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

  • Agentprivacy wiki llm knowledge base

    mitchuski/agentprivacy-skills/agentprivacy-skills-v5/wikis/agentprivacy-wiki-llm-knowledge-base Skill

    1★ repo

    Building and maintaining a persistent, LLM-maintained knowledge base — the LLM-Wiki pattern: an LLM incrementally compiles immutable raw sources into a cross-linked, self-consistent wiki it owns, governed by a schema, via ingest / query / lint, with a content index and a chronological log. Activates when designing a knowledge base, ingesting sources into a wiki, health-checking one, or mapping the pattern onto the agentprivacy federation (which IS an instance of it). Part of the git-less onboarding/distribution layer kept by the Librarian 🗃️ in the Tower's Wikis.

  • Agentprivacy wiki skill anatomy

    mitchuski/agentprivacy-skills/agentprivacy-skills-v5/wikis/agentprivacy-wiki-skill-anatomy Skill

    1★ repo

    What a Claude Code skill is — the SKILL.md folder format, frontmatter, storage location, and how skills are invoked (auto via description, or explicitly via /skill-name). Activates when explaining skills to a newcomer, authoring a new skill, or onboarding an agent into the skill model. The conceptual entry to the Librarian's 🗃️ Wikis.

  • Fastmcp

    Eng-Muhammad-Affan/digital-fte/.qwen/skills/fastmcp Skill

    no license1★ repo

    Build MCP servers in Python with FastMCP framework to expose tools, resources, and prompts to LLMs. Supports storage backends (memory/disk/Redis), middleware, OAuth Proxy, OpenAPI integration, and FastMCP Cloud deployment. Use when: creating MCP servers, defining tools or resources, implementing OAuth authentication, configuring storage backends for tokens/cache, adding middleware for logging/rate limiting, deploying to FastMCP Cloud, or troubleshooting module-level server, storage, lifespan, middleware order, circular imports, or OAuth errors. Keywords: FastMCP, MCP server Python, Model Context Protocol Python, fastmcp framework, mcp tools, mcp resources, mcp prompts, fastmcp storage, fastmcp memory storage, fastmcp disk storage, fastmcp redis, fastmcp dynamodb, fastmcp lifespan, fastmcp middleware, fastmcp oauth proxy, server composition mcp, fastmcp import, fastmcp mount, fastmcp cloud, fastmcp deployment, mcp authentication, fastmcp icons, openapi mcp, claude mcp server, fastmcp testing, storage misconfiguration, lifespan issues, middleware order, circular imports, module-level server, async await mcp

  • Mcp chrome devtools

    Eng-Muhammad-Affan/digital-fte/.qwen/skills/mcp-chrome-devtools Skill

    no license1★ repo

    This skill provides guidance for using Chrome DevTools MCP for browser debugging and automation. Use when debugging web pages, analyzing performance, inspecting network requests, viewing console messages, or interacting with Chrome DevTools features programmatically.

  • Knowledge consolidation

    bingooyong/agent-skills/skills/knowledge-consolidation Skill

    no license1★ repo

    Review completed work and consolidate learnings into long-term knowledge artifacts. Use when (1) a task or session is finishing and you want to capture durable insights, (2) deciding what belongs in AGENTS.md vs memory vs project docs, (3) surfacing reusable patterns from one-off work, (4) generating concrete update patches for knowledge files. Outputs prioritized suggestions with exact file locations and diffs.

  • Memory governance

    bingooyong/agent-skills/skills/memory-governance Skill

    no license1★ repo

    Govern AI agent memory files: classify, deduplicate, validate, and curate what goes into long-term memory. Use when (1) deciding if a preference or pattern should be saved to memory, (2) auditing memory for stale or conflicting entries, (3) deduplicating overlapping memories, (4) enforcing memory hygiene rules. Prevents memory bloat and ensures only stable, verified, reusable knowledge persists.

  • Rag search

    kuc-arc-f/agent_skills_2ex/skill-rag-1/.claude/skills/rag_search Skill

    no license1★ repo

    検索クエリーから、RAG 検索する

  • Rag search

    kuc-arc-f/agent_skills_2ex/skill-rag-3/.claude/skills/rag_search Skill

    no license1★ repo

    検索クエリーから、RAG 検索する

  • Rag search

    kuc-arc-f/agent_skills_2ex/skill-rag-4/.claude/skills/rag_search Skill

    no license1★ repo

    検索クエリーから、RAG 検索する

  • Rag search

    kuc-arc-f/agent_skills_2ex/skill-rag-5/.claude/skills/rag_search Skill

    no license1★ repo

    検索クエリーから、RAG 検索する

  • Rag embed

    kuc-arc-f/agent_skills_2ex/skills-example-5/.claude/skills/rag_embed Skill

    no license1★ repo

    ローカルchromadbに、ベクトルデータ登録する。

  • Rag search

    kuc-arc-f/agent_skills_2ex/skills-example-5/.claude/skills/rag_search Skill

    no license1★ repo

    検索クエリー(query) から、RAG検索結果を表示する。

  • Cc switch claude provider

    kiakun-collab/kiakun-skills/skills/cc-switch-claude-provider Skill

    no license1★ repo

    Configure Claude Code through local CC Switch with a third-party Anthropic or Claude-compatible base URL and API key. Use when the user wants "just give base URL + key and make Claude Code usable", wants to switch Claude Code to a third-party provider without manual editing, or wants CC Switch provider creation, provider switching, and a real Claude Code smoke test automated.

  • Clean deliverable

    kiakun-collab/kiakun-skills/skills/clean-deliverable Skill

    no license1★ repo

    纯净交付守卫(模型通用)。用于在"生成"或"审查"交付物(幻灯片、文案、报告、邮件、代码等)时, 防止元信息泄漏到成品里——包括自造占位符("符合营销话术的标题")、回声输入(把用户给的 要点/约束/设计依据原样贴进成品)、以及思考过程残留。适用于任何生成式模型(GPT、Gemini、 Claude 及本会话中的我自己)。三种用法:①产出可粘贴到任意目标模型的约束提示词; ②审查并清洗一份已有交付物(含图片类,给出重生成提示词);③我自己生成交付物时的交付前自检。 触发词:纯净交付、清洗交付物、防元信息泄漏、约束提示词、别把要点写进成品、 clean deliverable、anti meta leak。

  • Gpt image 2 api

    kiakun-collab/kiakun-skills/skills/gpt-image-2-api Skill

    no license1★ repo

    Generate or edit images with XApex asynchronous tasks as the default route, AtlasCloud as the first edit fallback, and aifast as the final fallback, plus forced-provider profiles and batch generation. Use for text-to-image, local or URL reference editing, multi-reference composition, precision-sensitive graphics, XApex image-group tokens, provider-specific sizes and quality, resilient routing, and batch jobs.

  • Improve claude config

    yu-iskw/coding-agent-fabric/.claude/skills/improve-claude-config Skill

    1★ repo

    Self-improvement skill for evolving Claude Code configuration. Use when you notice repeated mistakes, want to add new workflows, or optimize the development experience.

  • Mcp builder

    yunseo-kim/agent-toolbox/.agents/skills/mcp-builder Skill

    no license1★ 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).

  • Skill creator

    yunseo-kim/agent-toolbox/.agents/skills/skill-creator Skill

    no license1★ 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 6 other repositories

  • Google adk guide

    yunseo-kim/agent-toolbox/catalog/skills/google-adk-guide Skill

    no license1★ repo

    Guide to building AI agents with Google Agent Development Kit covering agent creation, tool integration, memory, callbacks, plugins, and multi-agent orchestration

  • Llm memory patterns

    yunseo-kim/agent-toolbox/catalog/skills/llm-memory-patterns Skill

    no license1★ repo

    Implementation patterns for LLM memory systems covering conversation buffers, persistent vector memory, bidirectional storage, local-private memory, and agentic memory

  • Mcp builder

    yunseo-kim/agent-toolbox/catalog/skills/mcp-builder Skill

    no license1★ 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).

  • Openai agents guide

    yunseo-kim/agent-toolbox/catalog/skills/openai-agents-guide Skill

    no license1★ repo

    Guide to building AI agents with the OpenAI Agents SDK covering agent creation, tool use, context management, guardrails, handoffs, multi-agent orchestration, and tracing

  • Rag patterns

    yunseo-kim/agent-toolbox/catalog/skills/rag-patterns Skill

    no license1★ repo

    Implementation patterns for Retrieval-Augmented Generation covering basic chains, corrective RAG, hybrid search, knowledge graphs with community detection, agentic RAG, multimodal retrieval, and reasoning-based vectorless RAG

  • Skill creator

    yunseo-kim/agent-toolbox/catalog/skills/skill-creator Skill

    no license1★ repo

    Guide for creating effective skills that extend AI assistant capabilities with specialized knowledge, workflows, and tool integrations. Use when creating or updating skills.

  • Setup

    CleanSlice/skills/setup Skill

    no license1★ repo

    Install the CleanSlice MCP server and required development skills for Claude Code. Run this when setting up Claude Code for the first time in this project.

  • Llm integration

    medy-gribkov/arcana/skills/llm-integration Skill

    1★ repo

    Integrate OpenAI and Anthropic APIs with streaming, structured output, tool calling, token management, and cost optimization

  • Memory management

    medy-gribkov/arcana/skills/memory-management Skill

    1★ repo

    Game memory optimization, object pooling, garbage collection tuning, and efficient resource management for target platforms.

  • Skill creator

    medy-gribkov/arcana/skills/skill-creator Skill

    1★ repo

    Create or update Claude skills. Use for new skills, skill references, skill scripts, optimizing existing skills, extending Claude's capabilities.

  • 03 fictional companion forge

    Aliciawque/openclaw-personalized-agent-forge/03-fictional-companion-forge Skill

    no license1★ repo

    Turn a fictional character from games, films, TV, novels, comics, or anime into a deployable OpenClaw companion agent. Use when the user names a character such as Ghost, König, Keegan, Hermione, Tony Stark, Cloud, or any other fictional persona, or asks for things like "turn this character into an AI companion", "let me talk to this character", "restore this character's personality", or "generate an agent based on this fictional role". Produce a character-faithful package centered on `soul.md`, `identity.md`, `memory.md`, and `agents.md`.

  • Delegation

    primeline-ai/primeline-skills/skills/delegation Skill

    1★ repo

    Use when facing any non-trivial task to decide whether to handle it yourself or delegate to a subagent. Provides score-based routing, model selection, and structured prompt templates for effective delegation.

  • Customer support agent

    skillsdirectory/claude-skills/skills/customer-support-agent Skill

    no license1★ repo

    Build AI-powered customer support systems with knowledge base access, ticket routing, and empathetic responses. Adapted from Anthropic's Claude Quickstarts.

    The same file is in 1 other repository

  • Prompt engineer

    skillsdirectory/claude-skills/skills/prompt-engineer Skill

    no license1★ repo

    Master prompt engineering with classification, summarization, and advanced techniques. Based on Anthropic's Claude Cookbooks and Courses.

    The same file is in 1 other repository

  • Rag specialist

    skillsdirectory/claude-skills/skills/rag-specialist Skill

    no license1★ repo

    Build Retrieval Augmented Generation (RAG) pipelines with vector databases, embeddings, and context-aware responses. Adapted from Anthropic's Claude Cookbooks.

    The same file is in 1 other repository

  • Tool use architect

    skillsdirectory/claude-skills/skills/tool-use-architect Skill

    no license1★ repo

    Design and implement Claude tool/function calling patterns with error handling, parallel execution, and validation. Based on Anthropic's Claude Cookbooks.

    The same file is in 1 other repository

  • Resume handoff

    corticalstack/flow/.claude/skills/resume-handoff Skill

    1★ repo

    Resume work from a handoff document, validating current state against it before continuing. Explicit-only; run only when invoked via /resume-handoff or explicitly asked.

  • Knowledge graph memory

    broomva/control-metalayer/.skills/knowledge-graph-memory Skill

    1★ repo

    Bridge Claude Code conversation logs to an Obsidian knowledge graph for persistent agent memory. Transforms .entire/ event logs and ~/.claude/ transcripts into searchable, wikilinked markdown docs with full conversation threads, tool call details, and session metadata. Use when setting up conversation history capture, configuring knowledge graph traversal for agents, building episodic memory from session logs, or connecting agent work to an Obsidian vault. Triggers on "conversation history", "session logs to obsidian", "knowledge graph memory", "agent episodic memory", "conversation bridge", "session documentation", or "knowledge traversal".

  • Implementation agent

    coreline-ai/android-subagent-skill/skills/implementation-agent Skill

    1★ repo

    [Android App Development] [Claude Code] 구현 전담 Agent가 PRD, TRD, code-quality-guide.md를 바탕으로 안드로이드 프레임워크와 NDK 기반의 실제 앱 코드 및 테스트 코드를 안전하게 구현하도록 안내하는 스킬입니다.

  • Pipeline orchestrator agent

    coreline-ai/android-subagent-skill/skills/pipeline-orchestrator-agent Skill

    1★ repo

    [Android App Development] [Claude Code] 안드로이드 서브에이전트 파이프라인의 유일한 시작점이자 지휘 Agent입니다. 문서 상태와 handoff를 읽어 document-review, guide-generation, implementation, review 중 다음 worker를 결정하고, Reject 시 최대 3회 루프를 제어합니다.

  • Review agent

    coreline-ai/android-subagent-skill/skills/review-agent Skill

    1★ repo

    [Android App Development] [Claude Code] 리뷰 전담 Agent가 설계 의도 문서(design-intent.md)와 품질 가이드(code-quality-guide.md)를 통해 구현된 안드로이드 및 NDK 코드를 엄격히 리뷰하도록 안내하는 스킬입니다.

  • Skill creator

    0rcaaa/icron/icron/skills/skill-creator Skill

    1★ repo

    Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

    The same file is in 1 other repository

  • Do wdr issue swarm

    d-oit/do-web-doc-resolver/.agents/skills/do-wdr-issue-swarm Skill

    1★ repo

    Implement GitHub issues in parallel using a swarm of specialist agents with wave-based dependency resolution. Use when the user asks to "implement all issues", "fix all GitHub issues", "swarm issues", or wants to batch-implement multiple GitHub issues. Covers dependency analysis, parallel agent launch, atomic commits, GH Actions monitoring, and issue closing.

  • Skill creator

    d-oit/do-web-doc-resolver/.agents/skills/skill-creator Skill

    1★ 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.

  • Fr execute

    derio-net/super-fr/.hermes/skills/fr/fr-execute Skill

    1★ repo

    Execute an agentic phase from a plan. Use when implementing assigned work from a plan file. Agent-facing skill.

  • Fr execute

    derio-net/super-fr/.opencode/skills/fr-execute Skill

    1★ repo

    Execute an agentic phase from a plan. Use when implementing assigned work from a plan file. Agent-facing skill.

  • Fr execute

    derio-net/super-fr/plugins/super-fr/skills/fr-execute Skill

    1★ repo

    Execute an agentic phase from a plan. Use when implementing assigned work from a plan file. Agent-facing skill.

  • Skill creator

    yugasun/skills/skills/skill-creator Skill

    1★ 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 19 other repositories

  • Skill creator

    eglenn-dev/dt-skills/skills/skill-creator Skill

    no license1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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 2 other repositories

  • Creating eval plan

    jek-bao-choo/productivity-plugins/sales-process/skills/creating-eval-plan Skill

    1★ repo

    Generate modular Evaluation Plan CSV files for Datadog Home Run POC/Trial management. Combines solution-area modules (Infrastructure, APM, Logs, Cloud SIEM, LLM Observability, NDM, RUM, Synthetics, CCM, Security, DBM, Incident Management, BitsAI, Service Management) into a 4-column CSV (Depth, Title, Description, Success Criteria) ready for upload to Home Run. Use when the user asks to create an evaluation plan, eval plan, POC plan, trial plan, Home Run template, or mentions "evaluation plan", "eval plan", "POC plan", "Home Run CSV", or "trial template".

  • Write a skill

    corneliu-iancu/skills/skills/productivity/write-a-skill Skill

    no license1★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

  • Ralph wiggum loop

    xpepper/pr-review-agent-skill/ralph-wiggum-loop Skill

    no license1★ repo

    Use when context window exhaustion is a concern or when addressing a large volume of PR comments — spawns a fresh agent session per comment via an external shell loop. For an in-session approach, use pr-review-loop or copilot-review-loop instead.

  • Figma

    michelve/hugin-cowork/skills/figma Skill

    1★ repo

    This skill should be used when the user provides Figma URLs or node IDs, asks about design-to-code implementation, or needs to set up or troubleshoot the Figma MCP server. It uses the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma and translate Figma nodes into production code.

  • Miro mcp

    michelve/hugin-cowork/skills/miro-mcp Skill

    1★ repo

    This skill should be used when the user asks about Miro capabilities, wants to create content on Miro boards, or needs to work with Miro board data. It teaches how to use Miro MCP tools effectively for creating diagrams, documents, tables, and extracting context from Miro boards.

  • Ski memory manager

    luisdomarco/AiAgentArchitect/.agents/layers/memory/skills/ski-memory-manager Skill

    no license1★ repo

    Manages lightweight persistent memory files for cross-session project context. Use when a workflow needs to save or retrieve a condensed summary of previous work on a project to enable fast startup without re-reading full context ledgers.

  • Ski layer embed

    luisdomarco/AiAgentArchitect/.agents/skills/ski-layer-embed Skill

    no license1★ repo

    Embeds, unembeds or updates a modular layer into a destination system (root or subsystem) by reading its MANIFEST.yaml, copying entities to the correct platform directories, injecting context-root sections (CLAUDE.md/AGENTS.md), wiring hooks (settings.json), updating the destination's manifest, and resolving dependencies. Use when activating, deactivating or upgrading any layer (qa, memory, context-ledger, mcp, help-router, onboarding, etc.) on AiAgentArchitect itself or on any generated subsystem.

  • Ski output claude code

    luisdomarco/AiAgentArchitect/.agents/skills/ski-output-claude-code Skill

    no license1★ repo

    Converts a generated Google Antigravity entity into its Claude Code equivalent, applying directory mapping, path transformations, CC-specific frontmatter injection, and settings.json hook entry generation. Use after generating the GA version of each entity in Step 3.

  • Ski memory manager

    luisdomarco/AiAgentArchitect/.claude/layers/memory/skills/ski-memory-manager Skill

    no license1★ repo

    Manages lightweight persistent memory files for cross-session project context. Use when a workflow needs to save or retrieve a condensed summary of previous work on a project to enable fast startup without re-reading full context ledgers.

  • Ski memory manager

    luisdomarco/AiAgentArchitect/.claude/skills/ski-memory-manager Skill

    no license1★ repo

    Manages lightweight persistent memory files for cross-session project context. Use when a workflow needs to save or retrieve a condensed summary of previous work on a project to enable fast startup without re-reading full context ledgers.

  • Ski memory manager

    luisdomarco/AiAgentArchitect/.codex/layers/memory/skills/ski-memory-manager Skill

    no license1★ repo

    Manages lightweight persistent memory files for cross-session project context. Use when a workflow needs to save or retrieve a condensed summary of previous work on a project to enable fast startup without re-reading full context ledgers.

  • Ski layer embed

    luisdomarco/AiAgentArchitect/.codex/skills/ski-layer-embed Skill

    no license1★ repo

    Embeds, unembeds or updates a modular layer into a destination system (root or subsystem) by reading its MANIFEST.yaml, copying entities to the correct platform directories, injecting context-root sections (CLAUDE.md/AGENTS.md), wiring hooks (settings.json), updating the destination's manifest, and resolving dependencies. Use when activating, deactivating or upgrading any layer (qa, memory, context-ledger, mcp, help-router, onboarding, etc.) on AiAgentArchitect itself or on any generated subsystem.

  • Ski output claude code

    luisdomarco/AiAgentArchitect/.codex/skills/ski-output-claude-code Skill

    no license1★ repo

    Converts a generated Google Antigravity entity into its Claude Code equivalent, applying directory mapping, path transformations, CC-specific frontmatter injection, and settings.json hook entry generation. Use after generating the GA version of each entity in Step 3.