所有 Skills
找到 8642 个 Skills
Skills 列表
fxmacrodata-calendar
Fetch official FXMacroData macro release-calendar events for trade planning, macro regime checks, and event-risk filters. Use before CPI, NFP, GDP, PCE, retail sales, PMI, and central-bank decision windows.
tradermonty
serve-sim
Control and stream a running iOS, iPad, or Apple Watch Simulator with npx serve-sim. Use for simulator preview, taps, gestures, hardware buttons, rotation, camera injection, permissions, accessibility, and CoreAnimation debug.
evanbaconcrypto-regime-analyzer
Quantifies crypto market regime health using free, keyless public data (CoinGecko + Binance funding). Generates a 0-100 composite score across 6 components (100 = risk-on) with a posture recommendation. No API key required. Use when user asks about crypto market conditions, whether it's alt season, BTC dominance, crypto risk-on vs risk-off, funding rates, or whether crypto exposure should be increased or reduced.
tradermontycot-contrarian-detector
Detect crowded speculative positioning in CFTC futures markets (COT report analysis) to find contrarian setups using Jason Shapiro's methodology. Screens large-speculator ("non-commercial") net positioning across 65 futures markets (indices, rates, FX, metals, energy, crypto) via the FMP Commitment of Traders API, computes a 3-year and 26-week COT Index per market, and classifies extremes as CROWDED_LONG / CROWDED_SHORT. Use when the user asks about COT report analysis, crowded positioning, "who is trapped", speculative positioning extremes, contrarian futures setups, or wants to run Jason Shapiro-style analysis. This skill automates crowding DETECTION only (step 1 of 5) — it does not generate trade signals by itself.
tradermontynews-reaction-failure-analyzer
Judge whether a market FAILED to react to news favorable to a crowded speculative position — step 2 of Jason Shapiro's COT contrarian process. Consumes a cot-contrarian-detector report (or an explicit direction) plus a Claude-curated events JSON, fetches the underlying price series with a documented fallback chain, and produces a fail-closed CONFIRMED / NOT_CONFIRMED / INSUFFICIENT_EVIDENCE verdict using a statistically validated drift-significance test (not a naive failure-ratio, which false-confirms on pure noise). Generic beyond COT — reusable for PEAD and macro-crowding news-failure checks. Use when the user asks to check news-failure confirmation, whether a crowded market "shrugged off" good/bad news, or wants to run Shapiro step 2 on a CROWDED_LONG/CROWDED_SHORT market.
tradermontyfutures-position-sizer
Calculate contract-based futures position sizes from a direction, entry, and stop-loss, using verified per-symbol contract specs (multiplier, tick size, tick value). Use when the user asks how many futures contracts to trade, wants to size a futures position (ES, NQ, ZB, GC, CL, 6E/E6, VX, BT, ...), or is handing off a contrarian-setup-gate READY_FOR_PLAN direction/invalidation_level for sizing. Pure, offline calculation -- no API keys, no network.
tradermonty
domain-authority-auditor
Use when auditing domain authority, trust, or citation credibility; runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks. Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer. 域名权威/网站可信度
aaron-he-zhu
dart-run-static-analysis
通过运行 `dart analyze` 来排查代码中的警告和错误，并使用 `dart fix --apply` 自动修复机械式的 lint 问题。建议在日常开发以及提交代码（commit）前使用，以确保代码质量。
flutterdart-fix-runtime-errors
利用 get_runtime_errors 与 lsp 获取实时堆栈信息，定位出错代码行并完成修复，最后通过 hot_reload 验证修复结果。
flutterdart-add-unit-test
使用 `package:test` 为函数、方法和类编写并组织单元测试。适用于开发新逻辑或修复 Bug 时，确保代码正确性并防止引入回归问题。
flutterdart-resolve-package-conflicts
修复依赖包版本冲突的操作流程。当由于包版本不兼容导致 `pub get` 报错失败时使用。
flutterdart-collect-coverage
使用 coverage 包收集测试覆盖率数据并生成 LCOV 报告
flutterdart-generate-test-mocks
使用 `package:mockito` 和 `build_runner` 为外部依赖定义并生成 Mock 对象。适用于对依赖 API、数据库等复杂外部服务的类进行单元测试的场景。
flutterdart-use-pattern-matching
在合适场景下使用 switch 表达式与模式匹配（pattern matching）。
flutterdart-use-primary-constructors
帮助用户在 Dart 中编写语法与语义正确的主构造函数（Primary Constructors），并迁移或使用全新的构造函数语法、空体分号语法、类体内初始化列表语法以及简写/精简构造函数语法。
flutterdart-migrate-to-checks-package
将 Dart 测试代码中来自旧版 `package:matcher` 的 `expect` 及相关断言函数，重构迁移为现代、类型安全的 `package:checks` 等效写法。
flutterdart-use-ffigen
指导 Agent 使用 `package:ffigen` 自动生成 FFI 绑定，而非手动编写。当任务涉及编写新的 FFI 绑定、扩展 C/Objective-C/Swift 集成，或替换手写的 `dart:ffi` 配置时，请使用此 Skill。
flutterdart-setup-ffi-assets
指导 Agent 使用 Dart 的 Native Assets Hook 机制（通过 `hook/build.dart` 与 `hook/link.dart`，结合 `package:hooks` 和 `package:native_toolchain_c`），将 C/C++ 源码编译并打包为动态库或静态库（Code Assets）。当用户提出以下需求时使用：“配置 native assets”、“编译 C/C++ 源码”、“打包动态库”、“构建原生 C 代码”、“链接 native assets”、“实现 build.dart 或 link.dart hook”或“在 Dart/Flutter 中集成 C/C++ 互操作”。帮助 Agent 摆脱手动编排编译工具链的繁琐流程，并支持安全且经过哈希校验的预编译二进制下载，或者通过 `package:record_use` 映射实现高级链接器 Tree-Shaking 优化。
flutterdart-build-cli-app
入口结构、退出码规范及跨平台脚本实现。适用于开发 Dart 命令行工具（CLI）、脚本或终端应用。
flutter
cudaq-guide
CUDA-Q 入门指南，涵盖环境安装、测试程序编写、GPU 加速仿真、QPU 硬件对接以及量子应用开发。
nvidiacuopt-install
通过 pip、conda 或 Docker 安装适用于 Python、C 或服务器端的 cuOpt，并进行安装验证。如需从源码构建 cuOpt，请参阅 cuopt-developer。
nvidia
sega
A playful, arcade-inspired interface for games — built on the VT323 pixel typeface, hard-edged 0px corners, chunky pill buttons that physically press into solid offset blocks
bergside
baoyu-design
以独立单文件 HTML 形式创建精致的设计产物：UI 高保真设计图、交互原型、线框图、落地页（Landing Page）、仪表盘、应用界面、移动端界面、演示文稿（即 PPT / PowerPoint 幻灯片）以及视觉探索稿。只要用户提出对界面、产品屏幕、用户流程、内容布局、视觉产物或 Pitch 演示概念进行设计、原型制作、绘制线框图、可视化、探索或制作 PPT/幻灯片（即使对方没直接提到“设计”一词），即可触发此 Skill。此外，还可将本 Skill 制作的演示文稿导出为 PowerPoint 格式（PPT/PPTX）——注意：仅支持导出在本工具中生成的幻灯片（即 deck-stage 或本 Skill 规范的幻灯片结构 HTML），不支持任意通用 HTML，使用前请先确认目标产物是否符合要求。同时支持搭建、导入或编写可复用的设计系统（Design System）、UI 组件库（UI Kits）、品牌 Token（Brand Tokens）或组件库。通用兼容 Claude Code、Cursor、Codex Agent 等支持文件操作的 Agent 环境。
jimliustockbee-episodic-pivot-analyzer
Analyze Stockbee-style Day 1 Episodic Pivot candidates from earnings, guidance raises, M&A, FDA/regulatory approvals, analyst actions, major contracts, product launches, short-squeeze catalysts, or theme/story events. Scores catalyst quality together with gap/range expansion, volume shock, neglect/revaluation context, liquidity, and risk to the EP-day low. Use when the user asks for EP candidates, episodic pivots, Day 1 catalyst trades, game-changing news reactions, delayed EP watchlists, or handoffs into PEAD monitoring.
tradermonty