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...
cisco-dc-networking-setup
by chambear2809Automate Cisco DC Networking TA setup and configuration on Splunk. Creates indexes, configures ACI/Nexus Dashboard/Nexus 9K accounts, enables data inputs, stores credentials securely, and validates the deployment. Use when the user asks about Cisco DC networking, ACI, APIC, Nexus Dashboard, Nexus 9K TA setup, Splunk TA automation, or cisco_dc_networking_app_for_splunk.
splunk-platform-pki-setup
by chambear2809Render, preflight, apply, validate, rotate, and inventory private or public PKI for Splunk Enterprise TLS surfaces: Splunk Web, splunkd REST, S2S, HEC, KV Store, indexer clusters, SHC, License Manager, Deployment Server, Monitoring Console, Federated Search, heavy forwarders, Universal Forwarders, Edge Processor, SAML SP signing, LDAPS trust, and CLI CA trust. Covers CSR handoffs, internal CA rendering, FIPS mode, TLS policy presets, KV Store EKU enforcement, default-cert refusal, SAN-aware leaf certs, mTLS, replication-port TLS, and delegated rotation runbooks. Use when the user asks to build Splunk PKI, mint certs, prepare third-party CA CSRs, replace default certs, configure mTLS, fix KV Store cert validation, encrypt replication traffic, configure SAML/LDAPS trust, or rotate Splunk TLS certificates.
splunk-search-head-cluster-setup
by chambear2809Render, preflight, apply, validate, and operate Splunk Enterprise Search Head Clusters end-to-end: bootstrap (deployer + N-member init + captain election), deployer bundle push (validate / status / apply / apply-skip-validation / rollback with SHA and generation-drift tracking), rolling restart (default, searchable with health-check loop, forced), captain transfer, member add / decommission / remove, KV Store replication health (lag thresholds, oplog reset, captain re-election), standalone-to-SHC migration, deployer replacement, ES-on-SHC deployer placement, and failure-mode runbooks (split-brain, quorum loss, deployer mismatch, captain crash loop). SHC pass4SymmKey is templated as `$SHC_SECRET` for operator-managed rotation (see Out of Scope). Use when the user asks to bootstrap an SHC, push a deployer bundle, perform a searchable rolling restart, transfer the captain, add or remove a member, troubleshoot KV Store replication lag, migrate a standalone search head to SHC, or replace a deployer.
splunk-microsoft-cloud-setup
by chambear2809Install, render, configure, and validate the Splunk add-ons for Microsoft cloud telemetry: the Splunk Add-on for Microsoft Office 365 (splunk_ta_o365, Splunkbase 4055) and the Splunk Add-on for Microsoft Cloud Services (Splunk_TA_microsoft-cloudservices, Splunkbase 3110). Renders real inputs.conf stanzas for Office 365 Management Activity (Entra/Azure AD, Exchange, SharePoint, General, DLP), Microsoft Graph Entra ID metadata, and Azure audit, emits an Entra app-registration account runbook, creates the o365 and azure indexes, maps source types to CIM, and validates ingestion. Use when the user asks about Splunk_TA_o365, Office 365, Microsoft 365, Entra ID, Azure AD audit/sign-in, Microsoft Graph, Splunk Add-on for Microsoft Cloud Services, or Microsoft cloud log onboarding in Splunk.
splunk-observability-cisco-nexus-integration
by chambear2809Standalone reusable skill for sending Cisco Nexus 9000 metrics to Splunk Observability Cloud via the OTel cisco_os receiver (multi-device + global scrapers format, PR #45562, currently at v0.149.0+ in upstream contrib). Renders the clusterReceiver overlay, K8s Secret manifest stub for SSH credentials, dashboards and starter detectors. Hands off base collector to splunk-observability-otel-collector-setup, dashboards to splunk-observability-dashboard-builder, detectors to splunk-observability-native-ops. Independent of Cisco AI Pod -- useful for any data center with Nexus fabric. Companion to cisco-dc-networking-setup (Splunk Platform TA for Nexus / ACI / Nexus Dashboard). Use when the user asks to send Cisco Nexus, NX-OS, IOS-XE, or IOS-XR device metrics to Splunk Observability Cloud, configure the cisco_os receiver, set up multi-device Nexus telemetry, or render dashboards/detectors for Cisco data center fabric.
cisco-thousandeyes-mcp-setup
by chambear2809Render and (optionally) apply Model Context Protocol client configurations for the official ThousandEyes MCP Server (https://api.thousandeyes.com/mcp, GA per docs.thousandeyes.com/.../thousandeyes-mcp-server). Supports Cursor, Claude Code, Codex, VS Code, and AWS Kiro clients with both OAuth Bearer and OAuth2 flows. Surfaces TE rate limits, the unit-consumption warning for Instant Tests, and gates the write/Instant-Test tool group behind an explicit opt-in. Use when the user asks to register the ThousandEyes MCP, set up TE in Cursor/Claude/Codex/VS Code/Kiro, configure the Cisco ThousandEyes Cursor plugin, or pair an AI assistant with TE.
splunk-ai-ml-toolkit-setup
by chambear2809Install, render, validate, and audit Cisco Data Fabric AI Toolkit and Splunk-owned AI and machine-learning workflows beyond Splunk AI Assistant: Splunk AI Toolkit / MLTK (`Splunk_ML_Toolkit`), Python for Scientific Computing (PSC), Splunk App for Data Science and Deep Learning (DSDL), MLTK anomaly workflows, LLM/`ai` command readiness, external model runtimes, and legacy anomaly app migration. Use when the user asks about MLTK, Splunk AI Toolkit, Machine Learning Toolkit, PSC, Python for Scientific Computing, DSDL, Deep Learning Toolkit, Splunk anomaly detection assistants, Smart Alerts Assistant, or AI/ML product coverage outside Splunk AI Assistant, including Cisco Data Fabric requests about AI Toolkit or machine-data model workflows.
splunk-appdynamics-security-ai-setup
by chambear2809Render, validate, and delegate Splunk AppDynamics security and AI workflows, including Application Security Monitoring, Secure Application, Secure Application runtime policies, Secure Application `policyConfigs`, Secure Application APIs, Secure Application for OpenTelemetry Java, Observability for AI, OpenAI, LangChain, Bedrock, GPU readiness, and Cisco AI Pod handoffs. Use when the user asks for AppDynamics Secure Application, application security monitoring, Secure Application policies, Secure Application APIs, Secure Application `policyConfigs`, Secure Application for OTel Java, Observability for AI, OpenAI or LangChain monitoring, Bedrock checks, GPU telemetry, or Cisco AI Pod AppDynamics handoffs.
splunk-observability-cisco-intersight-integration
by chambear2809Render and validate Cisco Intersight (UCS management plane) metrics into Splunk Observability Cloud through the Intersight OTel integration. Emits the namespace, Secret stub, Deployment, endpoint ConfigMap, Splunk OTel pipeline overlay, dashboards, detectors, and handoff scripts without reading key material. Use when the user asks to send Cisco Intersight, UCS, HyperFlex, or UCS-X compute metrics to Splunk Observability Cloud, configure the cisco_intersight OTel receiver, or render UCS chassis health dashboards and detectors. This is independent of Cisco AI Pod and complements the Splunk Platform TA skill cisco-intersight-setup.
splunk-observability-cisco-ai-pod-integration
by chambear2809Compose Cisco Nexus, Cisco Intersight, and NVIDIA GPU Observability skills into a Cisco AI Pod overlay, then add NIM, vLLM, Milvus, NetApp Trident, Pure Portworx, Redfish exporter, OpenShift SCC, workshop tenancy, RBAC, receiver naming, DCGM discovery, dual-pipeline filtering, NIM model-name extraction, and existing-collector cleanup patterns. Use when deploying Splunk Observability Cloud for a Cisco AI Pod with UCS, Nexus, NVIDIA GPUs, NIM/vLLM inference, and storage telemetry. Hand off base collector, HEC, dashboards, and detectors to the owning skills.
cisco-catalyst-ta-setup
by chambear2809Automate Cisco Catalyst Add-on for Splunk (TA_cisco_catalyst) setup and configuration. Creates indexes, configures Catalyst Center/ISE/SD-WAN/Cyber Vision accounts via REST API, enables data inputs, stores credentials securely, and validates the deployment. Use when the user asks about Cisco Catalyst Center, DNA Center, DNAC, ISE, SD-WAN, Cyber Vision TA setup, or TA_cisco_catalyst.
cisco-appdynamics-setup
by chambear2809Automate Cisco Splunk Add-on for AppDynamics (Splunk_TA_AppDynamics) setup and configuration. Creates the AppDynamics index, sets add-on defaults, configures controller and optional analytics connections, enables common input groups, and validates the deployment. Use when the user asks about AppDynamics setup, Splunk_TA_AppDynamics, controller connections, analytics connections, or AppDynamics dashboards in Splunk.
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.