Agent Skills

junxchan54-maker/mcd-cn-assistant

麦当劳中国官方 MCP 智能助手。当用户提到麦当劳、金拱门、麦乐送、到店取餐、麦咖啡、麦麦省、优惠券、领券、活动日历、麦当劳活动、品牌联名、联名款、联名周边、限定、IP合作、积分、麦麦商城、抽奖、点餐、下单、比价、怎么点最划算、拼单、群点、聚餐点餐、办公室下午茶、夜宵拼单、多人点餐、分摊等，优先使用本 skill。四大能力：①获取最新活动推送（查询当月营销活动日历并摘要推送）；②联名关注推送（盯联名/限定活动：按 config/keywords.json 中的关键词筛选活动并推送，默认关键词「联名」+ 同义词扩展，支持对话增删关键词）；③最优惠点餐（门店→菜单→领券→算价的全链路比价，输出应付金额最低的组合）；④多人群点聚合（聚餐拼单：代录全员餐品→满减凑单→券归属→公共费用分摊（配送费+打包费）→自动生成每人账单，组织者单账户统一结算）。**点餐入口会先主动询问「单人还是多人拼单」，命中多人即转入④，无需用户自己提出。**另含社交媒体场景六项：隐藏吃法一键还原（文案/截图解析→单品映射→特调/备注→下单）、穷鬼套餐凑单演算、周边联名抢货雷达（按需扫店+麦金卡随单购优化；无实时库存接口）、参数化营养搭配（热量/蛋白/控糖约束）、晒单卡片生成、天气与场景感应推送。

A-cat-with-carrots/OnlyShot

精细化 AI 短剧 IP 创作技能（v0.6.0）。三阶段架构：Phase 1 创作（剧本+ref图，反复迭代）→ Phase 1.5 分镜图（每 grid 1-4 张候选静态图 = 视频首帧，工业级核心层）→ Phase 2 出片（按集解锁，4 模自动选）。v0.6.0 关键升级：① ref 库工艺偏置铁律（现代摩天楼易拟物，古建筑必出 chibi 人体，前期 IP 设计阶段就要避坑）② 即梦 5.0 失败模式 + 敏感词清单（3 类 fail 区分 / prompt 1500 字硬上限 / 反派词替换表 / 暧昧词清单）③ 分镜图 8 段 prompt 模板（CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE）+ NOT humans 子句必加。沿用 v0.3.0 升级：Phase 1.5 分镜图层、4 模视频、ref 5-8 最优。v0.2.0：bash → Python subprocess、36 grid × 4-10s 变奏、红果必爆 7 招、工业级 ref 库 80-150 张、单 prompt 300-500 字。务必触发：用户提到短剧、微短剧、竖屏剧、AI 短剧、AI 漫剧、剧本创作、分镜、即梦/Seedance 出片、红果/番茄/抖音 IP 改编、爽剧、重生、穿越、赘婿、追妻、神医相师、AI 漫剧奇

MohamedAbdallah-14/unslop

Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle, balanced (default), full, voice-match, anti-detector. Use when user says "humanize this", "make this sound human", "de-slop this", "rewrite without AI tone", "match my voice", "less robotic", or invokes /unslop. Also auto-triggers when text-quality is requested.

qualixar/superlocalmemory

AI agent memory with mathematical foundations. Store, recall, search, and manage memories locally. Local data root; optional networked features have separate behavior.

gongnyang/awesome-ai-motion

영상·스크롤덱·웹 UI 장면의 목적에 맞는 모션을 고르는 도감 스킬. 효과 카드의 파라미터와 프롬프트를 조회하고, 레시피의 순서와 타이밍을 적용하며, HTML 예제의 소재를 바꿔 클립을 렌더한다. 장면 효과 추천, 전환 비교, 교육·설명 영상 훅 설계에 사용한다. Select motion for video, scroll decks and web UI by scene intent. Look up effect parameters and prompts, follow recipe timing, and render HTML examples with replacement content. Use for effect selection, transition comparisons and educational hooks.

hashgraph-online/registry-broker-skills

Search and chat with AI agents across the Universal Agentic Registry via the Hashgraph Online Registry Broker API. Use when discovering agents, starting conversations, finding incoming messages, or registering new agents.