86403 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

crewai-setup

CrewAI multi-agent orchestration setup for collaborative AI systems

a5c-ai
a5c-ai
1,52087

few-shot-example-gen

Few-shot example generation and optimization for improved LLM performance

a5c-ai
a5c-ai
1,52087

dp-pattern-library

Maintain and match against a library of classic dynamic programming patterns. Provides pattern matching, template code generation, variant detection, and problem-to-pattern mapping for DP problems.

babysitter-sdk
babysitter-sdk
1,52087

dp-optimizer

Apply advanced DP optimizations automatically

a5c-ai
a5c-ai
1,52087

code-profiler

Profile code performance and identify bottlenecks

a5c-ai
a5c-ai
1,52087

rag-chunking-strategy

Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking

a5c-ai
a5c-ai
1,52087

closed-book-frontier-reasoning

Perform closed-book frontier reasoning — complex problem solving from internalized knowledge without external retrieval or tool use.

a5c-ai
a5c-ai
1,52087

qdrant-integration

Qdrant vector database with filtering, payloads, and quantization support

a5c-ai
a5c-ai
1,52087

prompt-template-design

Structured prompt template creation with variables, formatting, and version control

a5c-ai
a5c-ai
1,52087

prompt-injection-detector

Prompt injection detection and prevention for secure LLM applications

a5c-ai
a5c-ai
1,52087

nemo-guardrails

NVIDIA NeMo Guardrails configuration for conversational safety and control

a5c-ai
a5c-ai
1,52087

multi-turn-tool-use

Design agents for multi-turn tool use — sequential tool calls, result accumulation, error recovery, and complex task decomposition over multiple turns.

a5c-ai
a5c-ai
1,52087

session-management

Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.

a5c-ai
a5c-ai
1,52087

guardrails-ai-setup

Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.

a5c-ai
a5c-ai
1,52087

multi-app-orchestration

Orchestrate workflows across multiple applications and APIs — inter-app coordination, data handoff, and multi-system task completion.

a5c-ai
a5c-ai
1,52087

milvus-integration

Milvus distributed vector database configuration for large-scale RAG applications

a5c-ai
a5c-ai
1,52087

autonomous-research-engineering

Autonomous research engineering — web search orchestration, source synthesis, hypothesis formation, and structured research report generation.

a5c-ai
a5c-ai
1,52087

data-structure-selector

Select optimal data structure based on operation requirements

a5c-ai
a5c-ai
1,52087

code-template-manager

Manage and generate competitive programming templates

a5c-ai
a5c-ai
1,52087

cses-tracker

Track progress through CSES Problem Set with structured learning

a5c-ai
a5c-ai
1,52087

prompt-compression

Token-efficient prompt compression techniques for cost optimization

a5c-ai
a5c-ai
1,52087

medical-agent

Build medical AI agents for clinical decision support, medical record summarization, diagnostic assistance, and healthcare workflow automation.

a5c-ai
a5c-ai
1,52087

codeforces-api-client

Interface with Codeforces API for contest data, problem sets, and submissions

a5c-ai
a5c-ai
1,52087

mcp-host-styling-integration

Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.

a5c-ai
a5c-ai
1,52087

combinatorics-calculator

Calculate combinatorial values with modular arithmetic

a5c-ai
a5c-ai
1,52087

pinecone-integration

Pinecone vector database setup, configuration, and operations for RAG applications

a5c-ai
a5c-ai
1,52087

mcp-tool-resource-pattern

Implements the core MCP Apps architectural pattern where a Tool declares _meta.ui.resourceUri referencing a registered Resource. Covers registerAppTool, registerAppResource, text fallback, structuredContent, and app-only helper tools.

a5c-ai
a5c-ai
1,52087

pii-redaction

PII detection and redaction utilities for privacy-compliant conversational AI

a5c-ai
a5c-ai
1,52087

verification

Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.

a5c-ai
a5c-ai
1,52087

complexity-analyzer

Automated Big-O complexity analysis of code and algorithms. Performs static analysis of loop structures, recursive call trees, space complexity estimation, and amortized analysis with detailed derivation documents.

babysitter-sdk
babysitter-sdk
1,52087

constitution-creation

Establish project governing principles including dev guidelines, code quality standards, testing policies, UX requirements, performance benchmarks, and security constraints.

a5c-ai
a5c-ai
1,52087

background-job-processing

Implement reliable background job processing systems — queue management, retry policies, dead-letter handling, and distributed workers.

a5c-ai
a5c-ai
1,52087

backend-async-processing

Implement backend async and background processing patterns — event-driven architectures, message queues, async task runners, and worker pools.

a5c-ai
a5c-ai
1,52087

implementation-execution

Execute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.

a5c-ai
a5c-ai
1,52087

systematic-debugging

Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.

a5c-ai
a5c-ai
1,52087

test-case-generator

Generate comprehensive test cases including edge cases, stress tests, and counter-examples for algorithm correctness verification. Supports random generation, constraint-based generation, and brute force oracle comparison.

babysitter-sdk
babysitter-sdk
1,52087

continuous-learning

Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.

a5c-ai
a5c-ai
1,52087

context-engineering

Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.

a5c-ai
a5c-ai
1,52087

planning-design

Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.

a5c-ai
a5c-ai
1,52087

memory-summarization

Conversation summarization for memory compression and context management

a5c-ai
a5c-ai
1,52087

langgraph-hitl

Human-in-the-loop integration for LangGraph workflows with approval and intervention points

a5c-ai
a5c-ai
1,52087

langgraph-checkpoint

LangGraph checkpoint and persistence configuration for stateful workflow management

a5c-ai
a5c-ai
1,52087

langfuse-integration

LangFuse LLM observability integration for tracing, analytics, and cost tracking

a5c-ai
a5c-ai
1,52087

haystack-pipeline

Haystack NLP pipeline configuration for document processing and QA

a5c-ai
a5c-ai
1,52087

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

a5c-ai
a5c-ai
1,52087

huggingface-classifier

Hugging Face transformer model fine-tuning and inference for intent classification

a5c-ai
a5c-ai
1,52087

code-review-pipeline

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

a5c-ai
a5c-ai
1,52087

langchain-chains

LangChain chain composition including SequentialChain, RouterChain, and LCEL patterns

a5c-ai
a5c-ai
1,52087

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.

a5c-ai
a5c-ai
1,52087

langchain-tools

LangChain tool creation and integration utilities for agent systems

a5c-ai
a5c-ai
1,52087

Page 318 of 1729 · 86403 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.