AI & ML

flonat Skill

Run an interactive one-question-at-a-time oral drill for research defence or active-recall study, escalating around weak answers and ending with a study sheet. Use when the user asks to be grilled, quizzed, or prepared for a viva, job talk, seminar, or exam. Not for a written critique; use $devils-advocate or a review agent.

flonat Bundle

Guide for creating MCP servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

githubnext Skill

Safely manage multiple GitHub identities (EMU + personal) in agent workflows

flonat Bundle

Design or audit the identification strategy for an observational study. Use when the task concerns estimands, causal assumptions, threats to identification, or defensible research design rather than model implementation.

vanman2024 Bundle

Performance optimization patterns for Mem0 memory operations including query optimization, caching strategies, embedding efficiency, database tuning, batch operations, and cost reduction for both Platform and OSS deployments. Use when optimizing memory performance, reducing costs, improving query speed, implementing caching, tuning database performance, analyzing bottlenecks, or when user mentions memory optimization, performance tuning, cost reduction, slow queries, caching, or Mem0 optimization.

vanman2024 Bundle

Production-ready database schema patterns for AI applications including chat/conversation schemas, RAG document storage with pgvector, multi-tenant organization models, user management, and AI usage tracking. Use when building AI applications, creating database schemas, setting up chat systems, implementing RAG, designing multi-tenant databases, or when user mentions supabase schemas, chat database, RAG storage, pgvector, embeddings, conversation history, or AI application database.

flonat Bundle

Adversarially challenge research assumptions, mechanisms, and arguments in writing. Use when stress-testing a claim or design before committing to it. Not for an interactive oral drill or a full referee report; use $grill-me or a review agent.

vanman2024 Bundle

DeepEval pytest-style LLM testing patterns with built-in metrics, custom evaluators, and CI integration. Use when creating LLM tests, evaluating RAG quality, or measuring faithfulness/relevance.

vanman2024 Bundle

promptfoo configuration patterns for prompt regression testing, multi-provider comparison, and assertion-based validation. Use when setting up prompt testing, comparing LLM providers, or creating eval pipelines.

vanman2024 Bundle

Training monitoring dashboard setup with TensorBoard and Weights & Biases (WandB) including real-time metrics tracking, experiment comparison, hyperparameter visualization, and integration patterns. Use when setting up training monitoring, tracking experiments, visualizing metrics, comparing model runs, or when user mentions TensorBoard, WandB, training metrics, experiment tracking, or monitoring dashboard.

vanman2024 Bundle

Agentic Platform Contract tables for AI agent applications - runs, events, artifacts, and tool calls tracking. Use when building AI agent backends that need structured run/event storage.

vanman2024 Bundle

RAG (Retrieval Augmented Generation) implementation patterns including document chunking, embedding generation, vector database integration, semantic search, and RAG pipelines. Use when building RAG systems, implementing semantic search, creating knowledge bases, or when user mentions RAG, embeddings, vector database, retrieval, document chunking, or knowledge retrieval.

vanman2024 Bundle

Deep reasoning with Claude's extended thinking feature for complex multi-step problems. Use when implementing think-aloud reasoning, complex analysis, or debugging difficult issues.

flonat Skill

Identify recurring weak arguments, unsupported assumptions, and vulnerable inference patterns across a literature corpus. Use when stress-testing a body of work rather than reviewing one manuscript. For one paper's argument, use the appropriate paper-review workflow.

amo-tech-ai-rocket-path-ai Skill

Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. **Trigger when user asks to:** - Store or search vector embeddings in PostgreSQL - Set up semantic search, similarity search, or nearest neighbor search - Create HNSW or IVFFlat indexes for vectors - Implement RAG (Retrieval Augmented Generation) with PostgreSQL - Optimize pgvector performance, recall, or memory usage - Use binary quantization for large vector datasets **Keywords:** pgvector, embeddings, semantic search, vector similarity, HNSW, IVFFlat, halfvec, cosine distance, nearest neighbor, RAG, LLM, AI search Covers: halfvec storage, HNSW index configuration (m, ef_construction, ef_search), quantization strategies, filtered search, bulk loading, and performance tuning. **This project:** We use OpenAI text-embedding-3-small (1536) and store as vector(1536) in knowledge_chunks. halfvec is an optional future optimization; apply this skill's tuning (ef_search, iterative_scan, et

dmzoneill Skill

Deep scan of project structure to update architecture knowledge. Uses semantic code search for API, model, error, and test patterns. Use to bootstrap or refresh project knowledge.

zephyrwang6 Bundle

agent-im 会话技能 - 通过 OpenAPI 创建会话、发送生图/生视频等消息、上传图片/视频文件，并查询会话进展。当用户需要生图、生视频、上传文件或查询当前会话消息时激活此技能。

dmzoneill Skill

Manage workflow daemon services - MCP, SLOP, Slack, Ollama, Scheduler. Start, stop, restart, status. Use when user says "start MCP", "restart slack daemon", "service status".

dmzoneill Skill

Test and benchmark local Ollama inference - status, test, benchmark. Check model availability, run generation/classification tests, measure response time. Use when user says "test Ollama", "Ollama status", "benchmark inference".

communitytoolkit Skill

Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn

communitytoolkit Skill

Determines which LLM model to use for each agent spawn

microsoft Skill

Adds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector (shared_a365copilotchatmcp), then wires up a production-ready McpSession wrapper for AI-powered, knowledge-grounded search and chat. Use when integrating Microsoft 365 Copilot search/chat. The CopilotChat tool searches internal Microsoft 365 content (documents, emails, chats, sites, files) across your organization — prefer workload-specific tools (SharePoint, OneDrive, Teams, Mail) when the workload is explicit; do not use it for general knowledge, news, public web, or external information.

microsoft Skill

Use when the user wants to iterate on an existing generated Power Apps mobile app after /create-mobile-app: update the plan, data model, native capabilities, design, screens, generated app code, and preview without restarting the full project flow.

bankrbot Bundle

Makes an agent crypto-native for onchain capital markets. Use for ANY question about DeFi, vaults, curators, yield, stablecoins, synthetic dollars, RWAs (real world assets), tokenized stocks, lending, perps, options, LP positions, or onchain credit. Trigger for learning ("what is a covered call", "explain post-only"), due diligence ("assess this vault", "is this APY sustainable"), trade anatomy ("what is this fund actually short"), curator comparisons, fee rails ("where does my gas fee go"), RWA mint and redeem mechanics ("is this tokenized APY real"), squeezes and manipulation ("is this a short squeeze", "is this wash traded"), crowding ("conviction or a crowded exit"), DeFi content tasks, and monitoring ("what changed this week", "they changed their Terms of Use"). Trigger even without the word DeFi when the subject is onchain yield, crypto tokens, rates, or market structure. Refresh live data before anything numeric. Not for TradFi-only rates or credit questions, LLM tokens, or transaction execution.

dmzoneill Skill

Test variant of multi-agent PR review. Runs architecture (Claude) and security (Gemini) agents with basic prompts. Does not post to MR by default. Use for testing agent availability.

dmzoneill Skill

Run AI evaluation on quarterly performance questions. Gathers evidence from daily events, builds prompt with competency context, generates summary via LLM, saves to question. Use when user says "evaluate questions" or "AI performance summary".

mashharuki Bundle

WebMCP(Webページ自身がブラウザ内AIエージェントに「ツール」を公開するW3C Web Machine Learning Community Groupのドラフト仕様。navigator.modelContext / document.modelContext 経由の registerTool API)の設計・実装・セキュリティレビュー・テストを網羅的に支援する。ユーザーが「WebMCPを使いたい」「Webページ内のAI Agent向けツールを実装したい」「ブラウザのAIエージェント(Chrome組み込みAI、ChatGPTのSite tools、Model Context Tool Inspector等)にフォーム入力・検索・カート追加などページ内操作をさせたい」「registerTool/provideContext/useWebMCPを書きたい」「chrome://flags#webmcp-for-testingを有効にしたい」「Web MCPとMCP(サーバー側)の違いを知りたい」などと言った場合は必ず使うこと。「WebMCP」という単語を出さなくても、既存のWebアプリをブラウザ内AIエージェントから安全に操作可能にしたい、DOM操作やスクリーンショットに頼らずページの機能をAIに公開したい、といった意図が見えたら積極的に使う。仕様は現在も激しく変化し続けているドラフト段階のため、コードを書く前に必ず一次情報を再確認する運用も併せて提供する。

microsoft Skill

(Preview) Builds and edits a model-driven Power Apps app from a natural-language intent — tables, columns, relationships, adaptive forms with sub-grids, views, Choice-column charts, business rules, business process flows, generative page intents for overview/dashboard surfaces (page `.tsx` generated in generate-pages after plan approval), and an app module + sitemap — via the headless cds-maker-sdk. Runs an interactive, multi-turn authoring flow (env selection, jobs-to-be-done first, then design-only App Spec authoring across confirmed levels, guardrail lint, plan-mode approval, generate-pages, full build) and a narrated build, and can download a deployed app back into an editable spec to change it. Use when the user says "build an app for X", "create a model-driven app", "make me an app to manage Y", "add a business process flow", or "edit/add to my app". This skill stands alone and does not require /genpage — but for a standalone generative page added to an app that already exists, use /genpage instead.

microsoft Skill

Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.

huytieu Bundle

CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.

huytieu Skill

Run a large, multi-session goal (e.g. shipping a whole side product) through the full V-model closed loop, one phase at a time, with cross-session state and a final north-star acceptance gate. Ultragoals never downgrade the lane: every phase runs CP-1→CP-6 with adversarial verification. Opt-in: invoke with /ultragoal or by calling something a long-running goal. Ordinary work does not run this.

bankrbot Bundle

Fund OpenCAP inference from Capminal with staked CAPU on Base. Buy or mint CAPU, stake it for daily inference credit, create a wallet-owned OpenCAP API key through Ethereum sign-in, check quota, and recover or rotate the key. Use when the user wants CAPU-funded AI compute or OpenCAP key setup; Capminal trading-wallet credentials and Harness account management are separate workflows.

microsoft Bundle

Integrates Power Pages generative-AI summarization APIs (PREVIEW) into a Single Page Application (SPA) site — the Search Summary API and the Data Summarization API — on any record-detail or list page. Generates per-target service code (CSRF-handled) and AI site settings; delegates Web API settings, table permissions, and web roles to `/integrate-webapi` and `/create-webroles`. Use whenever a user wants AI/Copilot output that condenses Dataverse content on a Power Pages site — an AI summary, AI-generated overview or "key insights" across a record or list, a search-results summary, a case/incident summary, or recommendation-chip refinement — even when phrased as "AI-generated paragraph", "insights", or "overview". Do NOT use for: generative pages in model-driven apps (use the model-apps `genpage` skill), Copilot Studio agents/chatbots, summarizing documents or PDFs, Power BI dashboards, plain keyword search with no AI summary, or plain Dataverse CRUD (use `/integrate-webapi`).

microsoft Bundle

Inspects and configures the security headers a Power Pages site sends to browsers — Content Security Policy, frame and clickjacking protection, cross-origin sharing, cookie behavior, and related site settings. Identifies gaps and walks the user through fixes. Use when the user wants to review headers, fix CSP errors, allow embedding in another site, control cross-origin access, harden cookie settings, or asks "are my browser settings safe?", "fix my CSP", "set up CORS" — even if they only mention a specific header name without saying "security headers".

huytieu Skill

Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).

mashharuki Bundle

EIP-8183（Agentic Commerce）準拠のスマートコントラクト開発を包括的に支援するスキル。 AI Agent間の信頼不要な商取引（Job escrow + evaluator attestation）を実現する ERC-8183プロトコルの設計・実装・テスト・デプロイをカバー。 3者構造（Client/Provider/Evaluator）、6状態ステートマシン、 IACPHookによる拡張、ERC-8004レピュテーション連携、x402マイクロペイメント統合、 OpenZeppelin UUPS対応のリファレンス実装まで完全対応。 Use when building AI agent commerce systems, implementing ERC-8183 or EIP-8183, creating job escrow contracts, building agentic marketplaces, integrating AI agents with smart contracts, implementing evaluator attestation patterns, or working with Virtuals Protocol ACP. Also use when the user mentions agent-to-agent commerce, agentic commerce, job escrow, evaluator contracts, ERC-8004 reputation integration, or asks about AI agent on-chain transactions.