Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
card-iso8583
by zenobiuszeto**ISO 8583 Card Authorization Processing**: End-to-end implementation of ISO 8583 message handling for debit/credit card authorization with real-time decision engine, network routing (Visa/Mastercard), clearing file processing, settlement workflows, and fraud detection integration. MANDATORY TRIGGERS: ISO 8583, ISO8583, card authorization, card auth, debit card, authorization request, authorization response, 0100, 0110, 0200, 0210, 0400, 0410, bitmap, primary bitmap, secondary bitmap, MTI, message type indicator, field 2, field 4, field 7, field 11, field 12, field 14, field 22, field 35, field 37, field 38, field 39, field 41, field 42, PAN, track data, CVV, CVV2, expiry, approval code, response code, acquirer, issuer, Visa, Mastercard, NetworkAdapter, IsoMessage, IsoParser, IsoBuilder, TCP socket, socket gateway, card network, stand-in, stand-in authorization, jPOS, clearing file, settlement, interchange, BIN table, card product
spring-gatling
by zenobiuszeto**Gatling Performance Testing Skill**: Production-grade load, stress, soak, and spike test simulations using Gatling 3.x Java DSL for the banking platform. Covers scenario design, feeders, session variables, assertions, HTML report analysis, Gradle integration, and CI gate configuration. MANDATORY TRIGGERS: Gatling, performance test, load test, stress test, soak test, spike test, simulation, scenario, feeder, ramp users, constant users, throughput, response time, percentile, p95, p99, assertions, gatlingRun, GatlingPlugin, io.gatling.gradle, ChainBuilder, ScenarioBuilder, PopulationBuilder, HttpProtocol, exec, pause, repeat, foreach, doIf, check, jsonPath, status, ElFileBody, StringBody, CSV feeder, JSON feeder, gatling-charts, Grafana, InfluxDB, baseline, regression, SmokeTestSimulation, LoadTestSimulation, StressTestSimulation.
eks-deployment
by zenobiuszeto**AWS EKS Deployment Skill**: Production-grade deployment of the banking platform to AWS EKS using Docker, Kubernetes manifests, Helm, IRSA (IAM Roles for Service Accounts), ALB Ingress Controller, HPA, PodDisruptionBudget, Network Policies, Secrets Manager integration, and cluster autoscaler. Tailored to the existing infra/k8s/ manifests in this project. MANDATORY TRIGGERS: EKS, AWS EKS, Elastic Kubernetes Service, eksctl, aws eks, kubectl apply, Helm, helm install, helm upgrade, ALB, AWS Load Balancer Controller, IRSA, IAM Role for Service Account, ECR, Amazon ECR, ACM, Certificate Manager, ExternalDNS, Cluster Autoscaler, Karpenter, aws-load-balancer-controller, Route53, VPC, eks.amazonaws.com/role-arn, AWS Secrets Manager, External Secrets Operator, ESO, HPA, PDB, Pod Disruption Budget, Network Policy, node group, Fargate, managed node group, EKS add-on, kube-proxy, CoreDNS, VPC CNI, EBS CSI driver, EFS, StorageClass, PVC, persistent volume, AWS deployment, production kubernetes.
spring-jfr
by zenobiuszeto**JDK Flight Recorder (JFR) Profiling Skill**: Production-safe JVM profiling using JFR for Java 21 banking platform. Covers enabling JFR, recording configurations, programmatic recording via JFR API, custom JFR events, JMC analysis workflows, Async Profiler, heap dump analysis, virtual thread profiling, and interpreting flamegraphs. MANDATORY TRIGGERS: JFR, Java Flight Recorder, JDK Flight Recorder, JMC, Java Mission Control, jcmd, jfr file, FlightRecorder, RecordingStream, RecordingConfiguration, profile recording, continuous recording, flamegraph, Async Profiler, heap dump, jmap, memory leak, CPU profiling, thread profiling, GC analysis, virtual threads, ZGC, lock contention, hot method, allocation profiling, jstack, thread dump, perf regression, profiling, jfr event.
pci-tokenization
by zenobiuszeto**PCI DSS Tokenization & Format-Preserving Encryption**: Eliminate cardholder data environment scope through HSM-backed token vault, network tokenization adapters, and PCI-segmented Kubernetes networking. MANDATORY TRIGGERS: PCI, PCI DSS, PCI compliance, PCI zone, cardholder data environment, CDE, tokenization, PAN tokenization, PAN token vault, TokenVault, TokenizationService, detokenization, DetokenizationService, PAN, Primary Account Number, card number, token format, format-preserving encryption, FPE, FF3, Luhn, Luhn check, network token, network tokenization, Visa Token Service, VTS, Mastercard MDES, HSM, Hardware Security Module, key ceremony, key loading, HSM adapter, ThalesHSM, FuturexHSM, HsmAdapter, PIN block, PIN encryption, PIN verify, TR-31 key block, key rotation, key custodian, PCI segmentation, cardholder data, SAD, sensitive authentication data, scope reduction, PCI audit, QSA, PCI SAQ, PA-DSS
terraform
by zenobiuszeto**Terraform IaC Skill**: Production-grade AWS infrastructure as code for the banking platform using Terraform 1.8+ with community modules. Covers VPC, EKS, RDS PostgreSQL, ElastiCache Redis, DocumentDB, S3, security groups, Helm releases (Vault, Consul, nginx, cert-manager), S3 remote state, DynamoDB locking, workspaces, variable validation, sensitive outputs, and CI/CD integration via GitHub Actions. MANDATORY TRIGGERS: Terraform, terraform, .tf, HCL, terraform init, terraform plan, terraform apply, terraform destroy, terraform workspace, terraform state, tfstate, terraform import, terraform output, provider, resource, module, variable, locals, data source, backend, S3 backend, DynamoDB lock, remote state, terraform fmt, terraform validate, tflint, tfsec, checkov, infracost, terraform-aws-modules, vpc module, eks module, rds module, helm_release, kubernetes provider, helm provider, aws provider, VPC, EKS, RDS, ElastiCache, DocumentDB, S3, security group, IAM, IRSA, outputs.tf, variables.tf, main.tf, IaC, in
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.