agentsclimarketplace

Context & AI engineering

25,815 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

  • Vector database ops

    BagelHole/DevOps-Security-Agent-Skills/infrastructure/databases/vector-database-ops Skill

    46★ repo

    Deploy, manage, and optimize vector databases for AI applications. Covers Qdrant, Weaviate, pgvector, and Pinecone — collection management, indexing strategies, backup, and performance tuning for production RAG and semantic search workloads.

  • Llm fine tuning

    BagelHole/DevOps-Security-Agent-Skills/infrastructure/local-ai/llm-fine-tuning Skill

    46★ repo

    Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP. Covers dataset prep, training runs, and model export.

  • Llm inference scaling

    BagelHole/DevOps-Security-Agent-Skills/infrastructure/local-ai/llm-inference-scaling Skill

    46★ repo

    Auto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling. Handle traffic spikes, implement queue-based scaling, and optimize cost with spot instances for AI workloads.

  • Mac mini llm lab

    BagelHole/DevOps-Security-Agent-Skills/infrastructure/local-ai/mac-mini-llm-lab Skill

    46★ repo

    Configure a Mac mini as a reliable local LLM server with remote access, observability, and power-safe operation. Use when building an always-on private AI inference server on Apple Silicon.

  • Multi tenant llm hosting

    BagelHole/DevOps-Security-Agent-Skills/infrastructure/local-ai/multi-tenant-llm-hosting Skill

    46★ repo

    Design secure, multi-tenant LLM hosting platforms with tenant isolation, quotas, billing attribution, noisy-neighbor protection, and per-tenant policy controls.

  • Rag infrastructure

    BagelHole/DevOps-Security-Agent-Skills/infrastructure/local-ai/rag-infrastructure Skill

    46★ repo

    Build and operate Retrieval-Augmented Generation (RAG) infrastructure with vector stores, embedding pipelines, and hybrid search. Covers ingestion, chunking strategies, reranking, and production deployment patterns.

  • Llm gateway

    BagelHole/DevOps-Security-Agent-Skills/infrastructure/networking/llm-gateway Skill

    46★ repo

    Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking. Covers LiteLLM Proxy, OpenRouter-compatible setup, and custom Nginx/Traefik patterns.

  • Ai agent security

    BagelHole/DevOps-Security-Agent-Skills/security/ai/ai-agent-security Skill

    46★ repo

    Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls. Use when building, deploying, or hardening agentic AI systems that invoke tools, access data, or interact with production infrastructure.

  • Ai coding agent guardrails

    BagelHole/DevOps-Security-Agent-Skills/security/ai/ai-coding-agent-guardrails Skill

    46★ repo

    Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

  • Llm app security

    BagelHole/DevOps-Security-Agent-Skills/security/ai/llm-app-security Skill

    46★ repo

    Secure LLM-powered applications with input validation, output controls, tenant isolation, and abuse prevention.

  • Mcp server security

    BagelHole/DevOps-Security-Agent-Skills/security/ai/mcp-server-security Skill

    46★ repo

    Secure Model Context Protocol (MCP) servers with transport encryption, tool authorization, input validation, and audit logging for safe AI agent integrations.

  • Prompt injection defense

    BagelHole/DevOps-Security-Agent-Skills/security/ai/prompt-injection-defense Skill

    46★ repo

    Defend AI systems against prompt injection and indirect prompt attacks using input controls, tool permissions, output validation, and isolation boundaries.

  • Using orchestrator

    Kanevry/session-orchestrator/skills/using-orchestrator Skill

    45★ repo

    Use this skill when dispatching implicit slash-command intent from the user's first message. Inspects the user's first message for implicit slash-command intent and dispatches to the highest-confidence matching entry-point skill via the Skill tool. Only active when `auto-skill-dispatch: true` in Session Config. Silent no-op otherwise.

  • Oc create agent

    sequenzia/agent-alchemy/claude/opencode-tools/skills/oc-create-agent Skill

    45★ repo

    Guides through creating a new OpenCode-compatible agent with interactive interview, permission configuration, and validation. Use when user says "create opencode agent", "new opencode agent", "build agent for opencode", or wants to create an OpenCode agent markdown file.

    The same file is in 2 other repositories

  • Oc update agent

    sequenzia/agent-alchemy/claude/opencode-tools/skills/oc-update-agent Skill

    45★ repo

    Updates an existing OpenCode agent to match current platform best practices, fixes deprecated patterns, and validates the result. Use when user says "update opencode agent", "fix opencode agent", "migrate agent to opencode", or wants to modernize an existing OpenCode agent file.

    The same file is in 2 other repositories

  • Port master

    sequenzia/agent-alchemy/claude/plugin-tools/skills/port-master Skill

    45★ repo

    Convert Claude Code plugins into generic, platform-agnostic format. Supports full conversion (skills, agents, hooks), flatten mode (skills only — agents converted to skills, hooks absorbed), or nested mode (agents nested as pure markdown within parent skills, hooks absorbed). Full mode supports per-group or unified output layouts — unified merges all groups into a single directory organized by component type. Strips Claude Code-specific implementation details to produce clean markdown files preserving only the intent and instructions. Use when asked to "make this portable", "convert to generic format", "export plugin", "create universal skills", "strip platform dependencies", "make harness-agnostic", "decouple from Claude Code", "flatten to skills only", "nest agents in skills", or when the user wants their plugin content usable outside Claude Code. Also use when the user wants to share skills with teams using different agent frameworks.

    The same file is in 2 other repositories

  • Write agent

    tale-project/tale/.agents/skills/write-agent Skill

    45★ repo

    Use this skill whenever you create or update an agent in a Tale organization — a chat assistant, an image generator, or an external coding agent (Claude Code / Cursor). Triggers include: "create an agent", "change an agent's instructions, model, or tools", "give an agent a skill or integration", or an automation that needs its own agent. Never author an agent definition without it — and never create one before listing the existing agents and ruling out reuse. For the trigger→steps definitions an agent participates in, use write-workflow; for the installable bundle that groups agents, use write-automation.

  • Write agent

    tale-project/tale/builtin-configs/skills/write-agent Skill

    45★ repo

    Use this skill whenever you create or update an agent in a Tale organization — a chat assistant, an image generator, or an external coding agent (Claude Code / Cursor). Triggers include: "create an agent", "change an agent's instructions, model, or tools", "give an agent a skill or integration", or an automation that needs its own agent. Never author an agent definition without it — and never create one before listing the existing agents and ruling out reuse. For the trigger→steps definitions an agent participates in, use write-workflow; for the installable bundle that groups agents, use write-automation.

  • Financial data analysis agent

    AndrewNgGirl/SkillLens/skills/skill-scorer/examples/financial-data-analysis-agent Skill

    45★ repo

    Use when analysts, finance teams, or operators need to clean financial datasets, check data quality, analyze revenue, margin, cash flow, customer value, anomalies, or trends, and produce traceable management-ready insights with confidence caveats.

  • Memory

    AndrewNgGirl/SkillLens/skills/skill-scorer/examples/mega-pipeline/agents/memory Skill

    45★ repo

    Use when the parent pipeline routes a memory-related PR review request. Reads the diff and emits structured memoryFindings using the memory specialist heuristics.

  • Reviewer

    AndrewNgGirl/SkillLens/skills/skill-scorer/examples/pr-pipeline/agents/reviewer Skill

    45★ repo

    Use when the parent pipeline routes a PR review request. Reads diff and produces a Pydantic ReviewReport.

  • Summarizer

    AndrewNgGirl/SkillLens/skills/skill-scorer/examples/pr-pipeline/agents/summarizer Skill

    45★ repo

    Use when the pipeline needs to compress reviewer output into a digest. Pure function over ReviewReport.

  • Ai native context engineering

    gmaxxxie/ai-native-product-agent-skills/skills/ai-native-context-engineering Skill

    no license45★ repo

    AI Native 产品方法论——上下文工程的实操 Skill。 用户提供任务场景,Skill 自动执行上下文组织流程: 任务目标识别 → 上下文层选择 → 动态拼装 → 成本与窗口控制 → 结果校验与纠偏 → 输出上下文工程方案。 基于《AI Native 产品方法论》第14章。

  • Ai native knowledge rag

    gmaxxxie/ai-native-product-agent-skills/skills/ai-native-knowledge-rag Skill

    no license45★ repo

    AI Native 产品方法论——RAG与知识系统设计的实操 Skill。 用户提供企业知识场景,Skill 自动执行知识系统设计流程: 资料来源分析 → 清洗与脱敏 → 索引与权限控制 → 检索召回 → 评估与更新 → 输出知识系统方案。 基于《AI Native 产品方法论》第15章。

  • Ai native memory system

    gmaxxxie/ai-native-product-agent-skills/skills/ai-native-memory-system Skill

    no license45★ repo

    AI Native 产品方法论——记忆系统设计的实操 Skill。 用户提供产品场景,Skill 自动执行记忆系统设计流程: 记忆需求分析 → 记忆分类设计 → 权限与时效策略 → 存储与索引 → 人工修正与再沉淀 → 输出记忆系统方案。 基于《AI Native 产品方法论》第13章。

  • Ai native pm agent

    gmaxxxie/ai-native-product-agent-skills/skills/ai-native-pm-agent Skill

    no license45★ repo

    AI Native 产品经理 Agent — — 五书合一的产品工作流编排器。 用户提供一个产品想法或问题线索,Agent 自动编排七个阶段: P1需求发现 → P2方向定界 → P3体验设计 → P4系统构建 → P5商业模式 → P6增长策略 → P7审计投产。 基于五本书:《AI Native 产品方法论》《AI时代的用户体验》《AI确定性商业模式》《AI Native 营销与增长》《AI rebuild product needs》。

  • P0 needs orchestrator

    gmaxxxie/ai-native-product-agent-skills/skills/p0-needs-orchestrator Skill

    no license45★ repo

    需求发现编排器。协调微需求检测、真需求验证、需求拆解、需求考古、好问题生成、Agent 边界设计、多元推荐改写、AI 产品三重平衡八个工具卡, 按顺序执行并输出完整的需求发现报告。自包含——八个工具卡的核心方法已内嵌。 基于《AI rebuild product needs》读者工具箱。

  • P0f agent boundary designer

    gmaxxxie/ai-native-product-agent-skills/skills/p0f-agent-boundary-designer Skill

    no license45★ repo

    Agent 边界清单。AI 产品最危险的不是做不到,而是做过头。 这个 Skill 帮你系统性地定义 AI 应该做什么、不应该做什么、什么时候必须停下来等人。 基于《AI rebuild product needs》工具卡。

  • P12 contemplation orchestrator

    gmaxxxie/ai-native-product-agent-skills/skills/p12-contemplation-orchestrator Skill

    no license45★ repo

    《观照》全书编排器——根据用户输入的问题类型,路由到对应的章节Skill,串联全链路决策修正流程

  • P13 intuition orchestrator

    gmaxxxie/ai-native-product-agent-skills/skills/p13-intuition-orchestrator Skill

    no license45★ repo

    《判断力与直觉力》全书编排器——九步闭环决策路线图的路由器与聚合器

  • P14 beauty orchestrator

    gmaxxxie/ai-native-product-agent-skills/skills/p14-beauty-orchestrator Skill

    no license45★ repo

    《AI Beauty》全书编排器——审美主导权与美感体系化训练的路由器

  • P4 agent skill design

    gmaxxxie/ai-native-product-agent-skills/skills/p4-agent-skill-design Skill

    no license45★ repo

    'AI Native 产品方法论——智能体与技能单元设计的实操 Skill。

  • P5 memory system

    gmaxxxie/ai-native-product-agent-skills/skills/p5-memory-system Skill

    no license45★ repo

    'AI Native 产品方法论——记忆系统设计的实操 Skill。

  • P6 context engineering

    gmaxxxie/ai-native-product-agent-skills/skills/p6-context-engineering Skill

    no license45★ repo

    'AI Native 产品方法论——上下文工程的实操 Skill。

  • P7 knowledge rag

    gmaxxxie/ai-native-product-agent-skills/skills/p7-knowledge-rag Skill

    no license45★ repo

    'AI Native 产品方法论——RAG与知识系统设计的实操 Skill。

  • Team memory protocol

    wigtn/wigtn-plugins/plugins/wigtn-plugins/skills/team-memory-protocol Skill

    45★ repo

    Claude Code Plugins for AI Native-based Engineer

  • Context engineering

    KevinKE93/Dev_Agent_OPC/dev-agent/skills/context-engineering Skill

    no license45★ repo

    Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

    The same file is in 12 other repositories

  • Gate News MCP

    gate/gate-mcp/io.github.gateio-dev/gate-news MCP server

    45★ repo

    Gate news MCP for crypto news, structured events, announcements, and social sentiment.

  • Gate Exchange MCP

    gate/gate-mcp/io.github.gateio-dev/gate-exchange MCP server

    45★ repo

    OAuth Gate exchange MCP for CEX trading, account, wallet, unified account, and sub-account.

  • Gate Info MCP

    gate/gate-mcp/io.github.gateio-dev/gate-info MCP server

    45★ repo

    Gate info MCP for coin discovery, market snapshots, technical analysis, and on-chain data.

  • Prompt enhance

    owainlewis/agent-skills/skills/prompt-enhance Skill

    44★ repo

    Rewrites a rough prompt, voice dump, or half-written instruction into an agent-ready prompt. Use when the user asks to make a prompt better, enhance/refine a prompt, clean up instructions for an agent, or improve pasted prompt text. One-shot transformer; does not interview.

  • Cpu memory tuning starter

    ma-compbio-lab/SkillFoundry/skills/hpc/cpu-memory-tuning-starter Skill

    44★ repo

    A framework for discovering, compiling, and validating reusable skills for scientific agents.

  • Materials benchmark datasets starter

    ma-compbio-lab/SkillFoundry/skills/materials-science-and-engineering/materials-benchmark-datasets-starter Skill

    44★ repo

    A framework for discovering, compiling, and validating reusable skills for scientific agents.

  • Inspect evaluation harness starter

    ma-compbio-lab/SkillFoundry/skills/scientific-agents-and-automation/inspect-evaluation-harness-starter Skill

    44★ repo

    A framework for discovering, compiling, and validating reusable skills for scientific agents.

  • Langgraph planning execution agent starter

    ma-compbio-lab/SkillFoundry/skills/scientific-agents-and-automation/langgraph-planning-execution-agent-starter Skill

    44★ repo

    A framework for discovering, compiling, and validating reusable skills for scientific agents.

  • Long horizon agent memory and provenance starter

    ma-compbio-lab/SkillFoundry/skills/scientific-agents-and-automation/long-horizon-agent-memory-and-provenance-starter Skill

    44★ repo

    A framework for discovering, compiling, and validating reusable skills for scientific agents.

  • Benchmark table mining starter

    ma-compbio-lab/SkillFoundry/skills/scientific-knowledge/benchmark-table-mining-starter Skill

    44★ repo

    Parse small benchmark markdown tables from paper notes and summarize datasets, metrics, and best-performing methods.

  • Knowledge base injection

    itallstartedwithaidea/agent-skills/skills/ai-agent-engineering/knowledge-base-injection Skill

    44★ repo

    Knowledge Base Injection is the technique of dynamically injecting domain expertise into an agent's context at the moment it is most relevant, using TF-IDF pattern matching and semantic scoring.

    The same file is in 1 other repository

  • Mcp server creation

    itallstartedwithaidea/agent-skills/skills/ai-agent-engineering/mcp-server-creation Skill

    44★ repo

    MCP Server Creation is the skill of building Model Context Protocol servers that expose tools, resources, and capabilities to AI agents through a standardized interface.

    The same file is in 1 other repository

  • Memory persistence

    itallstartedwithaidea/agent-skills/skills/ai-agent-engineering/memory-persistence Skill

    44★ repo

    Memory Persistence enables AI agents to maintain knowledge across sessions, transforming stateless inference calls into stateful, continuously improving systems.

    The same file is in 1 other repository

  • Parallel agent orchestration

    itallstartedwithaidea/agent-skills/skills/ai-agent-engineering/parallel-agent-orchestration Skill

    44★ repo

    Parallel Agent Orchestration is the discipline of dispatching, coordinating, and aggregating results from multiple concurrent subagents to dramatically accelerate complex tasks.

    The same file is in 1 other repository

  • Agent instinct system

    itallstartedwithaidea/agent-skills/skills/claude-mythos/agent-instinct-system Skill

    44★ repo

    The Agent Instinct System implements pre-cognitive reflexes — automatic safety checks and validations that fire before every code change, tool call, or output generation.

    The same file is in 1 other repository

  • Context engineering

    itallstartedwithaidea/agent-skills/skills/claude-mythos/context-engineering Skill

    44★ repo

    Context Engineering is the discipline of maximizing agent output quality while minimizing token expenditure.

    The same file is in 1 other repository

  • Multi harness portability

    itallstartedwithaidea/agent-skills/skills/claude-mythos/multi-harness-portability Skill

    44★ repo

    Multi-Harness Portability is the engineering discipline of writing agent skills, prompts, and configurations that work across every major AI coding harness — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and beyond.

    The same file is in 1 other repository

  • Prompt architecture

    itallstartedwithaidea/agent-skills/skills/claude-mythos/prompt-architecture Skill

    44★ repo

    Prompt Architecture is the structural engineering of agent instructions.

    The same file is in 1 other repository

  • Knowledge base rag

    itallstartedwithaidea/agent-skills/skills/productivity/knowledge-base-rag Skill

    44★ repo

    Knowledge Base RAG implements the complete Retrieval-Augmented Generation pipeline: document ingestion, intelligent chunking, embedding generation, vector store indexing, semantic retrieval, and grounded response generation.

  • Workflow orchestration

    itallstartedwithaidea/agent-skills/skills/productivity/workflow-orchestration Skill

    44★ repo

    Workflow Orchestration provides a visual AI flow-building framework with MCP plugin support, conditional branching, parallel execution, and error recovery.

  • Agent security scanning

    itallstartedwithaidea/agent-skills/skills/security/agent-security-scanning Skill

    44★ repo

    Agent Security Scanning detects vulnerabilities in AI-generated code before it reaches production.

  • Subagent driven development

    itallstartedwithaidea/agent-skills/skills/software-dev/subagent-driven-development Skill

    44★ repo

    Subagent-Driven Development dispatches each discrete task to a fresh subagent with a clean context window, then subjects the output to a two-stage review before merging.

  • Kai hook bench

    cgallic/kai-cmo-harness/harness/skills/kai-hook-bench Skill

    no license43★ repo

    Generate, rank, and gate a reusable hook bank — sourced pains × named hook formula families, scored on clarity/specificity/curiosity/proof-backing, gated at the 10/16 ad threshold, delivered in 3 lengths with per-hook provenance and downstream routing. Use when "hook bank", "generate hooks", "hook generator", "write hooks for", "ad hooks", "scroll stoppers", "opening lines", "hook ideas", "first 3 seconds", "hook matrix", "I need 50 hooks", or any request to batch-produce attention-openers for ads, social, or video.

    The same file is in 2 other repositories