AI Ml AI Skills

Create and manage messaging profiles with number pools, sticky sender, and geomatch features. Configure short codes for high-volume messaging. This skill provides Ruby SDK examples.

Implement the Strategy pattern with Symfony's tagged services for runtime algorithm selection and extensibility

Forces explicit reasoning before writing any code. Surfaces assumptions, manages confusion, and prevents hallucination by demanding clarity upfront.

Prove a concrete behavior, performance, UI, CLI, API, or memory claim with fresh baseline-versus-treatment evidence and one explicit verdict. Use when asked to verify, prove, compare before and after,…

When the user wants to plan, build, or optimize SMS or MMS marketing — including welcome flows, abandoned cart texts, post-purchase, win-back, promotional sends, or transactional/auth SMS. Also use…

Query OpenTargets for drug targets, disease associations, and therapeutic evidence. Use when user asks about drug targets, disease mechanisms, target validation, or drug-disease associations. Triggers…

Walks the user through Charlie Hills's AI Second Brain + Karpathy Wiki setup from the MarTech AI newsletter. Use whenever the user mentions building an AI second brain, the Karpathy wiki, organising…

Update the shipping address on an unfulfilled order before it ships.

Optimize a complete candidate context package by deduplicating, filtering, ordering, and allocating its token budget. Use when retrieved or assembled material is noisy or exceeds the useful context…

Wibi Style 官方视觉风格：把一张照片转换成怪趣波普涂鸦贴纸。适合人物、宠物、产品或道具主体清楚、动作和轮廓有记忆点的照片。适用于用户要求怪趣波普涂鸦贴纸，或明确调用 $quirky-pop-doodle-sticker 时。

Svelte 5 runes + SvelteKit adapter-static (SSG/SSR) patterns for hydration-safe state, store bridges, and reactivity that survives prerendering

Crypto wallet: balances, P&L, history. Swaps, transfers and withdrawals need Telegram approval. Use when the user asks about SwapWallet (swapwallet.app) or wants to check or use their own SwapWallet…

Create a self-contained cinematic narrated HTML story animation for a customer story, market-entry journey, product launch, campaign, or learning tutorial using the Story Studio editorial design…

Resolve a merge conflict in CHANGELOG.md by detecting the file's own convention (Keep a Changelog per-version sections, monthly sections, a single [Unreleased] bucket, or another format) and folding…

解释业绩指引上修、下修或维持不变的真实含义、可信度与影响链条。适用于管理层更新展望、财报后调预期、经营预警等场景。

hermes-mnemosyne — Configure, troubleshoot, and operate the Mnemosyne memory provider for Hermes Agent.

Use when designing visual motion systems, creating animation specifications, or when a designer needs guidance on crafting beautiful, meaningful movement.

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky…

创建专业的 PowerPoint 演示文稿。适用于根据主题、大纲、文档、数据或参考材料生成完整 .pptx；在新建演示文稿时参考上传PPTX 的视觉风格；也可基于材料或旧 PPT 内容重新生成一版演示文稿。

Apply Karpathy-style minimalism and anti-dependency principles to code and system design. Use this skill when the user wants to reduce dependencies, avoid supply chain risks, rewrite something in pure…

Query the WebMD Drug Reviews dataset (~362 k patient reviews, 2007–2020). Use whenever the user asks about patient-reported drug effectiveness, ease of use, satisfaction ratings, side effects, or…

Multi-tenant SaaS deployment on modern edge (Vercel, Cloudflare) / Deployment SaaS multi-tenant di edge modern (Vercel, Cloudflare).

Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up…

GTM Event Tracking & Setup Reference — dataLayer fundamentals, trigger types, variable types, GA4 tag configuration, debug mode, and best practices

Add voice & video calling to a Flutter app with the CometChat v6 UI Kit — turn calling on in settings, wire the native config and the root navigatorKey (the kit presents incoming/outgoing call screens…

Edge computing with Cloudflare Workers, Deno Deploy, Bun, Vercel Edge Functions, AWS Lambda@Edge, and edge databases (Turso, D1, DynamoDB Global Tables). Use when building low-latency edge…

Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use…

Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups,…

分步骤构建复杂对象。在对象有很多可选参数或构建步骤复杂时使用。

Work 2+ independent tasks in parallel when they share no state and have no sequential dependencies.

Use whenever someone is building, training, fine-tuning, or serving a generative AI / LLM workload on Amazon EKS — phrased as "GPU vs Trainium/Inferentia", "vLLM on EKS", "Ray Serve / KubeRay",…

Design LLM-as-judge rubrics, direct scores and pairwise comparisons. Use for judge models, evals, position bias and calibration against human labels.

Добавить управляемую форму к внешней обработке 1С

Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.

Apply the scGPT single-cell foundation model (Cui 2024) to annotate and embed cells — zero-shot and fine-tuned cell-type annotation, gene/cell embeddings, batch integration, and gene-regulatory /…

Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing…

Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy. Use when PR preparation or commit strategy is needed.

Write efficient ServiceNow GlideRecord queries — addQuery vs addEncodedQuery, setLimit, GlideAggregate for counts, avoiding N+1 in loops, query operators, and safe CRUD with workflow control.

Help recruiters and hiring managers design and run structured candidate assessments beyond interviews — skills tests, work samples, assessment centers, and scoring rubrics. Use when asked to design a…

Use this skill when a strategic solution has been approved and requires scaling across the organization. It applies the 0-1-10-100 framework to manage implementation phases and selects appropriate…

Detects infinite tool-call retry loops from deterministic errors and breaks them before they drain context or budget

Comprehensive security guide for Capacitor apps using Capsec scanner. Covers 63+ security rules across secrets, storage, network, authentication, cryptography, and platform-specific vulnerabilities.…

Compare competitor repositories using verified code and source evidence when technical competitive analysis or repository profiling is requested.

Apple FoundationModels framework for on-device LLM: text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.

Final-guarantee fallback for the find-CNetworkGameServerBase_ServiceQueue preprocessor. Recovers CNetworkGameServerBase_ServiceQueue in CS2 engine2.dll / libengine2.so when the LLM_DECOMPILE…

Enforces the non-happy paths every screen owes the user — loading/empty/error/content resolved in ONE switch over an AsyncValue or sealed view state, never an isLoading+error+data bool triple; a…

Teaches the experiential practice of courting creative inspiration, sustaining openness, creating conditions for breakthrough ideas, staying in creative mode continuously, harnessing spontaneity,…

Analyze agent extensions and generate self-contained HTML wiki reports with security audit and architecture diagrams. Use when asked to analyze, audit, or document a plugin. Triggers on GitHub plugin…

Use when building LLM applications with LangChain, implementing chains, agents, tools, memory, prompts, and retrieval systems. Includes best practices for prompt engineering, tool integration, and…

用户需要从可观察的外部信号推断隐藏的内部状态时激活;当需要评估某人或某系统的整体状态但无法直接检测内部时; 当多个外部信号互相矛盾需要综合判断时。 典型触发信号: 用户说"怎么看出来这个人状态怎么样""从表面现象怎么判断内在情况""几个信号互相矛盾该怎么判断"。 不适用于: 可以直接测量/检测的场景(有体检数据、有监控面板、有可量化的指标), 或只有一个信号源且无法交叉验证的情况。

当主要交付物是基于 R 的数据分析流程、科学结果、可复现数据产品、R Markdown/HTML 报告或论文级图表与解读时使用；即使流程中包含 `.R` 脚本和仅服务当前分析的辅助函数，也由本 Skill 主导。⚠️ 不适用：主要交付物是可独立复用的 R 函数、稳定公共 API、类或 R Package；这些任务使用 bensz-r-developer。也不用于仅渲染既有 Rmd…