[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ARY9KBCNQQ8MAMZP8RX86J":3,"skill-same:01M7ARY9KBCNQQ8MAMZP8RX86J":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},"01M7ARY9KBCNQQ8MAMZP8RX86J","robotics-learning-simulation-and-fleets",null,"Use when working on the learning layer or on simulation: reinforcement learning and imitation learning, vision-language-action foundation models and an honest assessment of where they actually are, simulation and the sim-to-real gap including domain randomization, Isaac Sim, Gazebo and MuJoCo, and multi-robot systems and fleet management.","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\u002Frobotics-software\u002Fskills\u002Frobotics-learning-simulation-and-fleets\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: robotics-learning-simulation-and-fleets\ndescription: \"Use when working on the learning layer or on simulation: reinforcement learning and imitation learning, vision-language-action foundation models and an honest assessment of where they actually are, simulation and the sim-to-real gap including domain randomization, Isaac Sim, Gazebo and MuJoCo, and multi-robot systems and fleet management.\"\n---\n\n# Robotics Software: The Learning Layer, Simulation and Sim-to-Real, and Fleets\n\n> **Part 3 of 5** of the *Robotics Software* reference (plugin `robotics-software`), covering §8–§10. Sibling skills: `robotics-stack-ros2-and-perception` (§0–§4), `robotics-planning-control-and-manipulation` (§5–§7), `robotics-safety-standards-and-deployment` (§11–§14), `robotics-reference` (§15–§20). Section numbers are shared across the set; a reference written as §N → `skill` points into that sibling skill.\n>\n> **Currency:** Verified August 2026. See §17 → `robotics-reference` for the currency snapshot and what goes stale first.\n\n> **How to read this.** Reference for engineers building robots that operate in the\n> physical world with real consequences — deliberately distinct from a hobbyist kit\n> reference. Three markers:\n> - **[DURABLE]** — control theory, estimation, architecture, and safety discipline.\n>   Most of this document.\n> - **[VERSIONED]** — frameworks, models, standards, tooling.\n> - **[CONTESTED]** — genuine and active disagreement, of which this field currently has\n>   a lot.\n>\n> **⚠️ GOTCHA** boxes mark the failures that damage hardware, or people.\n>\n> **The three framings that organize everything below:**\n> 1. **Physics doesn't have an undo button.** A web service that fails returns a 500;\n>    a robot that fails puts mass through space. **This single asymmetry justifies every\n>    piece of apparently excessive rigour below** — the redundancy, the state machines,\n>    the simulation, the safety cases (§11 → `robotics-safety-standards-and-deployment`, §13 → `robotics-safety-standards-and-deployment`).\n> 2. **⚠️ Robotics is an integration discipline, and the integration is where it fails.**\n>    Perception, estimation, planning, and control each work in isolation and break at\n>    the seams — timing, coordinate frames, latency, and units. **The classic robotics bug\n>    is not a bad algorithm; it's a transform published 40ms late** (§3.4 → `robotics-stack-ros2-and-perception`, §12 → `robotics-safety-standards-and-deployment`).\n> 3. **The field is in the middle of a genuine methodological argument** between\n>    classical model-based robotics and learned end-to-end policies (§8, §16.1 → `robotics-reference`).\n>    **Neither side has won, production systems are overwhelmingly hybrid, and anyone\n>    telling you the argument is settled is selling something.**\n\n---\n\n## §8. The Learning Layer\n\n**[VERSIONED — the fastest-moving material in robotics, and the subject of §16.1 → `robotics-reference`'s genuine\nargument.]**\n\n### 8.1 The approaches\n\n**Reinforcement learning** — ⚠️ **overwhelmingly trained in simulation** (§9), because\nreal-world sample complexity is prohibitive. **Massively parallel sim (Isaac Gym\u002FLab) made\nlegged locomotion RL practical** and is arguably its clearest success story.\n**Imitation learning \u002F behaviour cloning** — learn from demonstrations. ⚠️ **The\ndistribution-shift problem is fundamental**: the policy visits states the demonstrator\nnever did. **Diffusion policies** became the strong default for manipulation.\n**Learning from human video** — sidesteps teleoperation cost; active research.\n\n### 8.2 ⚠️ Vision-Language-Action models\n\n**[VERSIONED] The development that changed the field's trajectory since 2023.** A VLA\ntakes a pretrained vision-language model and adapts it to output robot actions —\nimporting internet-scale semantic knowledge into a domain that has almost no data.\n\n**The lineage**: **RT-1** (2022) → **RT-2** → **Open X-Embodiment \u002F RT-X** (a\ncross-institution dataset that demonstrated positive transfer *across robot embodiments* —\narguably the field's ImageNet moment) → the current frontier.\n\n**[VERSIONED] The frontier systems as of 2026:**\n\n| Model | Notes |\n|---|---|\n| **π₀ \u002F π₀.₅ \u002F π₀.₇** (Physical Intelligence) | Flow-matching VLA for general robot control; **π₀.₅ targets open-world generalization** |\n| **Gemini Robotics \u002F 1.5** (DeepMind) | Built on Gemini; ⚠️ **\"thinking before acting\" — internal natural-language reasoning before action**; 1.5 adds embodied reasoning and **motion transfer across embodiments**. An on-device variant exists for latency\u002Fconnectivity-constrained settings, adapting to new tasks with **as few as 50–100 demonstrations** |\n| **GR00T N-series** (NVIDIA) | Open foundation model for humanoids. ⚠️ **Dual-system architecture: System 2 is a VLM that reasons and plans; System 1 is a diffusion transformer producing smooth motor actions at 120Hz** — tightly coupled and jointly trained. **N1.7 reached General Availability (Apache 2.0)** with a Cosmos-Reason2-2B\u002FQwen3-VL backbone |\n| **Helix** (Figure) | Hierarchical: a larger VLM at low frequency over a fast action module |\n| **Open models** | OpenVLA, RDT-1B, X-VLA, LingBot-VLA (⚠️ **20K hours of real dual-arm data, fully open-sourced**), Xiaomi-Robotics-0 |\n\n**⚠️ The architectural constraint worth understanding**: **models are small by LLM\nstandards — π₀ and GR00T N1 both use ~2B-parameter backbones — because on-device inference\nand real-time latency demand it.** Hierarchical designs escape this by running a larger\nVLM slowly over a fast local policy. **Cloud-hosted models can be bigger but inherit\nnetwork latency and a connectivity dependency**, which is a safety consideration, not just\na performance one.\n\n**World models** are the adjacent development: **NVIDIA Cosmos** generates synthetic\ntrajectory data rather than acting as a policy, and **world-action models** pretrained to\npredict then fine-tuned to act are an active 2026 direction.\n\n### 8.3 ⚠️ The honest assessment\n\n**[CONTESTED, and I'll state the disagreement rather than resolve it.]**\n\n**What's genuinely working**: semantic generalization (⚠️ **\"pick up the thing that holds\ncoffee\" is a query classical pipelines could not answer**), long-tail object handling,\ntask specification in natural language, and cross-embodiment transfer.\n\n**⚠️ What is not solved, and the gaps matter**: **no formal guarantees** — you cannot\nwrite a safety case around a VLA's behaviour today; **evaluation is genuinely hard** and\nbenchmark numbers translate poorly to deployments; **reliability at the tail** is far\nbelow what industrial deployment requires; **data remains the bottleneck** (robot data is\nexpensive and embodiment-specific); **latency** constrains model size; and\n**failure modes are unpredictable in a way that classical stacks' are not.**\n\n**[DURABLE] The production pattern almost everyone actually uses is hybrid**: learned\nperception and high-level policy, **classical control and a classical safety layer\nunderneath.** ⚠️ **The safety layer is not learned.** That's not conservatism; it's the\nonly current way to make an argument about what the system will not do (§13 → `robotics-safety-standards-and-deployment`).\n\n---\n\n## §9. Simulation and Sim-to-Real\n\n**[DURABLE] Simulation is not optional at this point** — it's where RL training, CI,\nregression testing, and scenario coverage happen.\n\n| Simulator | Position |\n|---|---|\n| **Isaac Sim \u002F Isaac Lab** | ⚠️ **GPU-parallel, photorealistic, the RL training standard.** NVIDIA-coupled |\n| **MuJoCo** | ⚠️ **Fast, accurate contact dynamics, now free and open.** The research default for manipulation and locomotion |\n| **Gazebo** (Harmonic\u002FIonic) | ROS-native, general-purpose. Ionic is the recommended pairing for Kilted |\n| **PyBullet** | Lightweight, accessible, widely used in research |\n| **Drake** (TRI) | ⚠️ **Rigorous multibody dynamics and optimization**; strong on contact and verification |\n| **CARLA \u002F AWSIM** | Autonomous driving |\n| **Genesis, Newton** | Newer generative\u002Fdifferentiable physics efforts |\n\n> **⚠️ GOTCHA — the sim-to-real gap, which is the field's permanent tax.** Simulators get\n> **contact, friction, deformables, and sensor noise wrong**, and those are exactly the\n> things that matter. **The mitigations that work**:\n> - **Domain randomization** — randomize masses, friction, latencies, textures, and\n>   lighting so the policy can't overfit to sim's specifics. ⚠️ **Randomizing *latency* is\n>   under-done and disproportionately valuable.**\n> - **System identification** — measure your actual robot's parameters and put them in the\n>   sim.\n> - **Sim-to-real-to-sim** — use real rollouts to correct the simulator.\n> - **⚠️ Keep a real-hardware regression suite.** Sim-only validation always eventually\n>   ships something that only works in sim.\n\n---\n\n## §10. Multi-Robot and Fleets\n\n**Coordination**: centralized (optimal, ⚠️ **single point of failure**) vs. decentralized\n(robust, suboptimal) vs. market\u002Fauction-based task allocation. **Multi-agent path finding**\n(CBS and variants) for warehouse-scale routing. **Traffic management** and deadlock\navoidance — ⚠️ **deadlock in a fleet of AMRs is a real and recurring production problem**,\nnot a theoretical one.\n\n**[DURABLE] Fleet software is a distributed systems problem wearing a robotics costume** —\neverything a cloud reference says about consensus, partition tolerance, idempotency and\nat-least-once delivery applies, **with the added constraint that the actuators keep moving\nduring a partition.** ⚠️ **Design what a robot does when it loses contact with the fleet\nmanager, explicitly.**\n\n**Also**: **Open-RMF** for heterogeneous fleet interop, **OTA update strategy** (⚠️ **with\nstaged rollout and rollback — you cannot brick a fleet**), remote operation and\nteleoperation fallback, and observability across a fleet.\n","# Robotics Software: The Learning Layer, Simulation and Sim-to-Real, and Fleets\n\n> **Part 3 of 5** of the *Robotics Software* reference (plugin `robotics-software`), covering §8–§10. Sibling skills: `robotics-stack-ros2-and-perception` (§0–§4), `robotics-planning-control-and-manipulation` (§5–§7), `robotics-safety-standards-and-deployment` (§11–§14), `robotics-reference` (§15–§20). Section numbers are shared across the set; a reference written as §N → `skill` points into that sibling skill.\n>\n> **Currency:** Verified August 2026. See §17 → `robotics-reference` for the currency snapshot and what goes stale first.\n\n> **How to read this.** Reference for engineers building robots that operate in the\n> physical world with real consequences — deliberately distinct from a hobbyist kit\n> reference. Three markers:\n> - **[DURABLE]** — control theory, estimation, architecture, and safety discipline.\n>   Most of this document.\n> - **[VERSIONED]** — frameworks, models, standards, tooling.\n> - **[CONTESTED]** — genuine and active disagreement, of which this field currently has\n>   a lot.\n>\n> **⚠️ GOTCHA** boxes mark the failures that damage hardware, or people.\n>\n> **The three framings that organize everything below:**\n> 1. **Physics doesn't have an undo button.** A web service that fails returns a 500;\n>    a robot that fails puts mass through space. **This single asymmetry justifies every\n>    piece of apparently excessive rigour below** — the redundancy, the state machines,\n>    the simulation, the safety cases (§11 → `robotics-safety-standards-and-deployment`, §13 → `robotics-safety-standards-and-deployment`).\n> 2. **⚠️ Robotics is an integration discipline, and the integration is where it fails.**\n>    Perception, estimation, planning, and control each work in isolation and break at\n>    the seams — timing, coordinate frames, latency, and units. **The classic robotics bug\n>    is not a bad algorithm; it's a transform published 40ms late** (§3.4 → `robotics-stack-ros2-and-perception`, §12 → `robotics-safety-standards-and-deployment`).\n> 3. **The field is in the middle of a genuine methodological argument** between\n>    classical model-based robotics and learned end-to-end policies (§8, §16.1 → `robotics-reference`).\n>    **Neither side has won, production systems are overwhelmingly hybrid, and anyone\n>    telling you the argument is settled is selling something.**\n\n---\n\n## §8. The Learning Layer\n\n**[VERSIONED — the fastest-moving material in robotics, and the subject of §16.1 → `robotics-reference`'s genuine\nargument.]**\n\n### 8.1 The approaches\n\n**Reinforcement learning** — ⚠️ **overwhelmingly trained in simulation** (§9), because\nreal-world sample complexity is prohibitive. **Massively parallel sim (Isaac Gym\u002FLab) made\nlegged locomotion RL practical** and is arguably its clearest success story.\n**Imitation learning \u002F behaviour cloning** — learn from demonstrations. ⚠️ **The\ndistribution-shift problem is fundamental**: the policy visits states the demonstrator\nnever did. **Diffusion policies** became the strong default for manipulation.\n**Learning from human video** — sidesteps teleoperation cost; active research.\n\n### 8.2 ⚠️ Vision-Language-Action models\n\n**[VERSIONED] The development that changed the field's trajectory since 2023.** A VLA\ntakes a pretrained vision-language model and adapts it to output robot actions —\nimporting internet-scale semantic knowledge into a domain that has almost no data.\n\n**The lineage**: **RT-1** (2022) → **RT-2** → **Open X-Embodiment \u002F RT-X** (a\ncross-institution dataset that demonstrated positive transfer *across robot embodiments* —\narguably the field's ImageNet moment) → the current frontier.\n\n**[VERSIONED] The frontier systems as of 2026:**\n\n| Model | Notes |\n|---|---|\n| **π₀ \u002F π₀.₅ \u002F π₀.₇** (Physical Intelligence) | Flow-matching VLA for general robot control; **π₀.₅ targets open-world generalization** |\n| **Gemini Robotics \u002F 1.5** (DeepMind) | Built on Gemini; ⚠️ **\"thinking before acting\" — internal natural-language reasoning before action**; 1.5 adds embodied reasoning and **motion transfer across embodiments**. An on-device variant exists for latency\u002Fconnectivity-constrained settings, adapting to new tasks with **as few as 50–100 demonstrations** |\n| **GR00T N-series** (NVIDIA) | Open foundation model for humanoids. ⚠️ **Dual-system architecture: System 2 is a VLM that reasons and plans; System 1 is a diffusion transformer producing smooth motor actions at 120Hz** — tightly coupled and jointly trained. **N1.7 reached General Availability (Apache 2.0)** with a Cosmos-Reason2-2B\u002FQwen3-VL backbone |\n| **Helix** (Figure) | Hierarchical: a larger VLM at low frequency over a fast action module |\n| **Open models** | OpenVLA, RDT-1B, X-VLA, LingBot-VLA (⚠️ **20K hours of real dual-arm data, fully open-sourced**), Xiaomi-Robotics-0 |\n\n**⚠️ The architectural constraint worth understanding**: **models are small by LLM\nstandards — π₀ and GR00T N1 both use ~2B-parameter backbones — because on-device inference\nand real-time latency demand it.** Hierarchical designs escape this by running a larger\nVLM slowly over a fast local policy. **Cloud-hosted models can be bigger but inherit\nnetwork latency and a connectivity dependency**, which is a safety consideration, not just\na performance one.\n\n**World models** are the adjacent development: **NVIDIA Cosmos** generates synthetic\ntrajectory data rather than acting as a policy, and **world-action models** pretrained to\npredict then fine-tuned to act are an active 2026 direction.\n\n### 8.3 ⚠️ The honest assessment\n\n**[CONTESTED, and I'll state the disagreement rather than resolve it.]**\n\n**What's genuinely working**: semantic generalization (⚠️ **\"pick up the thing that holds\ncoffee\" is a query classical pipelines could not answer**), long-tail object handling,\ntask specification in natural language, and cross-embodiment transfer.\n\n**⚠️ What is not solved, and the gaps matter**: **no formal guarantees** — you cannot\nwrite a safety case around a VLA's behaviour today; **evaluation is genuinely hard** and\nbenchmark numbers translate poorly to deployments; **reliability at the tail** is far\nbelow what industrial deployment requires; **data remains the bottleneck** (robot data is\nexpensive and embodiment-specific); **latency** constrains model size; and\n**failure modes are unpredictable in a way that classical stacks' are not.**\n\n**[DURABLE] The production pattern almost everyone actually uses is hybrid**: learned\nperception and high-level policy, **classical control and a classical safety layer\nunderneath.** ⚠️ **The safety layer is not learned.** That's not conservatism; it's the\nonly current way to make an argument about what the system will not do (§13 → `robotics-safety-standards-and-deployment`).\n\n---\n\n## §9. Simulation and Sim-to-Real\n\n**[DURABLE] Simulation is not optional at this point** — it's where RL training, CI,\nregression testing, and scenario coverage happen.\n\n| Simulator | Position |\n|---|---|\n| **Isaac Sim \u002F Isaac Lab** | ⚠️ **GPU-parallel, photorealistic, the RL training standard.** NVIDIA-coupled |\n| **MuJoCo** | ⚠️ **Fast, accurate contact dynamics, now free and open.** The research default for manipulation and locomotion |\n| **Gazebo** (Harmonic\u002FIonic) | ROS-native, general-purpose. Ionic is the recommended pairing for Kilted |\n| **PyBullet** | Lightweight, accessible, widely used in research |\n| **Drake** (TRI) | ⚠️ **Rigorous multibody dynamics and optimization**; strong on contact and verification |\n| **CARLA \u002F AWSIM** | Autonomous driving |\n| **Genesis, Newton** | Newer generative\u002Fdifferentiable physics efforts |\n\n> **⚠️ GOTCHA — the sim-to-real gap, which is the field's permanent tax.** Simulators get\n> **contact, friction, deformables, and sensor noise wrong**, and those are exactly the\n> things that matter. **The mitigations that work**:\n> - **Domain randomization** — randomize masses, friction, latencies, textures, and\n>   lighting so the policy can't overfit to sim's specifics. ⚠️ **Randomizing *latency* is\n>   under-done and disproportionately valuable.**\n> - **System identification** — measure your actual robot's parameters and put them in the\n>   sim.\n> - **Sim-to-real-to-sim** — use real rollouts to correct the simulator.\n> - **⚠️ Keep a real-hardware regression suite.** Sim-only validation always eventually\n>   ships something that only works in sim.\n\n---\n\n## §10. Multi-Robot and Fleets\n\n**Coordination**: centralized (optimal, ⚠️ **single point of failure**) vs. decentralized\n(robust, suboptimal) vs. market\u002Fauction-based task allocation. **Multi-agent path finding**\n(CBS and variants) for warehouse-scale routing. **Traffic management** and deadlock\navoidance — ⚠️ **deadlock in a fleet of AMRs is a real and recurring production problem**,\nnot a theoretical one.\n\n**[DURABLE] Fleet software is a distributed systems problem wearing a robotics costume** —\neverything a cloud reference says about consensus, partition tolerance, idempotency and\nat-least-once delivery applies, **with the added constraint that the actuators keep moving\nduring a partition.** ⚠️ **Design what a robot does when it loses contact with the fleet\nmanager, explicitly.**\n\n**Also**: **Open-RMF** for heterogeneous fleet interop, **OTA update strategy** (⚠️ **with\nstaged rollout and rollback — you cannot brick a fleet**), remote operation and\nteleoperation fallback, and observability across a fleet.\n",{"name":5,"description":7},"develop","ae32736a1aabddabca5d2c96d665aa0ebc7d8700","src\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Frobotics-software\u002Fskills\u002Frobotics-learning-simulation-and-fleets",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 robotics-learning-simulation-and-fleets",{"tool":40,"command":41},"bunx","bunx skills add the-vibey-project\u002Fvibey --skill robotics-learning-simulation-and-fleets",{"tool":43,"command":44},"pnpm","pnpm dlx skills add the-vibey-project\u002Fvibey --skill robotics-learning-simulation-and-fleets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Frobotics-software\u002Fskills\u002Frobotics-learning-simulation-and-fleets\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",[],[]]