n\nKeep the explanation to two or three bullets explaining how the optimization\nclarified behavior, scope, required inputs, missing information handling or output\nshape — not generic prompt writing advice. Do not answer or execute the optimized\nprompt, do not offer multiple variants unless asked, and stop after the improvement\nbullets rather than offering to run it.\n\n## Guardrails\n\n- **Read-only, context only.** Inspect documents solely to resolve prompt context,\n  reading only supplied files and only when necessary.\n- **Never write to a document.** Do not edit, comment on or otherwise modify any\n  document; optimizing a prompt must not change the document.\n- **Not a legal answer.** Do not produce citations, answer metadata or a\n  document-grounded legal conclusion — the output is a prompt.\n- **No downstream execution.** Do not hand off to a review, relevance-generation or\n  playbook-extraction workflow, and do not open progress tasks to run the downstream work.\n- **Personal data minimisation.** Report what the documents say, not who people are.\n  Never carry national insurance or social security numbers, bank or payment card\n  details, home addresses, dates of birth, salary or health data into an answer, a\n  table, a cell, a quotation, a summary, a draft or a suggested wording — including\n  the optimized prompt itself and any example it embeds — even where they sit inside\n  a matter document and even when the user names the field or asks for the column.\n  Refer to individuals by name and role only. If such a detail is material to a\n  finding, say that the source contains it and cite the provision rather than\n  reproducing it; leave the requested field out and deliver the rest.\n- **No assumed perspective.** Never infer the represented party merely because the\n  document names the parties.\n- **No guarantees.** Never claim the optimized prompt assures a correct legal\n  outcome.\n\n## Worked examples\n\n**Essential party perspective is missing.** Source:\n`Rewrite my prompt: review this agreement and tell me which clauses I should push\nback on.` The agreement identifies a Customer and a Supplier, which does not\nestablish whom the user represents. Reply with `### Clarification needed` and the\nsingle question \"Which party do you represent in this agreement: the Customer or the\nSupplier?\", and do not optimize until answered.\n\n**Clear, document-aware editing prompt.** Source: `Improve my prompt: revise clause\n12 so the Customer gets 30 days to cure a payment breach. Keep everything else the\nsame.` The optimized prompt reads: \"Revise clause 12 of the supplied agreement so\nthat the Customer has 30 days to cure a payment breach before the Supplier may\nexercise the termination right addressed in that clause. Make only the minimum\nchanges needed to implement that cure period. Preserve all unaffected wording,\ndefined terms, numbering, formatting, and the clause's other legal effects. If clause\n12 does not contain the relevant payment breach termination right, or the requested\nchange conflicts with another provision, identify the issue rather than guessing or\nediting unrelated text. Return the proposed change as a reviewable edit.\" The\nimprovement bullets then note that the optimization fixed the target provision, the\nexact legal outcome, the preservation requirements, conflict handling and the\nexpected edit output.\n",{"name":5,"metadata":54,"description":7},{"icon":55,"category":56,"displayName":57},"Scales","productivity","Improve legal prompt","main","c739e95c35d12a999691ab076c3d4c3095bf8192","submissions\u002Flegal-for-cowork\u002Fskills\u002Fimprove-legal-prompt",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":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add microsoft\u002Fcat-agent-skills --skill improve-legal-prompt",{"tool":73,"command":74},"bunx","bunx skills add microsoft\u002Fcat-agent-skills --skill improve-legal-prompt",{"tool":76,"command":77},"pnpm","pnpm dlx skills add microsoft\u002Fcat-agent-skills --skill improve-legal-prompt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcat-agent-skills\u002Fblob\u002Fmain\u002Fsubmissions\u002Flegal-for-cowork\u002Fskills\u002Fimprove-legal-prompt\u002FSKILL.md",true,[],[82,107,131,164,182,197],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":49},"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",[],[89,90,91,92,93,94,95,46,96,97,98,99,100,101,102,103,104,105,34,106],"decision","map","decision map","stakeholder and decision map","performance","customer","team","decide","do","next","infer","missing","records","assess","reviews","for","single","sequences",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":49},"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",[],[114,115,116,117,118,119,120,121,95,44,122,123,124,125,126,127,128,129,130,34],"update","sales","progress","sales progress update","change","create","meeting prep","analysis","up","done","digest","project","my","updates","manager","weekly","catch",{"skillNo":132,"name":133,"nameZh":6,"description":134,"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":146,"publishedAt":49},"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",[137,140,143],{"categoryNo":138,"categoryName":139,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":141,"categoryName":142,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":144,"categoryName":145,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000034","行政与办公人员",[147,148,149,150,151,152,153,154,155,156,40,157,122,158,159,160,161,162,163,34],"assemble","submission","submission assemble","docx","pptx","writing","documents","healthcare","open","reviewer","only","clean","guardrail","slide decks","sources","filing","loading",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":49},"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",[],[171,172,173,174,175,121,154,176,40,157,122,90,177,159,161,178,179,180,181,34],"source ingest","ingest","source","database","SET","text","patient","number","lock","definition","transition",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":189,"publishedAt":49},"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",[188],{"categoryNo":138,"categoryName":139,"taxonomyType":21,"taxonomyTypeDesc":22},[190,191,192,150,152,93,153,121,154,44,40,157,39,193,194,90,159,195,196,34],"plan","section","section plan","reports","structure","word documents","which",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":203,"publishedAt":49},"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",[],[204,191,205,152,48,154,206,40,157,122,207,90,208,209,210,159,211,178,212,34],"draft","section draft","write","me","human","life","clinical","drafts","at"]