AI & ML

Agent Accuracy Enhancement Skill

Use when user experience design, interface optimization, usability testing, or conversion-focused design is needed. This agent specializes in UX design and user experience optimization within the ContentForge AI ecosystem.

Use when tenant onboarding strategy, onboarding process design, tenant success planning, or onboarding optimization is needed. This agent specializes in SaaS onboarding mastery within the SaaSForge AI ecosystem.

Use when Candy integration, API development, or data synchronization is needed. This agent specializes in Candy connectivity within the IntegrateForge AI ecosystem.

Use when tenant success management, adoption optimization, expansion planning, or customer success strategy is needed. This agent specializes in SaaS customer success within the SaaSForge AI ecosystem.

Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'cross-check this', 'get another perspective', /cross-audit

Testing strategies for MCP servers including unit tests, integration tests, schema validation, and security testingUse when "mcp testing, test mcp server, mcp inspector, mcp validation, mcp, testing, unit-testing, integration-testing, schema-validation" mentioned.

Security patterns for MCP servers including OAuth 2.0, rate limiting, input validation, and audit loggingUse when "mcp security, mcp authentication, mcp oauth, mcp rate limit, secure mcp server, mcp, security, oauth, authentication, rate-limiting, validation" mentioned.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when "building RAG, vector search, embeddings, semantic search, document retrieval, context retrieval, knowledge base, LLM with documents, chunking strategy, pinecone, weaviate, chromadb, pgvector, rag, embeddings, vector-database, retrieval, semantic-search, llm, ai, langchain, llamaindex" mentioned.

Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.

Anti-over-engineering guardrail that activates when an AI coding agent expands scope, adds abstractions, or changes files the user did not request.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Seaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.

Bayesian modeling and probabilistic programming with PyMC — hierarchical models, MCMC (NUTS) sampling, variational inference, LOO/WAIC model comparison, and posterior predictive checks. Use when fitting Bayesian or hierarchical models, estimating posteriors and credible intervals, running probabilistic inference, or comparing models with LOO/WAIC. Part of the AlterLab Academic Skills suite.

Query the Monarch Initiative knowledge graph for disease-gene-phenotype associations across species, integrating OMIM, ORPHANET, HPO, ClinVar, and model organism databases. Use when discovering rare disease genes, mapping phenotypes to genes, modeling disease across species, or looking up HPO terms. Part of the AlterLab Academic Skills suite.

Co-fold biomolecular complexes with Boltz-2, an open AlphaFold3-style model — predict protein + ligand (SMILES/CCD), protein + nucleic-acid, and multi-chain structures in one pass, with binding-affinity prediction. Use when folding a protein together with a small-molecule ligand, predicting a holo (ligand-bound) complex or its binding affinity, or co-folding protein–DNA/RNA assemblies. For protein-only or protein–protein folding without ligands prefer alterlab-alphafold; for antibody–antigen complexes prefer alterlab-chai; to dock a ligand into a FIXED receptor structure prefer alterlab-diffdock; to look up an existing structure prefer alterlab-pdb. Part of the AlterLab Academic Skills suite.

Read, create, and convert Microsoft PowerPoint (.pptx) presentations — extract slide text to JSON/markdown, build decks from JSON/markdown outlines, and export to PDF.

Guides attorneys through deposition witness preparation using a two-session model with document review, practice examination, and day-of logistics. Covers party witnesses, fact witnesses, 30(b)(6) corporate representatives, and experts. Produces preparation memos, document review lists, topic summaries, and day-of checklists. Enforces ABA Opinion 508 ethical boundaries. Use when preparing any witness for deposition, scheduling prep sessions, or building witness preparation materials.

Econometrics skill for time series analysis. Activates when the user asks about: "time series", "stationarity", "unit root test", "ADF test", "KPSS test", "ARIMA", "ARMA", "autocorrelation", "ACF", "PACF", "VAR model", "VECM", "Granger causality", "cointegration", "impulse response function", "forecast", "seasonal decomposition", "ARCH", "GARCH", "时间序列", "平稳性检验", "单位根", "自回归", "格兰杰因果", "协整", "脉冲响应", "预测", "向量自回归"

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.

Master storyteller for compelling narratives using proven frameworks. Use when the user asks to talk to Sophia or requests the Master Storyteller.

Disruptive innovation oracle for business model innovation and strategic disruption. Use when the user asks to talk to Victor or requests the Disruptive Innovation Oracle.

PyTorch deep learning development with transformers, diffusion models, and GPU optimization.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.

Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, or setting up skill directory structures. Handles frontmatter generation, section templates, and validation guidance.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, ...

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

Destructive Command Guard. Installs a pre-tool-use hook that blocks unrecoverable shell commands (rm -rf /, git reset --hard, git clean -fd, rm of .env / credentials, force-pushing to main, fork bombs, shred / dd, etc.) before the agent executes them. Use when the user says "install dcg", "destructive command guard", "guard rails for destructive commands", or invokes /dcg.

CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.

Two-party working posture — user as director, agent as executor. Every fork, tradeoff, and taste choice is surfaced via batched AskUserQuestion with structural framing, a recommended default, and concrete previews when comparison is visual, so the human steers direction while the agent handles implementation. Eliminates the review-bottleneck (no giant diff to approve at the end — review is distributed across picks) and prevents codebase-understanding debt (the user remembers the architecture because they picked it). Use whenever the user invokes /duet, or says "work with me", "ask before", "check with me", "I want to decide", "don't assume", "human-in-the-loop", "co-author", "pair with me", "duet", or whenever a task clearly involves aesthetic, architectural, or irreversible strategic decisions — even without those exact words. Pair with the Duet output style to minimize cognitive load between picks.

入力（テキストアイデア/音源/動画/YouTube URL）を映像制作用の4構造プロンプト仕様書（①映像タイムライン ②ビジュアル特徴・画風 ③画像生成AI用プロンプト(英+訳) ④動画AI用モーション指示）に変換し、Phase 5 で画像+動画の実際生成ウィザードまで担当する。音源・動画・YouTubeはGemini(gemini-code)に分析委任、テキストアイデアはCC単独で処理。音楽生成プロンプトは出力しない（それは reverse-engineer-song の役割）。ユーザーが「映像プロンプト」「動画プロンプト」「映像仕様書」「ビジュアルプロンプト作って」「このアイデアで映像」「映像構成作って」「武将の動画」「サイバー和の映像」「MV作って」等と言った時、または /video-prompt-spec を呼んだ時にトリガー。楽曲のMV・プロモーション映像・ショート動画の映像プロンプトが欲しい時、画像/動画の実際生成まで走らせたい時は必ず本スキルを使うこと。

Runs large language models locally with Ollama, including model management, custom Modelfiles, and API integration. Use for private, offline LLM inference.

Creates multi-agent AI systems with AutoGen, enabling agent conversations, tool use, and group chats.

RAG with Dspy. building RAG systems.