agentsclimarketplace

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

  • Agent mail automation

    goharabbas321/zeoel-framework/all-skills/awesome-claude-skills/composio-skills/agent-mail-automation Skill

    no license0★ repo

    Automate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.

    The same file is in 6 other repositories

  • Benchmark email automation

    goharabbas321/zeoel-framework/all-skills/awesome-claude-skills/composio-skills/benchmark-email-automation Skill

    no license0★ repo

    Automate Benchmark Email tasks via Rube MCP (Composio). Always search tools first for current schemas.

    The same file is in 6 other repositories

  • Mcp builder

    goharabbas321/zeoel-framework/all-skills/awesome-claude-skills/mcp-builder Skill

    no license0★ repo

    Guide 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).

    The same file is in 18 other repositories

  • Skill creator

    goharabbas321/zeoel-framework/all-skills/awesome-claude-skills/skill-creator Skill

    no license0★ repo

    Guide 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.

    The same file is in 16 other repositories

  • Benchmark

    goharabbas321/zeoel-framework/all-skills/benchmark Skill

    no license0★ repo

    Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.

    The same file is in 2 other repositories

  • Claude devfleet

    goharabbas321/zeoel-framework/all-skills/claude-devfleet Skill

    no license0★ repo

    Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

    The same file is in 6 other repositories

  • Agent mail automation

    goharabbas321/zeoel-framework/all-skills/composio-skills/agent-mail-automation Skill

    no license0★ repo

    Automate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.

    The same file is in 6 other repositories

  • Benchmark email automation

    goharabbas321/zeoel-framework/all-skills/composio-skills/benchmark-email-automation Skill

    no license0★ repo

    Automate Benchmark Email tasks via Rube MCP (Composio). Always search tools first for current schemas.

    The same file is in 6 other repositories

  • Continuous agent loop

    goharabbas321/zeoel-framework/all-skills/continuous-agent-loop Skill

    no license0★ repo

    Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

    The same file is in 5 other repositories

  • Cost aware llm pipeline

    goharabbas321/zeoel-framework/all-skills/cost-aware-llm-pipeline Skill

    no license0★ repo

    Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

    The same file is in 9 other repositories

  • Data scraper agent

    goharabbas321/zeoel-framework/all-skills/data-scraper-agent Skill

    no license0★ repo

    Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

    The same file is in 8 other repositories

  • Dmux workflows

    goharabbas321/zeoel-framework/all-skills/dmux-workflows Skill

    no license0★ repo

    Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

    The same file is in 5 other repositories

  • Enterprise agent ops

    goharabbas321/zeoel-framework/all-skills/enterprise-agent-ops Skill

    no license0★ repo

    Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

    The same file is in 7 other repositories

  • Eval harness

    goharabbas321/zeoel-framework/all-skills/eval-harness Skill

    no license0★ repo

    Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

    The same file is in 9 other repositories

  • Healthcare eval harness

    goharabbas321/zeoel-framework/all-skills/healthcare-eval-harness Skill

    no license0★ repo

    Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures.

    The same file is in 2 other repositories

  • Knowledge ops

    goharabbas321/zeoel-framework/all-skills/knowledge-ops Skill

    no license0★ repo

    Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.

    The same file is in 1 other repository

  • Llm trading agent security

    goharabbas321/zeoel-framework/all-skills/llm-trading-agent-security Skill

    no license0★ repo

    Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.

    The same file is in 2 other repositories

  • Mcp builder

    goharabbas321/zeoel-framework/all-skills/mcp-builder Skill

    no license0★ repo

    Guide 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).

    The same file is in 18 other repositories

  • Mcp server builder

    goharabbas321/zeoel-framework/all-skills/mcp-server-builder Skill

    no license0★ repo

    Build custom MCP (Model Context Protocol) servers for AI tool integration. Covers server architecture, tool definitions, resource providers, and deployment.

  • Mcp server patterns

    goharabbas321/zeoel-framework/all-skills/mcp-server-patterns Skill

    no license0★ repo

    Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

    The same file is in 2 other repositories

  • Prompt engineering

    goharabbas321/zeoel-framework/all-skills/prompt-engineering Skill

    no license0★ repo

    Systematic prompt design patterns. Covers system prompts, few-shot examples, chain-of-thought, structured output, and evaluation strategies.

  • Prompt optimizer

    goharabbas321/zeoel-framework/all-skills/prompt-optimizer Skill

    no license0★ repo

    Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

    The same file is in 2 other repositories

  • Rag pipeline

    goharabbas321/zeoel-framework/all-skills/rag-pipeline Skill

    no license0★ repo

    Retrieval-Augmented Generation (RAG) pipeline patterns. Covers document ingestion, chunking, embeddings, vector search, and answer generation.

  • Ralphinho rfc pipeline

    goharabbas321/zeoel-framework/all-skills/ralphinho-rfc-pipeline Skill

    no license0★ repo

    RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

    The same file is in 7 other repositories

  • Recsys pipeline architect

    goharabbas321/zeoel-framework/all-skills/recsys-pipeline-architect Skill

    no license0★ repo

    Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

    The same file is in 3 other repositories

  • Regex vs llm structured text

    goharabbas321/zeoel-framework/all-skills/regex-vs-llm-structured-text Skill

    no license0★ repo

    Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

    The same file is in 7 other repositories

  • Security scan

    goharabbas321/zeoel-framework/all-skills/security-scan Skill

    no license0★ repo

    Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

    The same file is in 9 other repositories

  • Skill creator

    goharabbas321/zeoel-framework/all-skills/skill-creator Skill

    no license0★ repo

    Guide 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.

    The same file is in 16 other repositories

  • Skill stocktake

    goharabbas321/zeoel-framework/all-skills/skill-stocktake Skill

    no license0★ repo

    Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

    The same file is in 3 other repositories

  • Dispatching parallel agents

    goharabbas321/zeoel-framework/all-skills/superpowers/skills/dispatching-parallel-agents Skill

    no license0★ repo

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

    The same file is in 13 other repositories

  • Subagent driven development

    goharabbas321/zeoel-framework/all-skills/superpowers/skills/subagent-driven-development Skill

    no license0★ repo

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

    The same file is in 6 other repositories

  • Compress

    noman3271/caveman/plugins/caveman/skills/compress Skill

    0★ repo

    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"

    The same file is in 3 other repositories

  • Compress

    noman3271/caveman/skills/compress Skill

    0★ repo

    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"

    The same file is in 3 other repositories

  • Skill creator

    mpuig/raw/skills/skill-creator Skill

    no license0★ repo

    Create Agent Skills that comply with the agentskills.io specification. Use when the user asks to create a new skill, add agent capabilities, or build reusable instructions.

  • Mcp builder

    senior-sigan/llm-skills/skills/mcp-builder Skill

    no license0★ repo

    Guide 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).

  • Memory curator

    gagip/gagip-dev/plugins/common/skills/memory-curator Skill

    no license0★ repo

    대화 세션에서 유의미한 정보/패턴을 메모리에 즉시 저장하고, 쌓인 메모리를 주기적으로 정리하는 스킬. 두 가지 모드로 동작한다: - 기본 모드 (`/memory-curator`): 현재 세션 JSONL을 분석해 놓친 메모리를 추출하고 저장 - 리뷰 모드 (`/memory-curator review`): 전체 메모리 파일을 정리하고 CLAUDE.md 승격 후보 및 문서화 대상 제안 다음 표현이 나오면 반드시 이 스킬을 사용할 것: "메모리 정리해줘", "세션 메모리 저장해줘", "memory curator", "메모리 큐레이션", "메모리 리뷰", "memory review", "지침 정리해줘", "문서화할 거 추려줘", "이번 세션 메모리", "놓친 메모리 있어?", "메모리 업데이트해줘"

  • Worktree scaffold

    gagip/gagip-dev/plugins/common/skills/worktree-scaffold Skill

    no license0★ repo

    레포의 환경·특이사항을 분석해 그 레포 전용 git worktree 부트스트랩 스크립트(`scripts/worktree-create.sh`)를 일관된 골격으로 생성하는 스킬. `git worktree add`가 자동으로 안 딸려오는 것 — 추적 제외된 머신·환경 설정 (`.env`·`local.properties`·keystore 등), 체크아웃마다 새로 만들어야 하는 산출물(node_modules·네이티브 생성물·git hooks), 동시 실행 시 충돌하는 자원(dev 서버 포트·임시 디렉터리) — 을 자동 감지해, 복사(A)·재생성(B)·격리(C) 3단계와 실패 롤백을 갖춘 스크립트를 만든다. 스킬 자신이 매번 세팅하는 게 아니라, 레포에 남아 재사용되는 스크립트를 짜주는 생성기다. 다음 표현이 나오면 반드시 이 스킬을 사용한다: "worktree 셋업 스크립트 만들어줘", "worktree 생성 스크립트 짜줘", "worktree bootstrap 스크립트", "새 worktree에서 바로 개발되게 해줘", "worktree 만들면 .env/설정 자동 복사되게", "병렬 작업용 worktree 스크립트", "worktree-create.sh 만들어줘". worktree를 새로 만들면 빌드가 깨지거나 설정 파일이 없어 매번 손으로 채운다고 호소할 때도, 사용자가 명시적으로 "스크립트"라 부르지 않아도 이 스킬로 해결한다.

  • Prompt structure writer

    andresnator/agents-orchestrator/skills/prompt-structure-writer Skill

    0★ repo

    Trigger: improve prompt, rewrite prompt, prompt structure, prompt para agente, ordenar instrucciones, convertir idea en prompt, prompt review, prompt evaluation, evaluar prompt. Convert loose ideas, rough instructions, or messy text into clear, brief, executable prompts for local agents such as Codex, Claude Code, OpenCode, and similar runtimes.

  • Skill creator

    andresnator/agents-orchestrator/skills/skill-creator Skill

    0★ repo

    Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

  • Gpt

    metrovoc/cc-skill-opencode/skills/gpt Skill

    no license0★ repo

    Use GPT for long-running coding tasks: large refactors, feature implementation etc.

  • Codex orchestrator

    Moliboy5000/.claude/plugins/cache/codex-orchestrator-marketplace/codex-orchestrator/1.0.0/skills/codex-orchestrator Skill

    no license0★ repo

    DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.

  • Skill copilot provider

    Moliboy5000/.claude/plugins/cache/nyldn-plugins/octo/9.30.0/skills/skill-copilot-provider Skill

    no license0★ repo

    GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode. Use when: AUTOMATICALLY ACTIVATE when user says:. "copilot provider" or "add copilot" or "github copilot" or "use copilot"

  • Skill meta prompt

    Moliboy5000/.claude/plugins/cache/nyldn-plugins/octo/9.30.0/skills/skill-meta-prompt Skill

    no license0★ repo

    Craft better prompts using proven optimization techniques — use when your prompt needs refinement. Use when: Use PROACTIVELY when user wants to:. "create a prompt for", "write a prompt for". "optimize this prompt", "improve this prompt"

  • Skill parallel agents

    Moliboy5000/.claude/plugins/cache/nyldn-plugins/octo/9.30.0/skills/skill-parallel-agents Skill

    no license0★ repo

    Multi-tentacled orchestration using Double Diamond methodology. Use when: PRIORITY TRIGGERS (always invoke immediately):. "/octo:multi" (explicit command). "run this with all providers", "run with all providers"

  • Mcp setup

    Moliboy5000/.claude/plugins/cache/omc/oh-my-claudecode/4.8.2/skills/mcp-setup Skill

    no license0★ repo

    Configure popular MCP servers for enhanced agent capabilities

  • Writer memory

    Moliboy5000/.claude/plugins/cache/omc/oh-my-claudecode/4.8.2/skills/writer-memory Skill

    no license0★ repo

    Agentic memory system for writers - track characters, relationships, scenes, and themes

  • Benchmark models

    Moliboy5000/.claude/skills/benchmark-models Skill

    no license0★ repo

    Claude dotfile containing skills, agents etc I use.

  • Benchmark

    Moliboy5000/.claude/skills/benchmark Skill

    no license0★ repo

    Claude dotfile containing skills, agents etc I use.

  • Figma

    Moliboy5000/.claude/skills/figma Skill

    no license0★ repo

    Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.

    The same file is in 5 other repositories

  • Opencode workflow

    Moliboy5000/.claude/skills/opencode-workflow Skill

    no license0★ repo

    Full OpenCode delegation workflow — routing rules, agent-to-role mapping, model routing, invocation patterns, and examples for delegating tasks to OpenCode (GitHub Copilot). Use when delegating heavy work to OpenCode or making one-shot queries via opencode-ask.

  • Pair agent

    Moliboy5000/.claude/skills/pair-agent Skill

    no license0★ repo

    Claude dotfile containing skills, agents etc I use.

  • Skill creator

    Moliboy5000/.claude/skills/skill-creator Skill

    no license0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Llm security audit

    ismael-joffroy-chandoutis/claude-skills-public/llm-security-audit Skill

    no license0★ repo

    Comprehensive security auditing framework for LLM applications covering OWASP Top 10 for LLMs, threat modeling, penetration testing, and compliance with NIST AI RMF and ISO 42001

  • Prompt injection defense

    ismael-joffroy-chandoutis/claude-skills-public/prompt-injection-defense Skill

    no license0★ repo

    Claude Code skills for game design, procedural generation, LLM security, and AI-art consistency

  • Prompt to game

    ismael-joffroy-chandoutis/claude-skills-public/prompt-to-game Skill

    no license0★ repo

    Master the art of "vibe coding" - creating playable games through natural language prompts to AI. Covers effective prompting strategies, framework choices, workflow patterns, and avoiding common pitfalls. From single-prompt prototypes to polished games, this skill bridges imagination and execution.

  • Skill builder

    Stoica-Mihai/claude-skills/plugins/skill-builder/skills/skill-builder Skill

    0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance with **unbiased blind evaluations**. Drop-in replacement for `skill-creator` that fixes its central design flaw — the same agent writing the skill also writing the tests, which lets implementation knowledge contaminate prompt selection. `skill-builder` delegates eval authoring to a blind subagent that sees only the skill's name + description, never the SKILL.md body, scripts, or fixtures. Use whenever the user wants to create, modify, or benchmark a skill, or optimize a skill's description for triggering accuracy.

  • Handoff create

    danielsitek/skills/skills/handoff-create Skill

    0★ repo

    Save a task or topic from the current conversation into a numbered handoff file under .handoffs/ so it can be picked up later. Use this skill whenever the user explicitly asks to park, stash, set aside, snapshot, or "hand off" something from the conversation for later — phrases like "create a handoff", "save this as a handoff", "park this for later", "stash this task", "ulož to na pozdéji", or just "handoff" while mid-conversation. Do NOT trigger based on the content of another agent's output (e.g. a task list, recommendations, or a "Following steps" section). An explicit intent signal from the user is required — the mere presence of future-oriented content in a response is NOT sufficient. Supports two modes: a focused excerpt of the relevant part (default) and a verbatim dump of the last N messages.

  • Handoff invoke

    danielsitek/skills/skills/handoff-invoke Skill

    0★ repo

    Load a previously saved handoff file from .handoffs/ and resume the parked task. Use this skill whenever the user wants to pick up, resume, open, reopen, continue, or "invoke" a handoff — phrases like "invoke handoff 3", "open handoff-0002", "let's pick up that handoff", "resume the handoff about the API rate limiting", "pokračuj s handoffem". Trigger even if the user only gives a number or a rough topic instead of an exact filename. This skill orients the user on what the handoff contains before any work starts — it does not delete the file. Also trigger when the user asks whether a parked task is still relevant or up to date.

  • Handoff list

    danielsitek/skills/skills/handoff-list Skill

    0★ repo

    List all saved handoff files in .handoffs/ with their summaries so the user can see what tasks they have parked. Use this skill whenever the user wants an overview of their handoffs — phrases like "list handoffs", "what handoffs do I have", "show my parked tasks", "what did I stash", "vypiš handoffy". Trigger whenever the user wants to know what is waiting in the handoff queue, even without the exact word "list".

  • Vscode copilot customization

    danielsitek/skills/skills/vscode-copilot-customization Skill

    0★ repo

    Expert guide for creating GitHub Copilot customization files in VS Code: custom instructions (.instructions.md), prompt files (.prompt.md), custom agents (.agent.md), agent skills (SKILL.md), hooks (JSON), and agent plugins. Use this skill whenever the user asks about customizing Copilot behavior, creating reusable AI workflows, writing copilot-instructions.md, building custom chat agents, automating Copilot tasks with prompt files, or setting up agent skills and hooks in VS Code. Also trigger when the user asks which Copilot customization type to use for a given scenario — always start with the decision matrix below.