agentsclimarketplace

Context & AI engineering

25,772 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

  • Rag evaluation matrix

    mouadja02/skills/skills/agent-eval/rag-evaluation-matrix Skill

    no license13★ repo

    Use when comparing basic, enhanced, GraphRAG, or agentic RAG designs, evaluating domain-specific RAG quality, tuning retrieval components, or deciding whether agentic RAG is worth its cost.

  • Python fastapi llm

    mouadja02/skills/skills/api-backend/python-fastapi-llm Skill

    no license13★ repo

    Also use for async Python patterns, Pydantic schemas for LLM structured outputs, retry strategies for LLM calls, background AI jobs, or any service combining FastAPI and LLMs. If Python + AI backend is in scope — use this skill

  • Typespec create agent

    mouadja02/skills/skills/api-backend/typespec-create-agent Skill

    no license13★ repo

    Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot

  • Agent protocol

    mouadja02/skills/skills/business-strategy/c-level-advisor/agent-protocol Skill

    no license13★ repo

    Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats

  • Amazon bedrock

    mouadja02/skills/skills/cloud-aws/core/amazon-bedrock Skill

    no license13★ repo

    Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching setup and debugging, quota health checks and throttling diagnosis, cost attribution and tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, 402 Payment Required, pay for content, paid endpoint, agent payments). NOT for custom model training, Rekognition, or Comprehend.

  • Amazon elasticache

    mouadja02/skills/skills/cloud-aws/database/amazon-elasticache Skill

    no license13★ repo

    Activate when developers have latent caching needs: slow API responses, database read bottlenecks, DynamoDB throttling or cost, RDS/Aurora scaling pressure, Bedrock latency or cost, or adding a cache; activate when working with Redis, Valkey, Memcached, or any in-memory data store, cache-aside patterns, session stores, rate limiting, leaderboards, counters, streams, queues, pub/sub, distributed locks, feature flags, shopping carts, or other caching strategies. Activate for GenAI and ML retrieval: vector similarity search for low-latency retrieval, semantic caching, RAG, LLM response caching, embedding stores, AI agent memory, recommendation, personalization. Activate for ElastiCache lifecycle: provisioning (serverless or node-based), engine selection, CloudFormation/CDK/Terraform IaC, VPC connectivity, TLS, RBAC, IAM auth, Global Datastore, monitoring, troubleshooting, cost optimization, and migration from self-managed Redis. Do not trigger for browser caches, CDN/CloudFront, HTTP Cache-Control, CPU caches.

  • Storing and querying vectors

    mouadja02/skills/skills/cloud-aws/storage/storing-and-querying-vectors Skill

    no license13★ repo

    Store and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector storage service with its own API namespace (s3vectors). Triggers on: create S3 vector bucket, vector index, store embeddings, semantic search, RAG vector storage, similarity search, vector database, migrate from other vector databases. Do NOT use for: querying tabular data (use querying-data-lake), S3 object storage, or hundreds/thousands of sustained QPS (use OpenSearch).

  • Aspire

    mouadja02/skills/skills/cloud-azure/aspire Skill

    no license13★ repo

    Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment

  • Azure pricing

    mouadja02/skills/skills/cloud-azure/azure-pricing Skill

    no license13★ repo

    Fetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption

  • Anti ai slop

    mouadja02/skills/skills/code-quality/anti-ai-slop Skill

    no license13★ repo

    Use when writing, editing, or reviewing code, READMEs, docs, commits, changelogs, or any repo content. Pre-2020 human style — terse, opinionated, restrained, with project voice. Blocks the LLM tics: emoji headers, "leverage", "robust", "seamless", "delve", defensive bloat, type-hint overkill, marketing prose, "Whether you're X or Y", verbose error messages, and the rest of the AI tells catalogued from cpython, requests, flask, git, ripgrep, express, kubernetes, serde, go stdlib, and other pre-2020 reference repos. Triggers on "anti-ai", "human-style", "professional code", "clean code", "no slop", "write it like a human", or any time the agent is producing code/docs that should look hand-written.

  • Context engineering

    mouadja02/skills/skills/coding/context-engineering Skill

    no license13★ repo

    Optimizes agent context setup

  • Swe agent issue loop

    mouadja02/skills/skills/coding/swe-agent-issue-loop Skill

    no license13★ repo

    Use when turning GitHub issues or bug reports into reproducible coding-agent repair loops with sandboxed execution, focused tests, patch generation, and regression verification.

  • Using agent skills

    mouadja02/skills/skills/coding/using-agent-skills Skill

    no license13★ repo

    Discovers and invokes agent skills

  • Context fundamentals

    mouadja02/skills/skills/context-engineering/context-fundamentals Skill

    no license13★ repo

    This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

  • Filesystem context

    mouadja02/skills/skills/context-engineering/filesystem-context Skill

    no license13★ repo

    This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

  • Integrate context matic

    mouadja02/skills/skills/context-engineering/integrate-context-matic Skill

    no license13★ repo

    Discovers and integrates third-party APIs using the context-matic MCP server. Uses `fetch_api` to find available API SDKs, `ask` for integration guidance, `model_search` and `endpoint_search` for SDK details

  • Memory systems

    mouadja02/skills/skills/context-engineering/memory-systems Skill

    no license13★ repo

    Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory or memory benchmarks (LoCoMo, LongMemEval).

  • Onboard context matic

    mouadja02/skills/skills/context-engineering/onboard-context-matic Skill

    no license13★ repo

    Context-matic MCP server tour — APIs, endpoints, capabilities walkthrough

  • Provenance grounded memory

    mouadja02/skills/skills/context-engineering/provenance-grounded-memory Skill

    no license13★ repo

    Use when designing or auditing long-term memory for persistent AI agents. Stores immutable source evidence before canonical facts, links beliefs to provenance, applies novelty-aware ADD/UPDATE/NOOP write gating, keeps uncertain merges explicit, separates retrieval from answer generation, supports deletion, and evaluates memory failures layer by layer.

  • Dependabot

    mouadja02/skills/skills/devops/dependabot Skill

    no license13★ repo

    Comprehensive guide for configuring and managing GitHub Dependabot. Use this skill when users ask about creating or optimizing dependabot.yml files, managing Dependabot pull requests, configuring dependency update strategies, setting up grouped updates, monorepo patterns, multi-ecosystem groups, security update configuration, auto-triage rules, or any GitHub Advanced Security (GHAS) supply chain security topic related to Dependabot. For pre-commit dependency vulnerability scanning in AI coding agents via the GitHub MCP Server, this skill references the Advanced Security plugin (`advanced-security@copilot-plugins`). Use this skill when an agent needs to scan dependencies for known vulnerabilities before committing.

  • Microsoft docs

    mouadja02/skills/skills/documentation/microsoft-docs Skill

    no license13★ repo

    Query Microsoft docs — Azure, .NET, Agent Framework, Aspire, Copilot, Microsoft 365

  • Project development

    mouadja02/skills/skills/documentation/project-development Skill

    no license13★ repo

    This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

    The same file is in 1 other repository

  • Dispatching parallel agents

    mouadja02/skills/skills/engineering-craft/dispatching-parallel-agents Skill

    no license13★ repo

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

  • Remember copilot

    mouadja02/skills/skills/engineering-craft/remember-copilot Skill

    no license13★ repo

    Transforms lessons learned into domain-organized memory instructions (global or workspace). Syntax: `/remember [>domain [scope]] lesson clue` where scope is `global` (default), `user`, `workspace`, or `ws`.

  • Subagent driven development

    mouadja02/skills/skills/engineering-craft/subagent-driven-development Skill

    no license13★ repo

    Use when executing implementation plans with independent tasks in the current session

  • X twitter scraper

    mouadja02/skills/skills/engineering-craft/x-twitter-scraper Skill

    no license13★ repo

    Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, MCP tools, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation

  • Gtm ai gtm

    mouadja02/skills/skills/go-to-market/gtm-ai-gtm Skill

    no license13★ repo

    Go-to-market strategy for AI products. Use when positioning AI products, handling "who is responsible when it breaks" objections, pricing variable-cost AI, choosing between copilot/agent/teammate framing, or selling autonomous tools into enterprises.

  • Arize evaluator

    mouadja02/skills/skills/llm-tooling/arize-evaluator Skill

    no license13★ repo

    Arize LLM judge — evaluators, hallucination/faithfulness/relevance scorers, eval runs

  • Arize experiment

    mouadja02/skills/skills/llm-tooling/arize-experiment Skill

    no license13★ repo

    Arize experiments — create, run, analyze. A/B eval, model comparison (GPT-4, Claude)

  • Arize prompt optimization

    mouadja02/skills/skills/llm-tooling/arize-prompt-optimization Skill

    no license13★ repo

    Also use when the user wants to make their AI respond better or improve AI output quality. Covers extracting prompts from spans, gathering performance signal, and running a data-driven optimization loop using the ax CLI

  • Multimodal rag architecture

    mouadja02/skills/skills/llm-tooling/multimodal-rag-architecture Skill

    no license13★ repo

    Use when designing or auditing RAG over PDFs, images, tables, charts, equations, video frames, or heterogeneous documents where text-only chunking loses important evidence.

  • Openrouter agent migration

    mouadja02/skills/skills/llm-tooling/openrouter-agent-migration Skill

    no license13★ repo

    @openrouter/sdk → @openrouter/agent — callModel, tool(), stop conditions migration

  • Phoenix evals

    mouadja02/skills/skills/llm-tooling/phoenix-evals Skill

    no license13★ repo

    Build and run evaluators for AI/LLM applications using Phoenix.

  • Qdrant clients sdk

    mouadja02/skills/skills/llm-tooling/qdrant-clients-sdk Skill

    no license13★ repo

    Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.

  • Qdrant deployment options

    mouadja02/skills/skills/llm-tooling/qdrant-deployment-options Skill

    no license13★ repo

    Guides Qdrant deployment selection

  • Qdrant model migration

    mouadja02/skills/skills/llm-tooling/qdrant-model-migration Skill

    no license13★ repo

    Guides embedding model migration in Qdrant without downtime

  • Qdrant monitoring

    mouadja02/skills/skills/llm-tooling/qdrant-monitoring Skill

    no license13★ repo

    Guides Qdrant monitoring and observability setup

  • Debugging

    mouadja02/skills/skills/llm-tooling/qdrant-monitoring/debugging Skill

    no license13★ repo

    Diagnoses Qdrant production issues using metrics and observability tools

  • Setup

    mouadja02/skills/skills/llm-tooling/qdrant-monitoring/setup Skill

    no license13★ repo

    Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization

  • Qdrant performance optimization

    mouadja02/skills/skills/llm-tooling/qdrant-performance-optimization Skill

    no license13★ repo

    Different techniques to optimize the performance of Qdrant, including indexing strategies, query optimization, and hardware considerations

  • Memory usage optimization

    mouadja02/skills/skills/llm-tooling/qdrant-performance-optimization/memory-usage-optimization Skill

    no license13★ repo

    Use when diagnosing Qdrant resident-memory pressure, page-cache confusion, optimization headroom, or RAM-versus-disk placement.

  • Qdrant scaling

    mouadja02/skills/skills/llm-tooling/qdrant-scaling Skill

    no license13★ repo

    Guides Qdrant scaling decisions

  • Minimize latency

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/minimize-latency Skill

    no license13★ repo

    Guides Qdrant query latency optimization

  • Scaling data volume

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/scaling-data-volume Skill

    no license13★ repo

    Guides Qdrant data volume scaling decisions

  • Horizontal scaling

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/scaling-data-volume/horizontal-scaling Skill

    no license13★ repo

    Diagnoses and guides Qdrant horizontal scaling decisions

  • Sliding time window

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/scaling-data-volume/sliding-time-window Skill

    no license13★ repo

    Guides sliding time window scaling in Qdrant

  • Tenant scaling

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/scaling-data-volume/tenant-scaling Skill

    no license13★ repo

    Guides Qdrant multi-tenant scaling

  • Vertical scaling

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/scaling-data-volume/vertical-scaling Skill

    no license13★ repo

    Guides Qdrant vertical scaling decisions

  • Scaling qps

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/scaling-qps Skill

    no license13★ repo

    Guides Qdrant query throughput (QPS) scaling

  • Scaling query volume

    mouadja02/skills/skills/llm-tooling/qdrant-scaling/scaling-query-volume Skill

    no license13★ repo

    Guides Qdrant query volume scaling

  • Qdrant search quality

    mouadja02/skills/skills/llm-tooling/qdrant-search-quality Skill

    no license13★ repo

    Diagnoses and improves Qdrant search relevance

  • Diagnosis

    mouadja02/skills/skills/llm-tooling/qdrant-search-quality/diagnosis Skill

    no license13★ repo

    Diagnoses Qdrant search quality issues

  • Search strategies

    mouadja02/skills/skills/llm-tooling/qdrant-search-quality/search-strategies Skill

    no license13★ repo

    Guides Qdrant search strategy selection

  • Qdrant version upgrade

    mouadja02/skills/skills/llm-tooling/qdrant-version-upgrade Skill

    no license13★ repo

    Guidance on how to upgrade your Qdrant version without interrupting the availability of your application and ensuring data integrity

  • Cs ai seo

    mouadja02/skills/skills/marketing-and-growth/cs-ai-seo Skill

    no license13★ repo

    Optimize content to get cited by AI search engines — ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot

  • Dotnet mcp builder

    mouadja02/skills/skills/mcp/dotnet-mcp-builder Skill

    no license13★ repo

    MCP servers in C#/.NET — tools, prompts, resources, STDIO/HTTP transports, MCP Apps, OAuth, routing

  • Fastmcp

    mouadja02/skills/skills/mcp/fastmcp Skill

    no license13★ repo

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.

  • Go mcp server generator

    mouadja02/skills/skills/mcp/go-mcp-server-generator Skill

    no license13★ repo

    Generate a complete Go MCP server project with proper structure, dependencies, and implementation using the official github.com/modelcontextprotocol/go-sdk

  • Java mcp server generator

    mouadja02/skills/skills/mcp/java-mcp-server-generator Skill

    no license13★ repo

    Generate a complete Model Context Protocol server project in Java using the official MCP Java SDK with reactive streams and optional Spring Boot integration

  • Kotlin mcp server generator

    mouadja02/skills/skills/mcp/kotlin-mcp-server-generator Skill

    no license13★ repo

    Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library