Recently Added

kotor-toolset

by Recoson

Engineering conventions, data model, and workflow for a Star Wars KOTOR-era tabletop RPG toolset built on a custom GURPS 4th Edition ruleset. Use this whenever working on any of the campaign HTML tools — the character sheet (sheet.html), the galaxy map (galaxy-map.html), the galactic-record companion, the GM console (KOTOR_GM_Console_v4.html), or the combat cheatsheet — or when editing campaign data such as the global C character object, Force powers, weapons / armour / shields, skills / traits, the credits system, or anything grounded in the compendium ("Star Wars the Old Republic GURPS 4E conversion.html"). Apply it for ANY edit, bugfix, feature, data conversion, JSON import, or test on these files, even when the request doesn't name the conventions explicitly, so the compendium-first rule, the point-cost data model, the exact trait-naming catalog, and the Python → node --check → Playwright → push workflow are followed consistently and silent failures are avoided.

dfc-customer-sync

by damienchen0624-spec

巨懂车客户自动同步到大风车。后台守护进程每 10 分钟从巨懂车后台抓取新留资客户, 手机号去重后写入大风车客户列表。当用户说"同步巨懂车客户"、"巨懂车留资同步大风车"、 "启动客户同步"时使用。

ai-tech-lead

by mkfire

Use when starting a new software project, initializing project docs, clarifying requirements, designing features before coding, guiding Codex implementation, or reviewing AI-generated code. This skill acts as an Engineering Manager: it should not trigger for tiny one-line edits unless the user asks for process, planning, or review.

qianchuan-ad-creative-workflow

by Ethan37358

Create Qianchuan/Douyin ad creative workflows for ecommerce and livestream conversion. Use when the user wants 千川投放素材, 巨量千川创意, 抖音广告口播, 直播间引流脚本, 商品卡成交素材, ad script matrices, storyboard/material plans, compliance-aware口播 variants,素材采集 planning, batch video production planning, or post-campaign creative iteration from CTR/CVR/ROI data.

viva

by jacquardlabs

Section-by-section markdown review. Human signs off on every section; agent rewrites and loops until all approved.

blackbox-hunter

by jinbaozi

AI-assisted black-box vulnerability scanning for rpm/deb packages using Track A tools and Track B AI binary analysis.

sage-router

by earlvanze

Local-first AI model routing for serious agents. One endpoint. Any provider. The router figures out the rest.

Wedding-invitation

by yamenAl

Skill: Live code verification with Purr Verify MCP

by 0xheycat

Verified = status: "success" and cleanupStatus: "done" and every command exitCode: 0.

xfactor

by generalizingai

"Use when the user wants to grow their X account with AI-powered content, engagement, and analytics. Full X growth engine: research-first posting, automated likes/follows, and live dashboard."

AI4BayesCode

by zjg540066169

Build Bayesian MCMC samplers with AI4BayesCode — a header-only C++ library of composable, stateful block-wise MCMC kernels (Gibbs / NUTS / slice / ESS / VI / BART / GP / HMM / particle-Gibbs / RJMCMC / ...). Use when the user wants to (a) GENERATE a sampler for a Bayesian model by composing existing blocks, or (b) DESIGN a brand-new sampler block primitive for the library. Triggers: "I want a sampler for <model>", "compose / generate an MCMC sampler", "design a new block", a model written as y ~ ... with priors, or any AI4BayesCode request.

setup-brain

by mycelium-hq

Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.

paper-outline-generator

by c3115644151

基于50篇跨学科真实论文（物理学/计算机/经济学/医学/人文学科）的章节树研究结果，生成符合学科结构规范的研究论文大纲。当用户需要生成论文大纲、设计文章结构、规划章节组织、验证大纲合理性、从研究想法生成结构框架时使用此技能。也适用于用户提出研究想法、需要结构化、写论文框架、想看看怎么写等场景。

thrive-desk-research

by thrive-incubator

Thrive Studio Stage 1 desk research on a venture idea. Asks scope questions, then writes a 1-2 page decision brief and a 5-10 page report on market size, competitors, risks, and studio fit — with a scored gate scorecard, a granular Thrive-alignment sub-score, and a 5-star idea rating, delivered as Markdown and Word.

SKILL.md — 이동됨 (정본: docs/technical/SKILL.md)

by pyorocop-lang

(단일 정본 유지를 위해 루트 사본을 포인터로 대체)

idapt-api

by idapt

Use the idapt REST API to manage chats, agents, workspaces, Drive (cloud files), images, speech, web search, triggers, code execution, notifications, and more programmatically.

shared-skill-installer

by SnooZou

Install, migrate, verify, refresh, or document local and open-source skills into one shared library, then expose them to multiple local AI clients through symlinks. Invoke when the user wants one skill library shared by Codex, WorkBuddy, TRAE, or similar clients.

awwwards-portfolio

by eng0ai

Award-winning portfolio template with Locomotive Scroll, GSAP, and Framer Motion animations. Use when the user wants to scaffold a new portfolio or landing page project.

games

by alpibrusl

"Invoke the games CLI to verify, export, and rank Lex arena game trails. Commands: verify, export, leaderboard, season. Use when you need to recompute the authoritative score of a recorded game from its trail, rank a field of policy rollouts, or update an ELO season — all from trails, never trusting a client-reported score."

gitmoot

by jerryfane

Use Gitmoot for local-first AI agent coordination across repositories, goals, reviews, PR comments, daemon jobs, stuck jobs, branch locks, agent templates, template capture and publish/pull, custom prompt agents, orchestration, heartbeats, event webhooks, the web dashboard, and Codex, Claude Code, or Kimi Code runtime workflows.

MarketAnalysis

by Mftrferdinand

"Format chat AI agent untuk analisis market lengkap dan akurat. Astronacci + Fibonacci, structured live chat format, consistent entries with tight risk management (TP/SL). Companion: TradeDataTracker for TP/SL logging. For all markets."

brand-strategy-guide

by DevinKuang

品牌全案策略指南 — 基于《品牌全案策略指南2.0》知识体系，通过深度对话式信息收集， 自动生成包含市场调研、战略定位、战略执行三阶段的完整品牌全案方案。 三种工作模式： - 标准模式：3 阶段深度对话（信息收集→战略定位提问→执行校验提问）→ 内容生成 → 格式化输出 - brief 模式（推荐深度方案）：用户填写 Word 问卷（output/brief_questionnaire.docx）→ skill 读取 Word 提取信息 → 3 个 Agent 分工生成（验证→市场研究→策略定位→执行规划）→ 合并 → 格式化输出。适合需要 80+ 页深度方案的场景。 - MD 输出模式（内容与排版解耦）：策略内容生成 → 结构化 MD brief 交付（非散文，精确到每页标题/数据/图表/案例）→ 用户审阅确认后，单独使用 guizang-ppt-skill 或 ppt-master 将 MD 转为可视化成品。适合 80-100+ 页大型方案，避免策略内容与排版代码在同一上下文窗口中互相挤占。 用途：输入行业、品牌、产品、团队等基本信息，通过三阶段深度对话（信息收集→战略定位提问→执行校验提问）， 生成包含市场调研、战略定位、战略执行的完整品牌全案方案。每个关键策略判断必有案例佐证。 输出格式：HTML（调用 guizang-ppt-skill）或 PPTX（调用 ppt-master），或结构化 MD brief（MD 输出模式，供下游排版 skill 使用）。禁止输出非结构化散文式 MD 作为最终交付物。 触发词：「做品牌全案」「品牌策略」「品牌方案」「帮我做个品牌定位」「新品牌怎么做」 「品牌战略规划」「生成品牌全案」「帮我做品牌策划」「打造品牌」。 English triggers: "brand strategy", "brand positioning", "brand plan", "create a brand", "brand blueprint", "how to build a brand", "brand consulting". DO NOT activate for: 纯设计需求（logo设计用 logo-generator）、已完成的品牌方案修改、 纯市场调研不涉及策略生成、翻译任务。

tk-vn-product-sheet-skill

by 23xxCh

Process TikTok cross-border e-commerce spreadsheets for Vietnam site: translate Chinese titles/variants to Vietnamese (de-branded, ≤80 chars), set brand→Generic N/A, stock→30, regenerate SKU, clear video links. Pre-screen product images via vision LLM → only send images containing brand/logo/watermark/text to Doubao Seedream 5.0 (2K) or GPT-Image-2 for cleaning (remove brand/logo/watermark + translate text to Vietnamese). All URL→API→URL — no local file downloads needed. Triggers: tk越南站表格, tiktok产品表, 电商表格翻译越南语, 产品图去logo水印, 跨境电商数据清洗.

RouteVideo Remotion Skill

by Equilibriumpress

Route still uses GeoJSON [lon, lat] coordinates.