[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AS43H1VV6ATF2CD3DGFKGE":3,"skill-same:01M7AS43H1VV6ATF2CD3DGFKGE":48},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7AS43H1VV6ATF2CD3DGFKGE","semi-integration-yield-metrology-test-and-packaging",null,"Use for making the process actually produce working parts: process integration and how hundreds of steps compose, yield and the models and defect mechanisms behind it, metrology and inspection, test including wafer sort, burn-in and the coverage question, and advanced packaging with 2.5D, 3D, chiplets and the interposer and bonding options.","the-vibey-project\u002Fvibey","the-vibey-project","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F329298758?v=4","01M7AJHGZ9722CTJ4JNQZVRH0Q","the vibey project","01M7AJHGZVMG2K7TGXQ6XFHVG3",5,"MIT","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fsemiconductors-and-chip-manufacturing\u002Fskills\u002Fsemi-integration-yield-metrology-test-and-packaging\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: semi-integration-yield-metrology-test-and-packaging\ndescription: \"Use for making the process actually produce working parts: process integration and how hundreds of steps compose, yield and the models and defect mechanisms behind it, metrology and inspection, test including wafer sort, burn-in and the coverage question, and advanced packaging with 2.5D, 3D, chiplets and the interposer and bonding options.\"\n---\n\n# Semiconductors and Chip Manufacturing: Process Integration, Yield, Metrology and Inspection, Test, and Advanced Packaging\n\n> **Part 4 of 6** of the *Semiconductors and Chip Manufacturing* reference (plugin `semiconductors-and-chip-manufacturing`), covering §16–§20. Sibling skills: `semi-carriers-doping-junctions-mosfet-and-scaling` (§0–§5), `semi-transistor-architectures-interconnect-memory-and-wafers` (§6–§9), `semi-cleanroom-lithography-deposition-etch-and-cmp` (§10–§15), `semi-pcb-assembly-reliability-design-flow-and-economics` (§21–§26), `semi-reference` (§27–§32). Section numbers are shared across the set; a reference written as §N → `skill` points into that sibling skill.\n>\n> **Currency:** The physics is settled. Two frontiers are moving. See §27 → `semi-reference` for High-NA lithography adoption, and advanced packaging as the binding constraint.\n\n> **⚠️ The most complex manufacturing humans do, by a wide margin.** ⚠️ **A leading-edge\n> chip involves on the order of a thousand process steps, features smaller than a virus,\n> tolerances measured in atoms, and a supply chain with genuine single points of failure.**\n>\n> **Builds directly on an electromagnetism reference (band theory, pn junctions, MOSFET\n> physics, wide-bandgap materials). Complements a manufacturing reference (tolerancing and\n> yield), an organic-chemistry reference (photoresists and packaging polymers), and a\n> resource-extraction reference (where the materials come from).**\n>\n> **⚠️ GOTCHA** boxes mark where marketing and physics diverge — and this industry has more\n> of that gap than most.\n>\n> **The three ideas that organize this document:**\n> 1. **⚠️ \"NODE NAMES ARE MARKETING\"** (§5 → `semi-carriers-doping-junctions-mosfet-and-scaling`). **\"3nm\" does not describe any physical\n>    dimension on the chip. It has been a marketing label for roughly a decade, and\n>    comparing nodes across foundries by name is meaningless.**\n> 2. **⚠️ YIELD IS THE WHOLE BUSINESS** (§17). **Everything — die size, chiplet\n>    architecture, defect control, cleanroom spend — is downstream of the fact that\n>    profitability is set by what fraction of die work.**\n> 3. **⚠️ THE BOTTLENECK MOVED TO THE BACK END** (§20, §27.2 → `semi-reference`). **For AI accelerators the\n>    binding constraint is no longer transistors — it is packaging and memory, which is a\n>    genuine reversal of thirty years of industry structure.**\n\n---\n\n## §16. Process Integration\n\n**⚠️ The discipline of making hundreds of individually-working steps work TOGETHER.**\n⚠️ **FEOL (front end of line — transistors) → MOL (contacts) → BEOL (interconnect).**\n**⚠️ A mask set for a leading node runs to dozens of layers and costs millions**, ⚠️ **which\nis a large part of why NRE at the leading edge is prohibitive for low-volume designs**\n(§25 → `semi-pcb-assembly-reliability-design-flow-and-economics`).\n**⚠️ The integration engineer's problem is that everything interacts**: ⚠️ **a change in\netch chemistry shifts a CMP rate, which changes overlay, which shifts device parameters.**\n**⚠️ Process control** uses SPC and increasingly run-to-run feedback (see a manufacturing\nreference on Cp\u002FCpk) — ⚠️ **and PROCESS VARIATION is now a first-order design concern:\nrandom dopant fluctuation, line edge roughness and metal grain variation make nominally\nidentical transistors measurably different.**\n\n---\n\n## §17. ⚠️ Yield\n\n> **⚠️ The number that decides whether a fab makes money.**\n```\n⚠️ THE MODELS  ⚠️ Poisson yield ≈ e^(−AD) where A is die area and\n   D is defect density. ⚠️ Murphy's and negative binomial models\n   are used in practice because defects CLUSTER\n⚠️ ⚠️ THE CENTRAL CONSEQUENCE: YIELD FALLS EXPONENTIALLY WITH DIE\n   AREA. ⚠️ Doubling die size does far more than double the loss\n⚠️ ⚠️ THIS IS THE ENTIRE ARGUMENT FOR CHIPLETS (§20) —\n   four small dies yield far better than one large die of the\n   same total area, and you can bin and mix them\n⚠️ THE RETICLE LIMIT  ⚠️ a hard maximum die size set by the\n   exposure field. ⚠️ Large AI accelerators are AT it, which is\n   another forcing function toward multi-die\n⚠️ YIELD TYPES  ⚠️ line yield (wafers surviving the flow) ·\n   ⚠️ DIE yield (good die per wafer) · parametric yield (die that\n   work but miss spec) · packaging and final test yield\n⚠️ DEFECT SOURCES  particles · pattern defects · ⚠️ systematic\n   layout-sensitive defects (⚠️ these are DESIGN issues, addressed\n   by DFM rules) · contamination · equipment excursions\n⚠️ LEARNING CURVE  ⚠️ yield ramps over months to years; ⚠️ early\n   production of a new node is often economically poor, which is\n   why node transitions are financially painful\n```\n**⚠️ Binning** monetizes partial failures — ⚠️ **a die with a defective core or cache block\nis sold as a lower-tier product rather than scrapped, which is why product stacks look the\nway they do.**\n\n---\n\n## §18. Metrology and Inspection\n\n**⚠️ You cannot control what you cannot measure, at nanometre scale, non-destructively, on\nproduction wafers.**\n**⚠️ Techniques**: ⚠️ **CD-SEM for critical dimensions, scatterometry\u002FOCD for profiles,\nellipsometry for film thickness, overlay metrology (⚠️ the tightest budget of all — sub-nm\nat the leading edge), and defect inspection by optical and e-beam.**\n**⚠️ The fundamental tension**: ⚠️ **optical inspection is fast and cannot resolve the\nsmallest defects; e-beam resolves them and is far too slow for full-wafer coverage.**\n**⚠️ Hence sampling, hot-spot inspection guided by design, and increasing use of machine\nlearning to classify defects.**\n**⚠️ Failure analysis** works backwards from a failing die: ⚠️ **fault isolation, then FIB\ncross-sectioning, then TEM — expensive, slow, and the only way to find root cause.**\n\n---\n\n## §19. Test\n\n**⚠️ Testing is a large fraction of total cost and is easy to underestimate.**\n⚠️ **WAFER SORT\u002Fprobe identifies good die before the expense of packaging; ⚠️ FINAL TEST\nafter packaging; ⚠️ BURN-IN stresses parts to precipitate infant mortality** (§23 → `semi-pcb-assembly-reliability-design-flow-and-economics`).\n**⚠️ DESIGN FOR TEST is mandatory**: ⚠️ **scan chains, BIST, and JTAG boundary scan exist\nbecause a billion-transistor chip has no other way to be observed.**\n**⚠️ Coverage versus time is the eternal trade** — ⚠️ **test time is money, and untested\nfaults escape to customers.**\n> **⚠️ GOTCHA — KNOWN GOOD DIE is the problem that makes chiplets hard** (§20).\n> ⚠️ **If you assemble ten dies into one package and any is bad, you scrap the whole\n> assembly including the good ones.** **⚠️ So multi-die packaging requires far higher\n> confidence in pre-assembly test than monolithic designs ever did, and reported estimates\n> put chiplet test cost at 15–30% above monolithic for this reason.**\n\n---\n\n# PART III — PACKAGING AND BOARDS\n\n## §20. ⚠️ Advanced Packaging\n\n> **⚠️ Historically an afterthought; now the most strategically important part of the\n> chain** (§27.2 → `semi-reference`).\n```\n⚠️ WHAT PACKAGING DOES  ⚠️ electrical connection · POWER delivery ·\n   ⚠️ HEAT removal · mechanical protection · and ⚠️ matching the\n   chip's micron-scale pitch to the board's millimetre scale\n⚠️ TRADITIONAL  wire bond · flip chip (⚠️ solder bumps, area array,\n   far better electrically) · BGA\n⚠️ 2.5D  ⚠️ multiple dies side by side on a SILICON INTERPOSER with\n   fine wiring. ⚠️ TSMC's CoWoS is the dominant example — this is\n   how a GPU sits next to HBM stacks\n   ⚠️ EMIB (Intel) embeds a small silicon bridge in the substrate\n   instead of a full interposer — cheaper, no through-silicon\n   interposer needed\n⚠️ 3D  ⚠️ dies stacked vertically, connected by THROUGH-SILICON VIAS\n   ⚠️ HYBRID BONDING  ⚠️ direct copper-to-copper and oxide-to-oxide\n   bonding with no solder — ⚠️ enables micron-scale pitch, far\n   denser than microbumps, and it is becoming essential (§27.2)\n⚠️ FAN-OUT WAFER LEVEL PACKAGING  redistribution layers, no substrate\n⚠️ CHIPLETS  ⚠️ partition a design into dies, each on the process\n   node that suits it — logic on the leading edge, I\u002FO and analog\n   on cheaper mature nodes. ⚠️ Yield (§17), cost and reticle limit\n   all push this way\n⚠️ UCIe  ⚠️ the standard die-to-die interconnect, aiming at an open\n   chiplet ecosystem\n⚠️ THE HARD PARTS  ⚠️ thermal (stacked dies trap heat) · warpage\n   from CTE mismatch · ⚠️ known good die (§19) · ⚠️ ABF SUBSTRATE\n   supply, which is concentrated and has had long lead times ·\n   power delivery through the stack\n```\n","# Semiconductors and Chip Manufacturing: Process Integration, Yield, Metrology and Inspection, Test, and Advanced Packaging\n\n> **Part 4 of 6** of the *Semiconductors and Chip Manufacturing* reference (plugin `semiconductors-and-chip-manufacturing`), covering §16–§20. Sibling skills: `semi-carriers-doping-junctions-mosfet-and-scaling` (§0–§5), `semi-transistor-architectures-interconnect-memory-and-wafers` (§6–§9), `semi-cleanroom-lithography-deposition-etch-and-cmp` (§10–§15), `semi-pcb-assembly-reliability-design-flow-and-economics` (§21–§26), `semi-reference` (§27–§32). Section numbers are shared across the set; a reference written as §N → `skill` points into that sibling skill.\n>\n> **Currency:** The physics is settled. Two frontiers are moving. See §27 → `semi-reference` for High-NA lithography adoption, and advanced packaging as the binding constraint.\n\n> **⚠️ The most complex manufacturing humans do, by a wide margin.** ⚠️ **A leading-edge\n> chip involves on the order of a thousand process steps, features smaller than a virus,\n> tolerances measured in atoms, and a supply chain with genuine single points of failure.**\n>\n> **Builds directly on an electromagnetism reference (band theory, pn junctions, MOSFET\n> physics, wide-bandgap materials). Complements a manufacturing reference (tolerancing and\n> yield), an organic-chemistry reference (photoresists and packaging polymers), and a\n> resource-extraction reference (where the materials come from).**\n>\n> **⚠️ GOTCHA** boxes mark where marketing and physics diverge — and this industry has more\n> of that gap than most.\n>\n> **The three ideas that organize this document:**\n> 1. **⚠️ \"NODE NAMES ARE MARKETING\"** (§5 → `semi-carriers-doping-junctions-mosfet-and-scaling`). **\"3nm\" does not describe any physical\n>    dimension on the chip. It has been a marketing label for roughly a decade, and\n>    comparing nodes across foundries by name is meaningless.**\n> 2. **⚠️ YIELD IS THE WHOLE BUSINESS** (§17). **Everything — die size, chiplet\n>    architecture, defect control, cleanroom spend — is downstream of the fact that\n>    profitability is set by what fraction of die work.**\n> 3. **⚠️ THE BOTTLENECK MOVED TO THE BACK END** (§20, §27.2 → `semi-reference`). **For AI accelerators the\n>    binding constraint is no longer transistors — it is packaging and memory, which is a\n>    genuine reversal of thirty years of industry structure.**\n\n---\n\n## §16. Process Integration\n\n**⚠️ The discipline of making hundreds of individually-working steps work TOGETHER.**\n⚠️ **FEOL (front end of line — transistors) → MOL (contacts) → BEOL (interconnect).**\n**⚠️ A mask set for a leading node runs to dozens of layers and costs millions**, ⚠️ **which\nis a large part of why NRE at the leading edge is prohibitive for low-volume designs**\n(§25 → `semi-pcb-assembly-reliability-design-flow-and-economics`).\n**⚠️ The integration engineer's problem is that everything interacts**: ⚠️ **a change in\netch chemistry shifts a CMP rate, which changes overlay, which shifts device parameters.**\n**⚠️ Process control** uses SPC and increasingly run-to-run feedback (see a manufacturing\nreference on Cp\u002FCpk) — ⚠️ **and PROCESS VARIATION is now a first-order design concern:\nrandom dopant fluctuation, line edge roughness and metal grain variation make nominally\nidentical transistors measurably different.**\n\n---\n\n## §17. ⚠️ Yield\n\n> **⚠️ The number that decides whether a fab makes money.**\n```\n⚠️ THE MODELS  ⚠️ Poisson yield ≈ e^(−AD) where A is die area and\n   D is defect density. ⚠️ Murphy's and negative binomial models\n   are used in practice because defects CLUSTER\n⚠️ ⚠️ THE CENTRAL CONSEQUENCE: YIELD FALLS EXPONENTIALLY WITH DIE\n   AREA. ⚠️ Doubling die size does far more than double the loss\n⚠️ ⚠️ THIS IS THE ENTIRE ARGUMENT FOR CHIPLETS (§20) —\n   four small dies yield far better than one large die of the\n   same total area, and you can bin and mix them\n⚠️ THE RETICLE LIMIT  ⚠️ a hard maximum die size set by the\n   exposure field. ⚠️ Large AI accelerators are AT it, which is\n   another forcing function toward multi-die\n⚠️ YIELD TYPES  ⚠️ line yield (wafers surviving the flow) ·\n   ⚠️ DIE yield (good die per wafer) · parametric yield (die that\n   work but miss spec) · packaging and final test yield\n⚠️ DEFECT SOURCES  particles · pattern defects · ⚠️ systematic\n   layout-sensitive defects (⚠️ these are DESIGN issues, addressed\n   by DFM rules) · contamination · equipment excursions\n⚠️ LEARNING CURVE  ⚠️ yield ramps over months to years; ⚠️ early\n   production of a new node is often economically poor, which is\n   why node transitions are financially painful\n```\n**⚠️ Binning** monetizes partial failures — ⚠️ **a die with a defective core or cache block\nis sold as a lower-tier product rather than scrapped, which is why product stacks look the\nway they do.**\n\n---\n\n## §18. Metrology and Inspection\n\n**⚠️ You cannot control what you cannot measure, at nanometre scale, non-destructively, on\nproduction wafers.**\n**⚠️ Techniques**: ⚠️ **CD-SEM for critical dimensions, scatterometry\u002FOCD for profiles,\nellipsometry for film thickness, overlay metrology (⚠️ the tightest budget of all — sub-nm\nat the leading edge), and defect inspection by optical and e-beam.**\n**⚠️ The fundamental tension**: ⚠️ **optical inspection is fast and cannot resolve the\nsmallest defects; e-beam resolves them and is far too slow for full-wafer coverage.**\n**⚠️ Hence sampling, hot-spot inspection guided by design, and increasing use of machine\nlearning to classify defects.**\n**⚠️ Failure analysis** works backwards from a failing die: ⚠️ **fault isolation, then FIB\ncross-sectioning, then TEM — expensive, slow, and the only way to find root cause.**\n\n---\n\n## §19. Test\n\n**⚠️ Testing is a large fraction of total cost and is easy to underestimate.**\n⚠️ **WAFER SORT\u002Fprobe identifies good die before the expense of packaging; ⚠️ FINAL TEST\nafter packaging; ⚠️ BURN-IN stresses parts to precipitate infant mortality** (§23 → `semi-pcb-assembly-reliability-design-flow-and-economics`).\n**⚠️ DESIGN FOR TEST is mandatory**: ⚠️ **scan chains, BIST, and JTAG boundary scan exist\nbecause a billion-transistor chip has no other way to be observed.**\n**⚠️ Coverage versus time is the eternal trade** — ⚠️ **test time is money, and untested\nfaults escape to customers.**\n> **⚠️ GOTCHA — KNOWN GOOD DIE is the problem that makes chiplets hard** (§20).\n> ⚠️ **If you assemble ten dies into one package and any is bad, you scrap the whole\n> assembly including the good ones.** **⚠️ So multi-die packaging requires far higher\n> confidence in pre-assembly test than monolithic designs ever did, and reported estimates\n> put chiplet test cost at 15–30% above monolithic for this reason.**\n\n---\n\n# PART III — PACKAGING AND BOARDS\n\n## §20. ⚠️ Advanced Packaging\n\n> **⚠️ Historically an afterthought; now the most strategically important part of the\n> chain** (§27.2 → `semi-reference`).\n```\n⚠️ WHAT PACKAGING DOES  ⚠️ electrical connection · POWER delivery ·\n   ⚠️ HEAT removal · mechanical protection · and ⚠️ matching the\n   chip's micron-scale pitch to the board's millimetre scale\n⚠️ TRADITIONAL  wire bond · flip chip (⚠️ solder bumps, area array,\n   far better electrically) · BGA\n⚠️ 2.5D  ⚠️ multiple dies side by side on a SILICON INTERPOSER with\n   fine wiring. ⚠️ TSMC's CoWoS is the dominant example — this is\n   how a GPU sits next to HBM stacks\n   ⚠️ EMIB (Intel) embeds a small silicon bridge in the substrate\n   instead of a full interposer — cheaper, no through-silicon\n   interposer needed\n⚠️ 3D  ⚠️ dies stacked vertically, connected by THROUGH-SILICON VIAS\n   ⚠️ HYBRID BONDING  ⚠️ direct copper-to-copper and oxide-to-oxide\n   bonding with no solder — ⚠️ enables micron-scale pitch, far\n   denser than microbumps, and it is becoming essential (§27.2)\n⚠️ FAN-OUT WAFER LEVEL PACKAGING  redistribution layers, no substrate\n⚠️ CHIPLETS  ⚠️ partition a design into dies, each on the process\n   node that suits it — logic on the leading edge, I\u002FO and analog\n   on cheaper mature nodes. ⚠️ Yield (§17), cost and reticle limit\n   all push this way\n⚠️ UCIe  ⚠️ the standard die-to-die interconnect, aiming at an open\n   chiplet ecosystem\n⚠️ THE HARD PARTS  ⚠️ thermal (stacked dies trap heat) · warpage\n   from CTE mismatch · ⚠️ known good die (§19) · ⚠️ ABF SUBSTRATE\n   supply, which is concentrated and has had long lead times ·\n   power delivery through the stack\n```\n",{"name":5,"description":7},"develop","ae32736a1aabddabca5d2c96d665aa0ebc7d8700","src\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fsemiconductors-and-chip-manufacturing\u002Fskills\u002Fsemi-integration-yield-metrology-test-and-packaging",3,"https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey","https:\u002F\u002Fthe-vibey-project.github.io\u002Fvibey\u002F","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project","https:\u002F\u002Fvibewithadam.matthewsteinberger.com","freedom for software engineers","2026-11-15 05:47:42",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add the-vibey-project\u002Fvibey --skill semi-integration-yield-metrology-test-and-packaging",{"tool":40,"command":41},"bunx","bunx skills add the-vibey-project\u002Fvibey --skill semi-integration-yield-metrology-test-and-packaging",{"tool":43,"command":44},"pnpm","pnpm dlx skills add the-vibey-project\u002Fvibey --skill semi-integration-yield-metrology-test-and-packaging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fsemiconductors-and-chip-manufacturing\u002Fskills\u002Fsemi-integration-yield-metrology-test-and-packaging\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7AT1FQJAE1FQYAMDTF490Y4","white-paper-writing","Use when writing white papers, technical reports, policy documents, thought leadership pieces, or any long-form authoritative document. Triggers on requests to write, structure, outline, or review white papers, technical reports, position papers, policy briefs, or evidence-driven arguments. Also use for B2B content marketing strategy, technical documentation requiring authority, academic-style reports, or any document that must educate while persuading. Use when someone asks \"how should I structure this\" for a long-form document.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fwhite-paper-writing\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AT16BJRJJKK2MASXRZS76G","prose-technical-mechanics","Use when editing or writing prose at a technical\u002Fmechanical level: choosing between Anglo-Saxon and Latinate diction, placing information in topic vs stress positions, writing periodic vs cumulative sentences, handling sentence rhythm, punctuation as logic, transitions, paragraph structure, or phonesthetics. Use when someone wants to understand WHY prose works or doesn't, not just surface-level style advice. Triggers on word choice, sentence structure, emphasis, rhythm, diction, or any deep writing mechanics question.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fprose-technical-mechanics\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AT0W9HT0ZZ9Y287NW99MR3","prose-mechanics","Use when writing, editing, or analyzing prose style; when trying to avoid generic AI-sounding writing; when applying specific prose styles such as journalistic, academic, narrative, KJV biblical, Hemingway plain, Latinate\u002FJamesian, Orwellian, Augustan, Victorian, Early Modern (Bacon, Browne, Milton), or free indirect discourse; or when coaching someone on writing voice and mechanics. Triggers on any request to improve, analyze, or write in a specific prose style, to fix \"AI-sounding\" writing, to make prose more vivid or concrete, to vary sentence rhythm, or to understand how a particular writer achieves their effects.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fprose-mechanics\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7AT0KR635JX66X2X6F3E2CP","narrative-structure","Use when structuring stories, pitches, presentations, white papers, or any persuasive narrative; analyzing the hero's journey in fiction or non-fiction; applying StoryBrand for business communication; designing narrative arcs for thought leadership; or understanding Vogler, Snyder, Propp, or Campbell frameworks. Triggers on any narrative structure, storytelling, pitch structure, StoryBrand, hero's journey, three-act structure, Freytag, Save the Cat, narrative arc, or \"how should I structure this story\u002Fpitch\u002Fpresentation\" request.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fnarrative-structure\u002FSKILL.md",[],[],{"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},"01M7AT0AKGW09NKKZDYBT8VRDE","legal-brief-writing","Use when writing legal briefs, motions, or any court filing; when analyzing judicial cognition and persuasion; when applying elite brief-writing techniques from Roberts, Clement, Kagan, Garner; or when structuring legal arguments for maximum persuasion. Also use for autistic\u002Fneurodivergent advocates who need to understand how their natural communication style maps to elite legal advocacy. Triggers on any legal writing, brief drafting, motion preparation, or legal argument structuring request.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Flegal-brief-writing\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},"01M7AT00VWPS4Q8B5VEMXX9NQT","journal-publishability-criteria","Use whenever a research paper, article or preprint is being written, revised, reviewed or published, and specifically before every publication of docs\u002Fpaper.md. Covers what legitimate journals actually gate on, in order of gating — the editor's desk screen (scope, novelty, package problems), what reviewers judge (methodological soundness, claims the evidence can carry, statistical and qualitative reporting), EQUATOR reporting guidelines, the ICMJE authorship criteria, COPE's view of text recycling, the near-universal generative-AI policy (no AI author, disclosure, author responsibility), TOP 2025 transparency standards, how to verify a journal is legitimate, submitting without an institution, and a pre-submission checklist. Triggers on requests to evaluate, review, prepare or submit a paper, to judge publishability, to write a declarations or data-availability section, to disclose AI use, or to check a journal.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fjournal-publishability-criteria\u002FSKILL.md",[],[]]