Total 50,658 skills, AI & Machine Learning has 8491 skills
Showing 12 of 8491 skills
Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
Master the AI tools that handle administrative work and boost personal productivity. From meeting notes to email management, get more done with less effort. Use when "meeting notes, email management, calendar optimization, productivity, time management, productivity, meetings, email, calendar, personal" mentioned.
Find every way users can break your AI before they do. Use when you need to red-team your AI, test for jailbreaks, find prompt injection vulnerabilities, run adversarial testing, do a safety audit before launch, prove your AI is safe for compliance, stress-test guardrails, or verify your AI holds up against adversarial users. Covers automated attack generation, iterative red-teaming with DSPy, and MIPROv2-optimized adversarial testing.
Stop your AI from making things up. Use when your AI hallucinates, fabricates facts, isn't grounded in real data, doesn't cite sources, makes unsupported claims, or you need to verify AI responses against source material. Covers citation enforcement, faithfulness verification, grounding via retrieval, and confidence thresholds.
Write, create, and improve CLAUDE.md project memory files for Claude Code. Use when: (1) Creating or bootstrapping a new CLAUDE.md, (2) Improving, refactoring, or splitting a bloated CLAUDE.md, (3) Questions about CLAUDE.md structure, imports, or modular rules, (4) After significant codebase exploration—cache discoveries to avoid re-crawling.
Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning. Use when building semantic search, RAG pipelines, or document retrieval systems that require cost-effective, high-quality embeddings.
Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.
Evaluate GitHub contributors for MLOps/engineering roles. Use when analyzing candidates, researching GitHub profiles, or updating CONTRIBUTORS.md with hiring assessments.
Implementation agent that executes a single task and creates handoff on completion
Show full session token usage, costs, TLDR savings, and hook activity
Deep Research Skill - Multi-source investigation across X (Twitter), the Web, and academic papers using team agents. Utilize this skill when users request deep research, comprehensive investigation, multi-perspective analysis, or hypothesis development on any topic. It is triggered by phrases such as "deep research", "investigate thoroughly", "research across sources", "ディープリサーチ", or requests for fact-based analysis with original hypotheses. It conducts a 6-phase research process: needs analysis, X preliminary research, parallel web deep-dive (3 agents), information integration, hypothesis construction, and final report delivery.