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...
kessoku-di
by mazreanKessoku compile-time DI with parallel initialization for Go. Use when writing or debugging kessoku providers/injectors, enabling async dependencies, migrating from google/wire, or fixing go:generate/codegen issues in Go services.
db-access-analysis
by mazreanGoプロジェクト内でDBアクセス（CRUD）が発生している関数・テーブルをisucrudで解析し、コーディングエージェントが「どの関数からどのテーブルにINSERT/UPDATE/DELETE/SELECTが行われるか」を把握するためのスキル。キャッシュ対象の判断、N+1の特定、DBアクセスを伴う関数の影響範囲調査、リファクタリング前のCRUD確認などに使用する。Go (database/sql, sqlx 等) で書かれたプロジェクトが対象。
verifying-dockportless
by mazreanLaunches and verifies local dev environments using dockportless with worktree-unique project names. Use when starting docker compose services, checking service accessibility via proxy, enabling TLS/HTTPS routing, or when developing across multiple git worktrees to avoid port collisions.
isutools-prometheus
by mazreanQuery isutools (isucon-go-tools) metrics via PromQL on a Prometheus server. Use when the user wants to analyze ISUCON performance — slow endpoints, slow SQL queries, cache hit rate, DB connection pool, lock contention, queue depth, object pool usage, or benchmark scores — using Prometheus (`/api/v1/query`, `/api/v1/query_range`, Grafana, `promtool`). Triggers on phrases like "isutools metrics", "isucon-go-tools metrics", "isutools_api_*", "isutools_db_*", "ISUCON のメトリクスをクエリ", "PromQL for isutools".
deploying-with-isucon-ansible
by mazreanDeploys ISUCON contest code and configs to competition servers using the isucon-ansible layout (Ansible playbook for provisioning + Makefile-over-SSH for the per-benchmark loop). The two deploy commands are `make bench` (regular deploy, with instrumentation ON) and `make maji` (final-run deploy, with instrumentation OFF). Use when running benchmarks, deploying app/nginx/MySQL config changes, reassigning roles between servers, or when working in a repo that uses mazrean/isucon-ansible (server.yaml, hosts inventory, .make.env, remote/Makefile).
creating-agent-skills
by mazreanCreates well-structured Agent Skills following best practices. Use when building new skills for Claude Code, designing skill directory structures, writing SKILL.md files, or improving existing skills with progressive disclosure patterns.
creating-test-cases
by mazreanDesigns comprehensive test cases using systematic techniques (boundary value analysis, equivalence partitioning, mutation testing, property-based testing). Use when writing tests, improving test coverage, finding edge cases, or when user mentions test cases, testing, or test design.
designing-isucon-architecture
by mazreanAnalyzes an existing ISUCON-style application, designs an optimal infrastructure and architecture redesign that respects every ISUCON rule, and emits the proposal as a self-contained Agent Skill that another Claude session can read and execute. Use when starting an ISUCON contest or practice, drafting a contest-day architecture plan before touching code, or when the user asks to "design the architecture", "plan the topology", or "produce an implementation skill" for an ISUCON problem.
operating-isucon-servers-via-ssh
by mazreanRun commands directly against ISUCON contest hosts (isu1/isu2/isu3) over plain SSH. Use when the user wants to ssh into a contest box and execute commands — checking app/nginx/mysql status, tailing journalctl, restarting services, opening a MySQL shell, running kataribe or pt-query-digest, profiling with pprof through an SSH tunnel, transferring files, or running anything ad-hoc that doesn't have (or doesn't need) a Makefile target. Covers `~/.ssh/config` + agent-forwarding setup, host inventory, server-side paths and service names, common one-liners by category, and SSH patterns (heredoc, port-forward, multi-host, scp/rsync).
porting-isucon-rust-to-go
by mazreanPorts an ISUCON-style Rust reference implementation to Go (Echo) using parallel subagents. Use when the contest provides a Rust reference but the team wants to compete in Go, or when the user asks to migrate a Rust web app to Go Echo endpoint by endpoint. Preserves API URI, request/response shape, frontend static files, the isuwari reboot/retest daemon, and the isuadmin account exactly as distributed (changing them = disqualification).
releasing-zig-with-goreleaser
by mazreanReleases Zig CLI applications using GoReleaser v2.5+. Use when setting up automated releases for Zig projects, configuring .goreleaser.yaml for Zig builds, creating GitHub Actions CI/CD for Zig releases, or publishing Zig binaries via Homebrew, Docker, or Linux packages.
sharing-sockets-with-so-reuseport-in-zig
by mazreanWrites Zig code for sharing TCP/UDP sockets between unrelated processes using SO_REUSEPORT. Use when implementing multi-process socket sharing, zero-downtime restarts, load balancing across processes, or when user mentions SO_REUSEPORT, reuseport, socket sharing, or graceful restart in a Zig project.
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.