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...
aosp-framework-core
by aospbooksAOSP Part VI — Framework Core. Use when reasoning about system_server's boot sequence (the four boot phases, service registration, Watchdog), the Intent system (Intent matching, IntentFilter, IntentResolver, package visibility, intent verification), Activity & Window Management (ActivityTaskManagerService, WindowManagerService, activity lifecycle, task/stack model, splash screens), the window system (WindowState, SurfaceControl, input dispatching, focus, IME insets, transitions), the display system (DisplayManagerService, logical vs. physical displays, HDR, brightness, refresh-rate switching), or the View system (View hierarchy, measure/layout/draw, Canvas/RenderNode, hardware acceleration). Chapters 20–25.
aosp-native-foundation
by aospbooksAOSP Part III — Native Foundation. Use when reasoning about Bionic (Android's libc/libm/libdl) and the dynamic linker, linker namespaces, GWP-ASan / MTE, memory management (jemalloc/scudo, ashmem/memfd, ION/dma-buf, lmkd, PSI), Binder IPC (transactions, parcels, one-copy semantics, AIDL/HIDL/NDK Binder, servicemanager, threadpool, death recipients), the HAL (Treble, HIDL→AIDL HAL migration, vendor/system split, hwservicemanager, VINTF), or the NDK (libandroid, JNI bindings, ABI compatibility). Chapters 7–11.
aosp-ai-and-devices
by aospbooksAOSP Part XII — AI & Devices. Use when reasoning about on-device ML in AOSP, NNAPI, the AppFunctions framework for assistant integration, the Computer Control flow, CompanionDeviceManager, or virtual devices (virtual displays/inputs/cameras for cross-device experiences). Chapters 50–51.
aosp-appendices
by aospbooksAOSP Internals — Appendices. Use when looking up a key file path (per-chapter table of the most important AOSP source files: build, init, kernel, HAL, framework services, system apps, infrastructure) or the meaning of an AOSP-specific acronym/term (Treble, VINTF, GKI, APEX, AIDL, HIDL, etc.). Reference material — load when you need a concrete path or a definition rather than narrative explanation.
aosp-connectivity
by aospbooksAOSP Part VIII — Connectivity. Use when reasoning about Networking (ConnectivityService, Wi-Fi framework, netd, DNS resolver, VPN, tethering, NetworkSecurityConfig, VCN, Thread mesh), Telephony (TelephonyManager, PhoneInterfaceManager, RIL/RILD, modem AIDL, IMS framework, emergency calling), Bluetooth (Bluetooth Mainline module, BTA, GATT, A2DP/HFP/AVDTP, LE Audio, pairing, scanning, advertising), NFC (NfcAdapter/NfcService, NCI, tag dispatch, HCE, secure element, reader mode, NFC-F/V), or USB & ADB (USB gadget framework, host-mode USB, MTP/PTP, RNDIS tethering, adb daemon, adb over Wi-Fi). Chapters 35–39.
aosp-device-support
by aospbooksAOSP Part XIV — Device Support. Use when reasoning about per-architecture support (ARM 32/64, x86_64, RISC-V, ABI matrix, toolchains), the QEMU-based Android emulator (AVD format, hardware acceleration, guest kernel), DevicePolicyManager (work profiles, fully-managed devices, COPE, enrollment), Android Automotive / TV / Wear (CarService, vehicle HAL, Leanback, TIF, Wear OS specifics), Print Services (PrintManager, IPP, PDF generation), or the Camera2 pipeline (Camera2 API, CaptureRequest/Result, camera HAL3). Chapters 57–62.
aosp-framework-services
by aospbooksAOSP Part VII — Framework Services. Use when reasoning about PackageManagerService (install/uninstall, APK parsing, permissions, package visibility), ContentProviders (ContentResolver, URI permissions, observers, FileProvider, MediaStore), Notifications (NMS, channels, ranker, posting/delivery, listener services, conversations, bubbles), Power Management (PowerManagerService, wake locks, Doze, App Standby, battery saver, BatteryStats), Background Tasks (JobScheduler, WorkManager, AlarmManager, foreground services, exact alarm policy), Multi-User (UserManagerService, profiles, restrictions, cross-user calls), Account & Sync (AccountManagerService, authenticator, syncadapter, SyncManager), Location (LocationManagerService, GPS/network/fused providers, GNSS HAL, geofencing), or Storage (vold, StorageManagerService, scoped storage, FUSE/sdcardfs, MediaProvider, SAF, FBE, adoptable storage, SQLite, SharedPreferences). Chapters 26–34.
aosp-getting-started
by aospbooksAOSP Part I — Getting Started. Use when reasoning about the AOSP source tree at a high level, the repo/manifest workflow, the Soong (Android.bp) and Bazel/Kleaf build systems, lunch targets, the m build entry point, or aconfig feature flags (build-time vs. runtime, release configs, ramp/cleanup workflows). Chapters 0–3 (Frontmatter, Introduction, Source Code & Build System, Feature Flags).
aosp-infrastructure
by aospbooksAOSP Part XIII — Infrastructure. Use when reasoning about Mainline modules / APEX (Project Mainline, APEX format/manifest/signing, apexd, module catalog, SDK Extensions, module boundaries), OTA updates (A/B updates, update_engine, payload format, Virtual A/B with snapshots, rollback protection), Virtualization (Android Virtualization Framework, pKVM, crosvm, microdroid), Testing (CTS/VTS/MTS, Tradefed, Ravenwood, atest, presubmit), or Debugging (Perfetto, atrace, simpleperf, heapprofd, logcat, dumpsys). Chapters 52–56.
aosp-kernel-and-boot
by aospbooksAOSP Part II — Kernel & Boot. Use when reasoning about Android's bootloader handoff, init.rc / first-stage init / second-stage init, the Generic Kernel Image (GKI) and KMI stability, dm-verity / Android Verified Boot, the kernel's Android-specific subsystems (binder driver, ashmem→memfd, low-memory killer, PSI), vendor modules, or system properties (property_service, property contexts, ro/persist/sys/build prefixes). Chapters 4–6.
aosp-native-services-and-media
by aospbooksAOSP Part IV — Native Services & Media. Use when reasoning about surfaceflinger, audioserver, mediaserver, cameraserver, the graphics pipeline (BufferQueue, GraphicBuffer, OpenGL ES / Vulkan / Skia / HWUI, RenderThread, layer composition), the animation system (Choreographer, ValueAnimator, RenderNode animations, dynamic spring/fling), the audio stack (AudioFlinger, AudioPolicyManager, AAudio, OpenSL ES, Spatializer), the media pipeline (MediaCodec, MediaExtractor, NuPlayer, codec2 HAL), or the sensor stack (SensorService, sensor HAL, batching, wake-up sensors). Chapters 12–17.
aosp-practical
by aospbooksAOSP Part XV — Practical. Use when reasoning about building a custom AOSP ROM end-to-end: picking a target device, syncing source, applying vendor blobs, branding, building, flashing the resulting images, and shipping OTA updates on your own channel. Chapter 63 (Custom ROM Guide).
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.