[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DFTZSAMSP8RW65JGZ48A2":3,"skill-same:01M79DFTZSAMSP8RW65JGZ48A2":76},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M79DFTZSAMSP8RW65JGZ48A2","draft-long-form-memo",null,"Writes a formal objective legal research memo (Questions Presented, Brief Answers, Facts, IRAC Discussion, Conclusion) as a .docx. Use to \"draft a research memo on whether…\" Predicts, never advocates.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: draft-long-form-memo\ndescription: \"Writes a formal objective legal research memo (Questions Presented, Brief Answers, Facts, IRAC Discussion, Conclusion) as a .docx. Use to \\\"draft a research memo on whether…\\\" Predicts, never advocates.\"\nmetadata:\n  version: 0.2.0\n  author: midpage\n---\n\n# Draft Long-Form Memo\n\nProduce the thorough, objective memorandum a litigator hands a partner: it **predicts, it does\nnot advocate**. The test for every sentence: would you write it the same way no matter which\nside retained you? Read the shared guides first — `references\u002Flitigation-writing.md` (the\ncraft; same point-first discipline, neutral verbs), `references\u002Fcitations.md` (how every cite\nlinks), and `references\u002Flegal-docx.md`. The research method is below — the memo is only as\ngood as the research under it.\n\n## Research with Midpage (the method)\n\nAll law comes from the Midpage tools this session. `search` finds candidates; `findInOpinion`\npreviews; **`analyzeOpinion` is what permits a citation** — no case is cited without it.\n\n- **Frame each Question Presented as the operative element actually in dispute**, pinned to\n  the forum (it controls what binds and how to filter). Split multi-part questions; each issue\n  gets its own searches, its own Brief Answer, its own Discussion section.\n- **Search semantic, parallel, filtered.** Concept- and proposition-style queries, never\n  boolean; one issue per query, up to four in parallel; filtered to the forum\n  (`jurisdictionType`, `circuits`\u002F`courts`\u002F`states`, dates). Binding authority first,\n  persuasive labeled as such. If you filter `publishStatus`, run a parallel `unknown` query\n  too (California: default `published` plus `unknown`).\n- **Triage** on `highlights` (previews only — never quote them) and `treatment`; use\n  `findInOpinion` as the free double-click before spending an `analyzeOpinion` call.\n- **Branch from the best case**: pull the authorities a strong opinion itself leans on, then\n  search its key holding language to find later cases applying it. Iterate per issue until new\n  queries keep returning the same leading cases — saturation means the field is mapped.\n- **Research both sides with equal force — the memo's defining duty.** For every issue, run\n  searches framed from each party's position and `analyzeOpinion` the strongest case on each\n  side. The prediction is only honest if the contrary line got the same effort.\n- **The `analyzeOpinion` gate, on every case cited.** Pass a `question` naming the exact\n  element. Check `doesNotAddress` first — if your point is listed, the case doesn't stand for\n  it. Build sentences from `supportedPropositions` (verified quote + `deeplinkURL`); rank by\n  `centrality` (lead with holdings, never sell background as one); carry `scope` qualifiers;\n  never present a concurrence\u002Fdissent (`opinionSection`) as the court's holding; surface\n  negative `treatment` honestly.\n- **Silence and splits are answers.** \"No controlling authority on X in this circuit\" is a\n  finding worth reporting plainly; a genuine split is reported as one, with the best authority\n  each way — never resolved by wishful citation.\n\n## Structure\n\n- **Caption block** — `MEMORANDUM`, then To \u002F From \u002F Date \u002F Re: lines. **From is always\n  \"Midpage Legal Research\"** — never an AI assistant's name. Front matter is single-spaced, no\n  first-line indent (the body is double-spaced).\n- **Question(s) Presented** — one neutral, answerable question per distinct issue, naming the\n  forum and the operative element. Framed so the answer is genuinely in doubt, not loaded.\n- **Brief Answer(s)** — one-to-one with the questions: lead with the prediction (\"Probably\n  yes,\" \"Likely not,\" \"Unsettled, but the better view is…\") plus the one-line reason. Readable\n  on their own.\n- **Statement of Facts** — only if the user supplied facts; even-handed; record facts cited.\n  Omit the section entirely otherwise.\n- **Discussion** — the heart, IRAC per issue under `h1` headings: state the rule with linked\n  controlling authority, apply it to the facts, then give the contrary or competing authority\n  its fair statement — distinguish it, weigh it, note negative treatment honestly — and\n  resolve with a predictive conclusion. Use predictive verbs (\"a court would likely hold\"),\n  never advocacy verbs (\"plaintiff plainly fails\").\n- **Conclusion** — pull the Brief Answers into a candid forecast across all issues, flagging\n  open questions and the principal risk on each. No new authority; synthesize.\n\n## Rendering\n\nPer `references\u002Flegal-docx.md`, memo profile, double-spaced:\n\n```js\nconst B = D.builders(\"memo\", { lineSpacing: 480 });\n\u002F\u002F front matter lines: B.p([...], { lineSpacing: 240, firstLineIndent: 0 })\n\u002F\u002F Questions Presented: B.numbered(q, { instance: 1 })\n\u002F\u002F Brief Answers:       B.numbered(a, { instance: 2 })   \u002F\u002F distinct instance → restarts at 1\n```\n\nQuestions and Brief Answers are real numbered lists (hanging indents, wrapped lines aligned\nunder the text) — never a literal \"1.\" plus a tab.\n\n## Hard rules\n\n- **Objective, not persuasive.** Present both sides fairly; predict. Advocacy is\n  `draft-brief`'s job.\n- **Tool-grounded only.** Never cite a case, quote, or pin cite not run through\n  `analyzeOpinion` this session; `search`\u002F`findInOpinion` alone are not enough. No invented\n  authority, ever. Respect `doesNotAddress`, `scope`, `centrality`, and `opinionSection`;\n  surface negative treatment.\n- **Unsettled is an answer.** A genuine split or open question is reported as one, with the\n  best authority each way — never resolved by wishful citation.\n- Every proposition carries the exact linked citation per `references\u002Fcitations.md`; short\n  verbatim quotes woven into prose, no block quotes, no short cites.\n","# Draft Long-Form Memo\n\nProduce the thorough, objective memorandum a litigator hands a partner: it **predicts, it does\nnot advocate**. The test for every sentence: would you write it the same way no matter which\nside retained you? Read the shared guides first — `references\u002Flitigation-writing.md` (the\ncraft; same point-first discipline, neutral verbs), `references\u002Fcitations.md` (how every cite\nlinks), and `references\u002Flegal-docx.md`. The research method is below — the memo is only as\ngood as the research under it.\n\n## Research with Midpage (the method)\n\nAll law comes from the Midpage tools this session. `search` finds candidates; `findInOpinion`\npreviews; **`analyzeOpinion` is what permits a citation** — no case is cited without it.\n\n- **Frame each Question Presented as the operative element actually in dispute**, pinned to\n  the forum (it controls what binds and how to filter). Split multi-part questions; each issue\n  gets its own searches, its own Brief Answer, its own Discussion section.\n- **Search semantic, parallel, filtered.** Concept- and proposition-style queries, never\n  boolean; one issue per query, up to four in parallel; filtered to the forum\n  (`jurisdictionType`, `circuits`\u002F`courts`\u002F`states`, dates). Binding authority first,\n  persuasive labeled as such. If you filter `publishStatus`, run a parallel `unknown` query\n  too (California: default `published` plus `unknown`).\n- **Triage** on `highlights` (previews only — never quote them) and `treatment`; use\n  `findInOpinion` as the free double-click before spending an `analyzeOpinion` call.\n- **Branch from the best case**: pull the authorities a strong opinion itself leans on, then\n  search its key holding language to find later cases applying it. Iterate per issue until new\n  queries keep returning the same leading cases — saturation means the field is mapped.\n- **Research both sides with equal force — the memo's defining duty.** For every issue, run\n  searches framed from each party's position and `analyzeOpinion` the strongest case on each\n  side. The prediction is only honest if the contrary line got the same effort.\n- **The `analyzeOpinion` gate, on every case cited.** Pass a `question` naming the exact\n  element. Check `doesNotAddress` first — if your point is listed, the case doesn't stand for\n  it. Build sentences from `supportedPropositions` (verified quote + `deeplinkURL`); rank by\n  `centrality` (lead with holdings, never sell background as one); carry `scope` qualifiers;\n  never present a concurrence\u002Fdissent (`opinionSection`) as the court's holding; surface\n  negative `treatment` honestly.\n- **Silence and splits are answers.** \"No controlling authority on X in this circuit\" is a\n  finding worth reporting plainly; a genuine split is reported as one, with the best authority\n  each way — never resolved by wishful citation.\n\n## Structure\n\n- **Caption block** — `MEMORANDUM`, then To \u002F From \u002F Date \u002F Re: lines. **From is always\n  \"Midpage Legal Research\"** — never an AI assistant's name. Front matter is single-spaced, no\n  first-line indent (the body is double-spaced).\n- **Question(s) Presented** — one neutral, answerable question per distinct issue, naming the\n  forum and the operative element. Framed so the answer is genuinely in doubt, not loaded.\n- **Brief Answer(s)** — one-to-one with the questions: lead with the prediction (\"Probably\n  yes,\" \"Likely not,\" \"Unsettled, but the better view is…\") plus the one-line reason. Readable\n  on their own.\n- **Statement of Facts** — only if the user supplied facts; even-handed; record facts cited.\n  Omit the section entirely otherwise.\n- **Discussion** — the heart, IRAC per issue under `h1` headings: state the rule with linked\n  controlling authority, apply it to the facts, then give the contrary or competing authority\n  its fair statement — distinguish it, weigh it, note negative treatment honestly — and\n  resolve with a predictive conclusion. Use predictive verbs (\"a court would likely hold\"),\n  never advocacy verbs (\"plaintiff plainly fails\").\n- **Conclusion** — pull the Brief Answers into a candid forecast across all issues, flagging\n  open questions and the principal risk on each. No new authority; synthesize.\n\n## Rendering\n\nPer `references\u002Flegal-docx.md`, memo profile, double-spaced:\n\n```js\nconst B = D.builders(\"memo\", { lineSpacing: 480 });\n\u002F\u002F front matter lines: B.p([...], { lineSpacing: 240, firstLineIndent: 0 })\n\u002F\u002F Questions Presented: B.numbered(q, { instance: 1 })\n\u002F\u002F Brief Answers:       B.numbered(a, { instance: 2 })   \u002F\u002F distinct instance → restarts at 1\n```\n\nQuestions and Brief Answers are real numbered lists (hanging indents, wrapped lines aligned\nunder the text) — never a literal \"1.\" plus a tab.\n\n## Hard rules\n\n- **Objective, not persuasive.** Present both sides fairly; predict. Advocacy is\n  `draft-brief`'s job.\n- **Tool-grounded only.** Never cite a case, quote, or pin cite not run through\n  `analyzeOpinion` this session; `search`\u002F`findInOpinion` alone are not enough. No invented\n  authority, ever. Respect `doesNotAddress`, `scope`, `centrality`, and `opinionSection`;\n  surface negative treatment.\n- **Unsettled is an answer.** A genuine split or open question is reported as one, with the\n  best authority each way — never resolved by wishful citation.\n- Every proposition carries the exact linked citation per `references\u002Fcitations.md`; short\n  verbatim quotes woven into prose, no block quotes, no short cites.\n",{"name":5,"metadata":24,"description":7},{"author":25,"version":26},"midpage","0.2.0","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fdraft-long-form-memo","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog","https:\u002F\u002Fgithub.com\u002Fzfifteen","I like to measure things.","2026-07-19 23:41:54",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add zfifteen\u002Fskills-catalog --skill draft-long-form-memo",{"tool":40,"command":41},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill draft-long-form-memo",{"tool":43,"command":44},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill draft-long-form-memo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002FSKILL.md",true,[48,54,58,62,66,70],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",224,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fcitations.md",2461,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002Freferences\u002Fcitations.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fcourt-rules.md",5306,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002Freferences\u002Fcourt-rules.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Flegal-docx.md",6652,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002Freferences\u002Flegal-docx.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Flitigation-writing.md",9870,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002Freferences\u002Flitigation-writing.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002Flegal_docx.js","SCRIPT","脚本",29188,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-long-form-memo\u002Fscripts\u002Flegal_docx.js",[77,84,91,98,107,114],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79GXQ2PWPT2E4CJYHXVJ0YE","Zotero","Use Zotero Desktop from Codex to enable\u002Fprobe the local API, search a local Zotero library, list items\u002Fcollections\u002Ftags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX\u002FRIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzotero\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79GXN85NETKBE06865CWK6Z","zoom-apps-sdk","Use when using Apps SDK.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M79GXCYD7FGYS932J9N9RFFY","youtube","Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript.  Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or \"what does this video actually say\".  The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content.  Triggers: \"youtube transcript\", \"get the transcript of this video\", \"summarize this youtube video\", \"what did they say in https:\u002F\u002Fyoutube.com\u002F...\", \"key claims from this talk\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M79GX8EXHHYM566BKR7MS778","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"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":19},"01M79GX2HFJPX84NMRE5VBTYX9","x-post-creator","Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, \u002Fx-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs\u002Fx-posts\u002F[story-name]\u002F.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-post-creator\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M79GWXQT4HBT6QME6QSBZJFA","x-api","Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X\u002Fx.com, reading threads and replies, creating lists, staging\u002Fpublishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions \u002Fx-api or \"search X\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]