[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ASPYWK2322XT14C3Q313SW":3,"skill-same:01M7ASPYWK2322XT14C3Q313SW":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},"01M7ASPYWK2322XT14C3Q313SW","game-ai-networking-and-tools",null,"Use when building gameplay AI, multiplayer, or the content pipeline: the decision-making toolbox (FSMs, utility AI, GOAP), pathfinding (navmesh, A*, flow fields), making AI feel right, the networking models (peer-to-peer, client-server, lockstep), client-server done properly (authoritative server, prediction, reconciliation, lag compensation, interest management), rollback netcode specifics, and tools and the content pipeline.","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\u002Fvideo-game-development\u002Fskills\u002Fgame-ai-networking-and-tools\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: game-ai-networking-and-tools\ndescription: \"Use when building gameplay AI, multiplayer, or the content pipeline: the decision-making toolbox (FSMs, utility AI, GOAP), pathfinding (navmesh, A*, flow fields), making AI feel right, the networking models (peer-to-peer, client-server, lockstep), client-server done properly (authoritative server, prediction, reconciliation, lag compensation, interest management), rollback netcode specifics, and tools and the content pipeline.\"\n---\n\n# Game Development: Gameplay AI, Networking, and Tools and Pipeline\n\n> **Part 3 of 5** of the *Video Game Development* reference (plugin `video-game-development`), covering §8–§10. Sibling skills: `game-engines-loop-and-architecture` (§0–§3), `game-rendering-physics-animation-and-audio` (§4–§7), `game-performance-feel-and-shipping` (§11–§15), `game-development-reference` (§16–§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 → `game-development-reference` for the currency snapshot and what goes stale first.\n\n> **How to read this.** Reference, not tutorial. Sections are independent. Three markers:\n> - **[DURABLE]** — real-time systems reality, human perception, or a lesson the industry\n>   has relearned every console generation. Does not expire.\n> - **[VERSIONED]** — specific to an engine version, API, platform, or market condition.\n>   Verify before relying on it.\n> - **[CONTESTED]** — practitioners genuinely disagree, usually because the right answer\n>   depends on team size and genre.\n>\n> **⚠️ GOTCHA** boxes mark the mistakes that ship broken games, blow the frame budget, or\n> destroy a studio's schedule.\n>\n> **The three framings that organize everything below:**\n> 1. **A game is a soft-real-time simulation with a hard deadline, 60 times a second.**\n>    16.67 ms at 60 fps, 8.33 ms at 120. Everything — rendering, physics, AI, audio,\n>    networking, streaming, GC — shares that budget. **Consistency beats peak framerate**;\n>    a stable 30 feels better than a 60 that stutters.\n> 2. **Games are content pipelines with a game attached.** On any team above about five\n>    people, the tools, build system, and iteration loop determine your output more than\n>    your engine code does. Ten-minute iteration times will cost you the game.\n> 3. **Scope is the thing that kills projects, not technology.** The overwhelming majority\n>    of unfinished games died of ambition, not of a hard technical problem. §14 → `game-performance-feel-and-shipping` is the\n>    section most people need and skip.\n\n---\n\n## §8. Gameplay AI\n\n**[DURABLE] Game AI is not machine learning; it is the craft of producing believable,\nreadable, *beatable* behaviour.** The goal is a good opponent from the player's\nperspective, not an optimal agent. **An AI that is too good is a design failure.**\n\n### 8.1 The decision-making toolbox\n\n| Technique | Use |\n|---|---|\n| **Finite state machine** | Simple agents. Readable, debuggable, and it explodes combinatorially past ~10 states |\n| **Hierarchical FSM** | Nested states — a real improvement for character control |\n| **Behaviour tree** | **The industry default.** Composable, designer-authorable, good tooling in every engine |\n| **Utility AI** | Score each option, pick the best. Excellent for sims and many-option agents (*The Sims*) |\n| **GOAP** (goal-oriented action planning) | Plans a sequence of actions to reach a goal. *F.E.A.R.*'s famous squad AI |\n| **HTN planning** | Hierarchical task networks. *Horizon Zero Dawn*, *Transformers* |\n| **Steering behaviours** | Seek, flee, arrive, separate, flock (Reynolds' boids) — the movement layer beneath everything |\n\n### 8.2 Pathfinding\n\n**A\\*** on a navmesh (or grid) is still the answer. **Navmesh generation** (Recast is the\nopen-source standard, and is what most engines use or imitate). Then the practical layer:\n**hierarchical pathfinding** for large maps, **string pulling \u002F funnel algorithm** to\nsmooth the path off the mesh polygon centers, **local avoidance** (RVO\u002FORCA) so agents\ndon't collide, **path caching and request budgeting** (⚠️ don't path 500 agents in one\nframe — amortize across frames), and **flow fields** when many agents share a destination\n(the standard RTS answer).\n\n### 8.3 Making AI *feel* right\n\n**[DURABLE] The techniques that make AI good are mostly about legibility, not\nintelligence:** telegraphed attacks with wind-up frames; **deliberately imperfect\naccuracy** (and the near-universal \"first shot always misses\" rule); **reaction delays**\nso the player can respond; **barks and animation that externalize internal state** so the\nplayer can read what the AI is doing; **attack tokens** so only one or two enemies engage\nat a time regardless of how many are present; and **cheating in the player's favour**\n(hidden last-hit-point buffers, ammo drops when low). *F.E.A.R.*'s AI is remembered as\nbrilliant largely because the agents **announce their plans out loud**.\n\n---\n\n## §9. Networking\n\n**[DURABLE] Multiplayer is not a feature you add. It is an architectural decision made on\nday one**, and retrofitting it onto a single-player codebase is one of the most reliable\nways to destroy a schedule.\n\n### 9.1 The models\n\n| Model | How | Trade-off |\n|---|---|---|\n| **Lockstep \u002F deterministic** | Send only inputs; every peer simulates identically | Tiny bandwidth, scales to thousands of units (RTS). **Requires perfect determinism (§2.2 → `game-engines-loop-and-architecture`)**; one desync ruins the match; latency = worst player |\n| **Client-server, authoritative** | Server simulates; clients send input and render state | **The standard for action games.** Cheat-resistant. Costs server infrastructure |\n| **Peer-to-peer** | Direct connections | No server cost; NAT traversal pain, and trivially cheatable |\n| **Rollback** | Predict remote inputs, roll back and re-simulate on mismatch | **The fighting-game standard (GGPO).** Superb feel; demands determinism and cheap re-simulation |\n\n### 9.2 Client-server, done properly\n\nThe canonical stack — from the Quake\u002FSource lineage and still correct:\n1. **Client-side prediction** — apply your own input immediately, don't wait for the\n   server round trip.\n2. **Server reconciliation** — server sends authoritative state with the last-processed\n   input sequence number; client rewinds and replays unacknowledged inputs.\n3. **Entity interpolation** — render other players slightly in the past (~100 ms) to\n   smooth their motion.\n4. **Lag compensation** — the server rewinds other players to where the shooter *saw* them\n   when validating a hit.\n\n> **⚠️ GOTCHA — lag compensation is a design decision, not a technical one.** It makes\n> shooting feel right for the shooter and produces the \"I got shot behind cover\"\n> experience for the target. **You are choosing whose experience to privilege**, and every\n> shooter makes that call explicitly. There is no setting that satisfies both.\n\n**Also**: **snapshot delta compression** and **interest management \u002F relevancy** (don't\nsend what the client can't see) are what make bandwidth tractable; **UDP with your own\nreliability layer** for game traffic (TCP head-of-line blocking is fatal), with TCP or\nHTTPS for lobby, matchmaking, and commerce.\n\n**⚠️ Never trust the client.** Validate movement, rate-limit actions, keep the inventory\nand economy server-side. Anti-cheat is an arms race with real anti-cheat middleware\n(EAC, BattlEye), and kernel-level anti-cheat is itself contested for privacy and stability\nreasons.\n\n### 9.3 Rollback specifics\n\nRollback needs: full deterministic simulation, cheap **save\u002Frestore of game state**\n(usually a compact struct you can memcpy), simulation fast enough to run **7–10 frames of\nre-simulation inside one frame's budget**, and input delay tuning. It's the reason modern\nfighting games feel dramatically better online than the delay-based generation did — and\nit's essentially impossible to bolt onto a game whose state lives scattered across engine\nobjects.\n\n---\n\n## §10. Tools and Pipeline\n\n**[DURABLE] On any team past a few people, tools and iteration time determine your output\nmore than your engine choice does.** This is the most consistently under-invested area in\ngame development.\n\n- **Iteration time is the metric that matters.** From \"change a value\" to \"see it in the\n  game\": target **seconds**. A 10-minute rebuild-and-reload loop doesn't slow you by\n  10 minutes — it eliminates the experimentation that finds the fun.\n- **Hot reload** for scripts, shaders, and assets. Worth building.\n- **Asset pipeline**: source assets (`.psd`, `.blend`, `.wav`) → **deterministic,\n  cacheable import** → platform-optimized runtime format. **Never ship source formats.**\n- **Content authoring in data, not code**, so designers can work without programmers and\n  without a rebuild.\n- **In-game debug tooling**: console, cheat commands, free camera, state visualizers,\n  hitbox and navmesh overlays, AI state readouts, performance HUD. **Build these early;\n  they pay for themselves within weeks.**\n- **Version control**: **Perforce** remains the industry standard for large binary assets;\n  **Git with LFS** works for smaller projects. ⚠️ Git handles large binaries badly and\n  cannot lock files, which matters enormously when two artists edit the same `.uasset`.\n- **Build system and CI**: automated builds per commit, on every target platform, with\n  automated smoke tests. **A broken build blocks the whole team.**\n","# Game Development: Gameplay AI, Networking, and Tools and Pipeline\n\n> **Part 3 of 5** of the *Video Game Development* reference (plugin `video-game-development`), covering §8–§10. Sibling skills: `game-engines-loop-and-architecture` (§0–§3), `game-rendering-physics-animation-and-audio` (§4–§7), `game-performance-feel-and-shipping` (§11–§15), `game-development-reference` (§16–§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 → `game-development-reference` for the currency snapshot and what goes stale first.\n\n> **How to read this.** Reference, not tutorial. Sections are independent. Three markers:\n> - **[DURABLE]** — real-time systems reality, human perception, or a lesson the industry\n>   has relearned every console generation. Does not expire.\n> - **[VERSIONED]** — specific to an engine version, API, platform, or market condition.\n>   Verify before relying on it.\n> - **[CONTESTED]** — practitioners genuinely disagree, usually because the right answer\n>   depends on team size and genre.\n>\n> **⚠️ GOTCHA** boxes mark the mistakes that ship broken games, blow the frame budget, or\n> destroy a studio's schedule.\n>\n> **The three framings that organize everything below:**\n> 1. **A game is a soft-real-time simulation with a hard deadline, 60 times a second.**\n>    16.67 ms at 60 fps, 8.33 ms at 120. Everything — rendering, physics, AI, audio,\n>    networking, streaming, GC — shares that budget. **Consistency beats peak framerate**;\n>    a stable 30 feels better than a 60 that stutters.\n> 2. **Games are content pipelines with a game attached.** On any team above about five\n>    people, the tools, build system, and iteration loop determine your output more than\n>    your engine code does. Ten-minute iteration times will cost you the game.\n> 3. **Scope is the thing that kills projects, not technology.** The overwhelming majority\n>    of unfinished games died of ambition, not of a hard technical problem. §14 → `game-performance-feel-and-shipping` is the\n>    section most people need and skip.\n\n---\n\n## §8. Gameplay AI\n\n**[DURABLE] Game AI is not machine learning; it is the craft of producing believable,\nreadable, *beatable* behaviour.** The goal is a good opponent from the player's\nperspective, not an optimal agent. **An AI that is too good is a design failure.**\n\n### 8.1 The decision-making toolbox\n\n| Technique | Use |\n|---|---|\n| **Finite state machine** | Simple agents. Readable, debuggable, and it explodes combinatorially past ~10 states |\n| **Hierarchical FSM** | Nested states — a real improvement for character control |\n| **Behaviour tree** | **The industry default.** Composable, designer-authorable, good tooling in every engine |\n| **Utility AI** | Score each option, pick the best. Excellent for sims and many-option agents (*The Sims*) |\n| **GOAP** (goal-oriented action planning) | Plans a sequence of actions to reach a goal. *F.E.A.R.*'s famous squad AI |\n| **HTN planning** | Hierarchical task networks. *Horizon Zero Dawn*, *Transformers* |\n| **Steering behaviours** | Seek, flee, arrive, separate, flock (Reynolds' boids) — the movement layer beneath everything |\n\n### 8.2 Pathfinding\n\n**A\\*** on a navmesh (or grid) is still the answer. **Navmesh generation** (Recast is the\nopen-source standard, and is what most engines use or imitate). Then the practical layer:\n**hierarchical pathfinding** for large maps, **string pulling \u002F funnel algorithm** to\nsmooth the path off the mesh polygon centers, **local avoidance** (RVO\u002FORCA) so agents\ndon't collide, **path caching and request budgeting** (⚠️ don't path 500 agents in one\nframe — amortize across frames), and **flow fields** when many agents share a destination\n(the standard RTS answer).\n\n### 8.3 Making AI *feel* right\n\n**[DURABLE] The techniques that make AI good are mostly about legibility, not\nintelligence:** telegraphed attacks with wind-up frames; **deliberately imperfect\naccuracy** (and the near-universal \"first shot always misses\" rule); **reaction delays**\nso the player can respond; **barks and animation that externalize internal state** so the\nplayer can read what the AI is doing; **attack tokens** so only one or two enemies engage\nat a time regardless of how many are present; and **cheating in the player's favour**\n(hidden last-hit-point buffers, ammo drops when low). *F.E.A.R.*'s AI is remembered as\nbrilliant largely because the agents **announce their plans out loud**.\n\n---\n\n## §9. Networking\n\n**[DURABLE] Multiplayer is not a feature you add. It is an architectural decision made on\nday one**, and retrofitting it onto a single-player codebase is one of the most reliable\nways to destroy a schedule.\n\n### 9.1 The models\n\n| Model | How | Trade-off |\n|---|---|---|\n| **Lockstep \u002F deterministic** | Send only inputs; every peer simulates identically | Tiny bandwidth, scales to thousands of units (RTS). **Requires perfect determinism (§2.2 → `game-engines-loop-and-architecture`)**; one desync ruins the match; latency = worst player |\n| **Client-server, authoritative** | Server simulates; clients send input and render state | **The standard for action games.** Cheat-resistant. Costs server infrastructure |\n| **Peer-to-peer** | Direct connections | No server cost; NAT traversal pain, and trivially cheatable |\n| **Rollback** | Predict remote inputs, roll back and re-simulate on mismatch | **The fighting-game standard (GGPO).** Superb feel; demands determinism and cheap re-simulation |\n\n### 9.2 Client-server, done properly\n\nThe canonical stack — from the Quake\u002FSource lineage and still correct:\n1. **Client-side prediction** — apply your own input immediately, don't wait for the\n   server round trip.\n2. **Server reconciliation** — server sends authoritative state with the last-processed\n   input sequence number; client rewinds and replays unacknowledged inputs.\n3. **Entity interpolation** — render other players slightly in the past (~100 ms) to\n   smooth their motion.\n4. **Lag compensation** — the server rewinds other players to where the shooter *saw* them\n   when validating a hit.\n\n> **⚠️ GOTCHA — lag compensation is a design decision, not a technical one.** It makes\n> shooting feel right for the shooter and produces the \"I got shot behind cover\"\n> experience for the target. **You are choosing whose experience to privilege**, and every\n> shooter makes that call explicitly. There is no setting that satisfies both.\n\n**Also**: **snapshot delta compression** and **interest management \u002F relevancy** (don't\nsend what the client can't see) are what make bandwidth tractable; **UDP with your own\nreliability layer** for game traffic (TCP head-of-line blocking is fatal), with TCP or\nHTTPS for lobby, matchmaking, and commerce.\n\n**⚠️ Never trust the client.** Validate movement, rate-limit actions, keep the inventory\nand economy server-side. Anti-cheat is an arms race with real anti-cheat middleware\n(EAC, BattlEye), and kernel-level anti-cheat is itself contested for privacy and stability\nreasons.\n\n### 9.3 Rollback specifics\n\nRollback needs: full deterministic simulation, cheap **save\u002Frestore of game state**\n(usually a compact struct you can memcpy), simulation fast enough to run **7–10 frames of\nre-simulation inside one frame's budget**, and input delay tuning. It's the reason modern\nfighting games feel dramatically better online than the delay-based generation did — and\nit's essentially impossible to bolt onto a game whose state lives scattered across engine\nobjects.\n\n---\n\n## §10. Tools and Pipeline\n\n**[DURABLE] On any team past a few people, tools and iteration time determine your output\nmore than your engine choice does.** This is the most consistently under-invested area in\ngame development.\n\n- **Iteration time is the metric that matters.** From \"change a value\" to \"see it in the\n  game\": target **seconds**. A 10-minute rebuild-and-reload loop doesn't slow you by\n  10 minutes — it eliminates the experimentation that finds the fun.\n- **Hot reload** for scripts, shaders, and assets. Worth building.\n- **Asset pipeline**: source assets (`.psd`, `.blend`, `.wav`) → **deterministic,\n  cacheable import** → platform-optimized runtime format. **Never ship source formats.**\n- **Content authoring in data, not code**, so designers can work without programmers and\n  without a rebuild.\n- **In-game debug tooling**: console, cheat commands, free camera, state visualizers,\n  hitbox and navmesh overlays, AI state readouts, performance HUD. **Build these early;\n  they pay for themselves within weeks.**\n- **Version control**: **Perforce** remains the industry standard for large binary assets;\n  **Git with LFS** works for smaller projects. ⚠️ Git handles large binaries badly and\n  cannot lock files, which matters enormously when two artists edit the same `.uasset`.\n- **Build system and CI**: automated builds per commit, on every target platform, with\n  automated smoke tests. **A broken build blocks the whole team.**\n",{"name":5,"description":7},"develop","ae32736a1aabddabca5d2c96d665aa0ebc7d8700","src\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fvideo-game-development\u002Fskills\u002Fgame-ai-networking-and-tools",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 game-ai-networking-and-tools",{"tool":40,"command":41},"bunx","bunx skills add the-vibey-project\u002Fvibey --skill game-ai-networking-and-tools",{"tool":43,"command":44},"pnpm","pnpm dlx skills add the-vibey-project\u002Fvibey --skill game-ai-networking-and-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fvideo-game-development\u002Fskills\u002Fgame-ai-networking-and-tools\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",[],[]]