Context & AI engineering
25,729 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
sitapix/apple-text/skills/txt-apple-docs Skill
0★ repoLook up authoritative Apple-authored documentation for any text-system or Swift API via Sosumi (sosumi.ai URL swap and MCP server) and Xcode 26.3+ xcrun mcpbridge. Use when an Apple Text skill needs grounding against the actual Apple docs, an exact API signature is required, a Swift compiler diagnostic needs the official explanation, or a recently-shipped framework update has to be verified against the source. This is the entry point for documentation grounding — invoke it before reciting any specific API signature from memory.
JLugagne/claude-skills/tools/mct-cli/skills/mct-cli Skill
0★ repoReference guide for mct (claude-mercato), a Git-based package manager for Claude agent and skill definitions. Use this skill whenever the user asks how to use mct, asks about mct commands, wants to install/update/search/export agents or skills, asks about markets, drift, sync, pinning, import/export, or any other mct workflow. Also trigger when the user is looking for skills or agents to add to their project, wants to find a skill for a specific task, asks "is there a skill for X", "find me a skill that does Y", "what skills are available", or wants to browse or discover available Claude skills and agents. Trigger even if the user says "claude-mercato", "mct add", "mct sync", or just asks "how do I install an agent from a market?"
JLugagne/agach/.claude/skills/doc-daemon Skill
0★ repoAgach daemon agent: onboarding, WebSocket reconnect, Docker builds, chat sessions (Claude CLI), git worktrees, SQLite persistence
khujta/gabe-suite/skills/gabe-handoff Skill
no license0★ repoSession handoff — emit a paste-able next-session prompt + sync durable KDBP state so a fresh session resumes with full fidelity. Run when context is heavy or when wrapping up. Usage: /gabe-handoff [--dry-run | --no-sync | <focus note>]
ortus-boxlang/skills/boxlang-modules/bx-ai/bx-ai-memory Skill
no license0★ repoUse this skill when implementing memory in BoxLang AI: aiMemory() types (windowed, summary, session, file, cache, JDBC, vector), multi-tenant isolation with userId and conversationId, using memory with agents and pipelines, and choosing the right memory type.
ortus-boxlang/skills/boxlang-modules/bx-ai/bx-ai-rag Skill
no license0★ repoUse this skill when building RAG (Retrieval-Augmented Generation) systems with BoxLang AI: aiDocuments() for loading and chunking documents, aiEmbed() for embeddings, vector memory providers, ingesting documents into vector stores, and wiring RAG into agents.
Yakoub-ai/Tech-Skills/skills/mcp Skill
0★ repoMCP Manager for Model Context Protocol server lifecycle, token optimization, and context-efficient external data access. Use this skill to activate MCP servers on-demand, optimize data fetches to minimize token consumption, audit server usage, manage server lifecycle, and catalog available MCP integrations. Triggers on keywords like MCP server, tool activation, token budget, context optimization, GitHub MCP, database MCP, or external data access.
Yakoub-ai/Tech-Skills/skills/orchestrator Skill
0★ repoMaster AI orchestrator for complex, multi-domain engineering tasks. Use this skill when a task spans multiple disciplines (AI + DevOps, security + data, frontend + backend + QA), requires coordinated specialist agents, or needs structured plan-then-execute workflow with session continuity across multiple conversations. Triggers on requests like "build and deploy a full-stack app", "set up a secure data pipeline", or any task requiring more than one domain of expertise.
stotihv/skills/skills/orchestrator Skill
no license0★ repoPlan and coordinate multi-agent bead execution. Use when starting a new epic, assigning tracks to agents, or monitoring parallel work progress.
namos2502/CortexLink/skills/orchestration Skill
no license0★ repoThis skill should be used when a multi-step task can benefit from parallel subtask execution or cross-CLI delegation — decomposing work into independent subtasks, routing them to native subagents or CLI agents in parallel, and synthesizing their structured reports back to the user.
payals/ai-skills-engine/dot_cursor/skills/ai-research/agent-memory-mcp Skill
0★ repoA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
The same file is in 3 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/agent-memory-systems Skill
0★ repoMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
The same file is in 2 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/agent-tool-builder Skill
0★ repoTools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa
The same file is in 2 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/agents-crewai Skill
0★ repoMulti-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/ai-agents-architect Skill
0★ repoExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.
The same file is in 3 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/autonomous-agent-patterns Skill
0★ repoDesign patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
The same file is in 3 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/claude-code-guide Skill
0★ repoMaster guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
The same file is in 1 other repository
payals/ai-skills-engine/dot_cursor/skills/ai-research/context-window-management Skill
0★ repoStrategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.
The same file is in 3 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/conversation-memory Skill
0★ repoPersistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
The same file is in 2 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/crewai Skill
0★ repoExpert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.
The same file is in 2 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/dispatching-parallel-agents Skill
0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 15 other repositories
Inference serving tensorrt llm
payals/ai-skills-engine/dot_cursor/skills/ai-research/inference-serving-tensorrt-llm Skill
0★ repoOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/infrastructure-skypilot Skill
0★ repoMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
The same file is in 6 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/llm-app-patterns Skill
0★ repoProduction-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
The same file is in 5 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/loki-mode Skill
0★ repoMulti-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/model-architecture-torchtitan Skill
0★ repoProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/parallel-agents Skill
0★ repoMulti-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
The same file is in 5 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/prompt-caching Skill
0★ repoCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/prompt-engineer Skill
0★ repoExpert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.
The same file is in 2 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/prompt-engineering Skill
0★ repoExpert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/prompt-library Skill
0★ repoCurated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/rag-chroma Skill
0★ repoOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
The same file is in 5 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/rag-engineer Skill
0★ repoExpert 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.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/rag-implementation Skill
0★ repoRetrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.
The same file is in 1 other repository
payals/ai-skills-engine/dot_cursor/skills/ai-research/rag-pinecone Skill
0★ repoManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
The same file is in 5 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/rag-qdrant Skill
0★ repoHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/rag-sentence-transformers Skill
0★ repoFramework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/ai-research/subagent-driven-development Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 7 other repositories
payals/ai-skills-engine/dot_cursor/skills/context-engineering Skill
0★ repoMaster context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
The same file is in 2 other repositories
payals/ai-skills-engine/dot_cursor/skills/development/dispatching-parallel-agents Skill
0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 15 other repositories
payals/ai-skills-engine/dot_cursor/skills/development/senior-ml-engineer Skill
0★ repoWorld-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
The same file is in 5 other repositories
payals/ai-skills-engine/dot_cursor/skills/development/senior-prompt-engineer Skill
0★ repoWorld-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
The same file is in 5 other repositories
payals/ai-skills-engine/dot_cursor/skills/utilities/browser-automation Skill
0★ repoBrowser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/web-development/blockrun Skill
0★ repoUse when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/workflow-automation/n8n/n8n-mcp-tools-expert Skill
0★ repoExpert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
The same file is in 2 other repositories
competlab/competlab-ci-skills/skills/competlab-ai-visibility Skill
0★ repoAnalyzes how AI models (ChatGPT, Claude, Gemini) mention and recommend your brand vs competitors using CompetLab monitoring data. Use this skill when the user asks "how do LLMs see my brand", "AI visibility report", "AI brand check", "what does ChatGPT say about us", "GEO analysis", "AI SEO report", "AI Visibility Score", "AI mentions", "AI perception", or "who do AI models recommend in my space". NOT for traditional SEO, Google rankings, or web traffic analysis. Requires CompetLab MCP server (competlab.com) with an active project.
competlab/competlab-ci-skills/skills/competlab-battlecard Skill
0★ repoGenerates sales-ready competitive battlecards using CompetLab monitoring data and live web research — quick-reference cards for sales calls, demos, and competitive objection handling. Use this skill when the user asks to "create a battlecard", "sales battlecard for [competitor]", "competitive comparison card", "why us vs [competitor]", "win against [competitor]", "how to beat [competitor]", "objection handling for [competitor]", "sales cheat sheet", or "competitive one-pager". NOT for deep strategic analysis (use competlab-competitor-dive), weekly updates (use competlab-weekly-briefing), or full market landscape analysis (use competlab-landscape). Requires CompetLab MCP server (competlab.com) with competitors being monitored.
competlab/competlab-ci-skills/skills/competlab-competitor-dive Skill
0★ repoGenerates a comprehensive competitor dossier combining CompetLab monitoring data with live web research — tech stack, pricing, positioning, content strategy, AI visibility, public sentiment, SWOT analysis, and recommended responses. Use this skill when the user asks to "analyze [competitor]", "deep dive on [competitor]", "competitor dossier", "competitor profile", "research [competitor]", "what is [competitor] doing", "SWOT analysis for [competitor]", "competitor SWOT", or "tell me everything about [competitor]". NOT for multi-competitor landscape analysis (use competlab-landscape) or weekly updates (use competlab-weekly-briefing). Requires CompetLab MCP server (competlab.com) with the target competitor being monitored.
competlab/competlab-ci-skills/skills/competlab-landscape Skill
0★ repoGenerates a comprehensive competitive landscape analysis combining all 5 CompetLab monitoring dimensions with deep web research — market dynamics, competitive matrices, cross-dimensional patterns, market macro trends, positioning opportunities, and strategic recommendations. Use this skill when the user asks for "competitive landscape", "full CI analysis", "landscape scan", "quarterly competitive review", "market analysis", "market overview", "competitive overview", "competitor matrix", "board-level CI", "market trends in [category]", or "where is the market heading". NOT for single-competitor analysis (use competlab-competitor-dive) or quick weekly updates (use competlab-weekly-briefing). Requires CompetLab MCP server (competlab.com) with an active project.
competlab/competlab-ci-skills/skills/competlab-weekly-briefing Skill
0★ repoGenerates a weekly competitive intelligence briefing from CompetLab monitoring data — what changed, what it means, and what to do about it. Use this skill when the user asks for "weekly briefing", "CI update", "competitive update", "what changed with competitors", "Monday briefing", "competitive summary", "competitive news", "CI digest", or "catch me up on competitors". NOT for deep single-competitor analysis (use competlab-competitor-dive) or full landscape reviews (use competlab-landscape). Requires CompetLab MCP server (competlab.com) with an active project.
arndvs/ctrlshft/skills/review-pr-copilot Skill
0★ repoAddress GitHub Copilot review comments on the active PR by triaging into confidence tiers, fixing in atomic commits, resolving threads, and re-requesting review.
arndvs/ctrlshft/skills/skill-scaffolder Skill
0★ repoMeta-skill for creating new agent skills that involve multi-step automation, browser navigation, state tracking, evidence capture, and both local (VS Code Insiders) and VPS (Playwright) execution. Use when the user wants to 'create a skill', 'build a new skill', 'scaffold a skill', 'make a skill for X', or describes a multi-step agentic workflow they want to automate.
torarnv/claude-project-manager/skills/memory Skill
no license0★ repoRecord a decision, lesson, tool note, or any project knowledge mid-session.
mnttnm/claude-skills/video-decompose Skill
no license0★ repoConvert screen recording videos (Loom, mp4) into structured keyframes + transcript for LLM consumption. Use when the user provides a video URL or local video file and wants to extract product requirements, document a feature walkthrough, or convert video content into a format Claude can analyze. Triggers on "decompose this video", "extract frames from video", user shares a Loom or video URL and wants requirements extracted, "convert this video to requirements", or user mentions video-based product requirements or feature walkthroughs they need analyzed.
Backend to frontend handoff docs
uts58/my-random-skills/backend-to-frontend-handoff-docs Skill
no license0★ repoCreate API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.
The same file is in 3 other repositories
uts58/my-random-skills/mcp-builder Skill
no license0★ repoGuide for creating high-quality MCP (Model Context Protocol) 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).
uts58/my-random-skills/skill-creator Skill
no license0★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Pamacea/strike/plugins/ui/skills/optional/teams Skill
0★ repoMANDATORY parallel execution gate BEFORE building large/complex UI projects. Orchestrates multi-agent teamwork with 2-4 specialist agents working concurrently. Specific phrases: 'parallel agents', 'team build', 'multi-agent UI', 'split work', 'concurrent UI generation', 'agent team for design'. Auto-activates with --team flag or large/complex prompts (>3 features, multi-domain). Team composition: Orchestrator (analyze/detect/select/enrich), Build (build/validate/metrics), Adversarial (challenge/stress-test), Reviewer (a11y/quality/docs). Parallel execution: 1.85x faster than sequential (4 agents), 1.6x faster (2 agents). Inter-agent communication via team messaging system. Shared task list at ~/.claude/tasks/ui-<session-id>/. Error handling: Orchestrator fails → stop build, Build fails → spec reusable, Communication fails → 30s timeout + restart. Integrates with ui orchestrator and step mode.
Pamacea/strike/plugins/ui/skills/ui Skill
0★ repoMANDATORY UI generation gate BEFORE creating interfaces. Orchestrates positive-directed innovation methodology with 12+ flags (--step/--team/--build/--demo/--analyze/--constraints/--full/--score/--validate) and Attractor-powered workflow orchestration (DOT graphs, checkpoints, events, parallel execution). Specific phrases: 'create UI', 'build interface', 'design dashboard', 'make website', 'generate layout', 'build page'. Uses PIVOT MATRIX: detects trend-trap keywords → maps to radical positive paradigms → applies creative constraints with scoring (creativity 30%, difficulty 25%, impact 25%, synergy 20%). Integrates with step mode (interactive human-in-the-loop), teams mode (parallel agents), and design-taste-frontend patterns (positive directive patterns, accessibility-first). Reads memory via claude-mem before implementing, saves patterns after completion.
jord0-cmd/jord0.skills/skills/FORGE Skill
0★ repoProject onboarding and CLAUDE.md generation. Use when: starting work on a new codebase, setting up a project for the first time, creating or updating a project CLAUDE.md, generating module summaries, or when opening a project with no CLAUDE.md file. Forges a complete project knowledge base so Claude understands the codebase from day one.