搜索

搜索结果

1032 results for "ai coding"

msw-planning

msw-planning

33research-knowledge

MSW (MapleStory Worlds) game-planning mode — for BOTH starting a brand-new game from scratch AND continuing/resuming an in-progress prototype. Narrow the idea with guided questions, ground it in the MSW genre catalog (3 map types, ~180 core mechanic tags, build-effort hints), and produce or advance an implementation-ready GDD / roadmap (markdown). Trigger proactively (even without the word 'planning') whenever the user wants to decide WHAT to build, scope an MVP, or continue/resume a phased build — INCLUDING when a Docs/*-GDD.md or *-Phase*.md already exists and the user says to continue: do NOT treat that as plain implementation and jump straight into the phase doc; a continue/resume runs through this skill's resume flow first. Match triggers by intent, not exact wording — variants like 'what now?', 'where were we?', and their equivalents in ANY language fire it too. A comprehensive build request spanning multiple implementation pieces, made while no GDD exists, is ALSO a planning trigger — not a plain implementation request, with NO 'small/simple game' exception; implementing that without a plan is the exact failure mode this skill prevents. Triggers: 'plan a new game', 'GDD', 'what game should I make', 'scope an MVP', 'planning mode', 'continue my game', 'resume my game', 'what should I work on next', 'next task'. (Plans & manages the game's build across its milestones — GDD · standing milestone roadmap · phase plans · progress · revisions; does NOT write code — implementation (.mlua/.model etc.) uses msw-general/msw-scripting.)

msw-git avatarmsw-git
获取
msw-scripting

msw-scripting

32research-knowledge

Authoring MSW scripts (.mlua) plus integrated playtest and debugging. Covers mlua syntax, annotations (@Component/@Logic/@ExecSpace/@Sync), lifecycle, exec spaces, property sync, event system, file workflow, build-log inspection, error classification, and the test/debug loop. Keywords: script, mlua, lua, Component, Logic, annotation, ExecSpace, Sync, event, play, test, debug, lifecycle.

msw-git avatarmsw-git
获取
msw-ui-system

msw-ui-system

32design-ui

MSW `.ui` single entry point — design + component API + builder + runtime. Anchor/pivot/RectTransform, UIGroup/CanvasGroup hierarchy, layout recipes (HUD/popup/toast/menu/inventory/scroll-list), full API tables for ButtonComponent/TextGUIRendererComponent/SpriteGUIRendererComponent/ScrollLayoutGroup/GridView/TextInput/Slider/Mask/AvatarGUIRenderer + UI enums (AlignmentType/TextOverflowMode/ImageType/FillAmount), `.mlua` runtime patterns (popup open-close, toast, HP bar, GridView, drag, tab, cooldown, world nametag), UI-client-only caveats (nil on server, no RPC), `.ui`↔`.mlua` UUID auto-binding (write+injectBindings), resolution/safe-area/touch. UIBuilder (msw_ui_builder.cjs): all node types (empty/panel/text/sprite/button/slider/scrollLayout/textInput/group/mask/gridView/avatar/skeleton etc.), component add/replace/patch/remove, 13 anchor presets+stretch, auto-inject .mlua UUID bindings after write.

msw-git avatarmsw-git
获取
msw-painter

msw-painter

32writing-content

当 msw-search 找不到合适的精灵 RUID 时,直接用 SVG / HTML5 Canvas / HTML 代码绘制像素风格精灵,渲染为 PNG,并通过 msw-mcp 资源上传工具上传以获取精灵 RUID(如果未连接上传工具,则引导用户通过 Maker 注册)。支持两种风格模式:chunky pixel(复古/图标/瓦片风格)和 maple cartoon(冒险岛风格角色/NPC 风格)。触发词:直接绘制精灵、创建精灵、图像生成、自定义图形、像素艺术、卡通精灵、枫叶风格、Q版角色、画家、画精灵、制作图标、直接创建 NPC 图像、画史莱姆、自定义精灵。

msw-git avatarmsw-git
获取
msw-behaviourtree

msw-behaviourtree

32writing-content

Authors MSW `.behaviourtree` files end-to-end and maintains the project-specific authoring spec (`.behaviourDocs/bt-spec.md`). Scans every `.codeblock` whose paired `.mlua` extends `ActionNode`/`DecoratorNode`/`CompositeNode` to build a compact catalog of custom action/decorator/composite UUIDs, propertyKey names, and version-stamped MODNativeType strings. Then generates the full tree: RootNode → Nodes graph, Blackboard variables, nodeProperties wiring, and self-validates parent/child consistency. Triggers: 'create behaviourtree', 'new BT', 'add a behaviour tree', 'BT node graph', '비헤이비어 트리 만들어', '.behaviourtree 생성', 'SequenceNode SelectorNode', 'Blackboard variable', 'definitionId codeblock', 'startNodeId', 'build BT spec', 'refresh bt-spec', 'generate behaviourtree catalog', 'BT 스펙 생성', 'bt-spec.md 만들어', 'rescan BT nodes'.

msw-git avatarmsw-git
获取
twill-cloud-coding-agent

twill-cloud-coding-agent

9agent-workflows

Use Twill Cloud Coding Agent to manage Twill's public v1 API workflows. Create/list/update tasks, stream and cancel jobs, manage scheduled tasks, list repositories, and export Claude teleport sessions.

twillai avatartwillai
获取
coding-agent

coding-agent

386Kagent-workflows

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

openclaw avataropenclaw
获取
coding-agent

coding-agent

384Kagent-workflows

将编码工作委托给 Codex、Claude Code 或 OpenCode 作为后台工作进程;不用于简单编辑或只读代码查询。

steipete avatarsteipete
获取
inherit-legacy-style

inherit-legacy-style

240Kresearch-knowledge

Legacy-project style inheritance skill. Use when the user types /inherit-legacy-style, or when onboarding an AI coding agent onto a hand-written legacy project and you need to prevent "style drift" (the model imposing its pretrained mainstream idioms onto the project). Language- and framework-agnostic — it aligns meta-architecture only, not syntax. Once run, it becomes a behavioral constraint on all subsequent coding tasks. Do NOT use for pure research or one-off questions unrelated to code-style alignment.

affaan-m avataraffaan-m
获取
flox-environments

flox-environments

240Kbackend-api

Create reproducible, cross-platform (macOS/Linux) development environments with Flox, a declarative Nix-based environment manager. Use when setting up project toolchains for any language, installing system-level dependencies (compilers, databases, native libs like openssl/BLAS), pinning exact package versions for a team, running local services (PostgreSQL, Redis, Kafka), onboarding developers with one command, or solving 'works on my machine' problems — including agent/vibe-coding setups that need project-scoped tools without sudo. Also use when the user mentions .flox/, manifest.toml, flox activate, or FloxHub.

affaan-m avataraffaan-m
获取
agent-eval

agent-eval

239Kagent-workflows

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

affaan-m avataraffaan-m
获取
claude-devfleet

claude-devfleet

239Kagent-workflows

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

affaan-m avataraffaan-m
获取
coding-standards

coding-standards

239Kcode-generation

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.

affaan-m avataraffaan-m
获取
java-coding-standards

java-coding-standards

239Ktesting-qa

Java coding standards for Spring Boot and Quarkus services: naming, immutability, Optional usage, streams, exceptions, generics, CDI, reactive patterns, and project layout. Automatically applies framework-specific conventions.

affaan-m avataraffaan-m
获取
cpp-coding-standards

cpp-coding-standards

239Kcode-generation

C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.

affaan-m avataraffaan-m
获取
search-first

search-first

239Kresearch-knowledge

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.

affaan-m avataraffaan-m
获取
flox-environments

flox-environments

237Kbackend-api

使用 Flox 打造可复现、跨平台(macOS/Linux)的开发环境。Flox 是一款基于 Nix 的声明式环境管理工具。适用于为任意语言搭建项目工具链、安装系统级依赖(编译器、数据库、openssl/BLAS 等底层原生库)、锁定团队统一的软件包版本、运行本地服务(PostgreSQL、Redis、Kafka)、一键完成新成员入职环境配置,或解决“在我电脑上明明能跑”的经典坑——也包括不需要 sudo 权限就能在项目作用域下安装所需工具的 AI Agent / vibe coding 场景。当用户提及 .flox/、manifest.toml、flox activate 或 FloxHub 时同样适用。

affaan-m avataraffaan-m
获取
subagent-driven-development

subagent-driven-development

233Ktesting-qa

在当前会话中执行包含独立任务的实施计划时使用

obra avatarobra
获取
verification-before-completion

verification-before-completion

233Ktesting-qa

在声称工作已完成、已修复或通过之前,在提交或创建PR时使用——要求运行验证命令并确认输出后再做出任何成功声明;始终先有证据再断言

obra avatarobra
获取
receiving-code-review

receiving-code-review

233Kcode-generation

用于接收代码审查反馈时,在实施建议之前,特别是当反馈看起来不明确或技术上可疑时——需要技术严谨性和验证,而非表演性同意或盲目实施

obra avatarobra
获取
writing-skills

writing-skills

233Kresearch-knowledge

当需要创建新技能、编辑现有技能或在部署前验证技能是否正常工作时使用

obra avatarobra
获取
dispatching-parallel-agents

dispatching-parallel-agents

233Ktesting-qa

当面临两个或更多独立任务且这些任务无需共享状态或顺序依赖时使用

obra avatarobra
获取
finishing-a-development-branch

finishing-a-development-branch

233Ktesting-qa

当实现完成、所有测试通过,且需要决定如何整合工作时使用——通过提供合并、PR或清理的结构化选项来指导开发工作的完成

obra avatarobra
获取
using-git-worktrees

using-git-worktrees

233Ktesting-qa

在开始需要与当前工作区隔离的功能开发或执行实施计划之前使用——确保通过原生工具或git worktree回退方式存在隔离的工作区

obra avatarobra
获取