Automatically activated when user asks how something works, wants to understand unfamiliar code, needs to explore a new codebase, or asks questions like "where is X imple — from…
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and — from…
Use when generating weekly GTM performance reports, summarizing pipeline activity, reviewing outreach metrics, or creating executive updates.
Classify text sentiment using NLP techniques, lexicon-based analysis, and machine learning for opinion mining, brand monitoring, and customer feedback analysis
Master scikit-learn machine learning patterns including pipeline design, cross-validation, hyperparameter tuning, feature engineering, and model evaluation.
Structured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-aware feedback.
libeval - RAG evaluation system. Evaluator orchestrates quality assessment using LLM-as-judge patterns. CriteriaEvaluator scores responses against rubrics.
L3 Worker. Analyzes single pattern implementation, calculates 4 scores (compliance, completeness, quality, implementation), identifies gaps and issues.
Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assisti — from…
Especialista en Sistema PERMISOS SyV - validación, marcado y coherencia de alertas de información sensible — from majiayu000/claude-skill-registry
コーディング用プロンプトを最適化・添削するスキル。 以下の状況で使用: (1) ユーザーが「このプロンプトを改善して」「プロンプトを最適化して」と依頼した時 (2) ユーザーが明示的に「/coding-prompt-optimizer」を実行した時 (3) AI向けプロンプトの品質改善を求められた時 — from…
[Code Quality] Defines clear boundaries and goals for a refactoring session. Use to establish what WILL and WILL NOT change, set success criteria, and create a focused refactoring…
Operational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling, quantization/compression, parallelism, and reliable serving — from…
Produce a Competitive Analysis Pack (competitive alternatives map, competitor landscape, differentiation & positioning hypotheses, battlecards, monitoring plan).
Research external libraries with evidence-backed responses and GitHub permalinks. Use when investigating library APIs, implementation patterns, or historical context for open…
Implement real-time streaming UI patterns for AI chat applications. Use when adding response lifecycle handlers, progress indicators, client effects, or thread state sync — from…
deeply review a system/architecture area and propose a simplification plan (Elon’s Algorithm). — from majiayu000/claude-skill-registry
Expert knowledge for Azure AI Metrics Advisor development including decision making, security, configuration, and integrations & coding patterns.
Identity, routing, communication style, memory protocol, task protocol, decision frameworks, and clarification for TARS — from majiayu000/claude-skill-registry
Multi-backend deep learning library for building, training, running inference, and saving neural network models in Python.
Use when the user provides a text file (PDF, DOCX, MD, TXT) written in Spanish that was generated by AI and needs to be rewritten to sound naturally human-written, for re — from…
Manages distributed workloads and file sharing across Tailscale SSH-connected machines. Automates remote command execution, intelligent load balancing, file synchronization…
Build and optimize SOQL queries including relationship queries, aggregate functions, polymorphic TYPEOF, and selective filters.
Deploy LLMs with Hugging Face Text Generation Inference. Configure quantization, continuous batching, and tensor parallelism.
Use when designing, implementing, or reviewing frontend-to-backend API integration, typed API clients, REST/tRPC/OpenAPI client choices, auth refresh, API error mapping, upload…
Guidelines for using facet crates (facet-json, facet-toml, facet-args) instead of serde-based alternatives for consistent dogfooding
Define tools for the support agent. Use when adding new capabilities like refund processing, license transfer, knowledge lookup, or any agent action.
Build recommendation systems with collaborative filtering, matrix factorization, hybrid approaches. Use for product recommendations, personalization, or encountering cold start,…
App Store スクリーンショット A/B テスト自動クローズドループ。メトリクス確認 → 勝者判定 → ヘッドライン生成（生成→採点→改善ループ）→ l.md Bible（make generate-store-screenshots）でPNG生成 → visual-qa採点 → Slackにダイスへ送る → ASCアップロード →…
Generiert Rueckfragen an den Mandanten wenn das vorgelegte Material fuer eine sinnvolle Recherche nicht ausreicht oder Abgrenzungsfragen offen sind.
Convert Haskell code to idiomatic Elm. Use when migrating Haskell logic to frontend applications, translating pure functional patterns to Elm's architecture, or refactori — from…
Explain something in detail with investigation. No changes, no suggestions, no opinions. Facts and technical depth only. Usage: /dev-explain <topic>
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findi — from…
Multi-engine web search with full parameter control. Supports Tavily, Exa, Serper, and SerpAPI with domain filtering, date ranges, deep search, news mode, and content extraction.
Generate or edit images with Gemini Pro. Use when user says "generate an image", "create a picture", "make me a logo", "edit this image", "remove the background", "change the…
Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches).
Measure model performance on test datasets. Use when assessing accuracy, precision, recall, and other metrics.
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.
Auto-generates code flow diagrams from Python module analysis. Detects when architecture diagrams become stale (code changed, diagram didn't).
Cross-domain isomorphic pattern forge. Dokkado Five Rings x meta-pattern 3+ domain validation, with arxiv evidence hunting and smithery tool discovery. RSI-refined.
Add a new field to an existing entity/model with related service and endpoint updates
Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for m — from…
PRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features.
Cloudflare Workers KV key-value storage playbook: namespaces, bindings, Workers API (get/put/delete/list), metadata, expiration TTL, bulk operations, REST API, consistency model,…
Verify a proposed architecture diagram against the actual codebase, selectively checking existing vs new components.
QA an analysis before sharing with stakeholders — methodology checks, accuracy verification, and bias detection.
Use when the user provides an implementation plan file and asks to analyze it, assess impact, update specifications, or verify planned changes.
Expertise in reviewing technical research for objectivity, evidence, and completeness. Use to ensure the "Documentarian" standard is met.
Background knowledge about WeReply project architecture, features, and context. Automatically loaded for AI reference, not directly user-invocable.
Expert skill for implementing OpenAI Agents SDK with function tools, MCP server integration, and context management for building intelligent AI assistants.
Generate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA.
Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform — from…
Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to evaluate how well a project supports unattended age — from…
Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, implementing tool use, streaming responses, or working wi — from…
Génère des mappers bidirectionnels entre Domain Entities et Prisma Models pour l'isolation de la couche persistence.
Time series modeling, stationarity, ARIMA/GARCH, SDEs, and regime detection for trading.
Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history.
Analyze survey responses with Likert scale analysis, cross-tabulations, sentiment scoring, and frequency distributions with visualizations.
Multi-provider reasoning/thinking configuration. Discriminated unions for OpenAI effort, Anthropic budget, Google level/budget, DeepSeek middleware.
Codequalitäts-Audit für die Speicher Analyse Tauri-App (React + Vite + TypeScript Frontend). Prüft Security, Performance, WCAG-Kontrast, Tauri-Best-Practices und…