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...
property-rates-nz
by thecolab-aiQuery Auckland Council public property rates, capital value (CV), land value, improvement value, and annual rates through the council's no-login rate-assessment API. Use when the task involves Auckland property CV, council valuation, land value, improvement value, annual rates total, floor area, land area, or legal description. Read-only; requires an Auckland Council property ID (ACRateAccountKey).
public-housing-nz
by thecolab-aiQuery New Zealand public and social housing open data from the Ministry of Housing and Urban Development (HUD) on data.govt.nz — public housing stock (Kainga Ora and community housing providers), social housing IRRS and market-rent tenancies, accommodation supplement recipients and weekly spend, and the Local Housing Statistics dashboard (housing affordability, rent burden, bonds, building consents, MSD benefit numbers, and the year-on-year change in the public/social housing register). Use when the task involves NZ public housing, the social housing register or wait-list, Kainga Ora, housing deprivation, accommodation supplement, housing affordability, or HUD housing statistics. No API key, login, or browser session required.
auckland-bin-schedule
by thecolab-aiQuery Auckland Council rubbish, recycling, and food scraps collection days for Auckland properties using the public collection-day website flow. Use when the task involves Auckland bin day, rubbish/recycling schedules, food scraps collection, address lookup, or property-id based collection checks. No account login required.
wellington-bin-schedule
by thecolab-aiQuery Wellington City Council rubbish and recycling collection days using a WCC street ID. Use when the task involves Wellington bin day, rubbish/recycling schedules, or kerbside collection for a Wellington address. Requires a WCC street ID (found by searching your address on the WCC collection-day page). No account login required.
christchurch-bin-schedule
by thecolab-aiQuery Christchurch City Council kerbside collection schedules (rubbish, recycling, organics). Use when the task involves Christchurch bin days, kerbside collection for a Christchurch address, or CCC three-bin schedules. Supports address search (name → RatingUnitID) or direct RatingUnitID lookup. No account required.
child-poverty-nz
by thecolab-aiQuery official New Zealand child poverty statistics from Stats NZ — the nine Child Poverty Reduction Act measures (BHC/AHC low-income lines, material hardship, severe material hardship, DEP-17 deprivation), national rates and child numbers 2007-2025 with confidence intervals, and breakdowns by region, ethnicity (Māori, Pacific, European, Asian) and disability. Use for tasks about NZ child poverty rates, kids in hardship or deprivation, poverty by region or ethnic group, annual change, or finding the latest Stats NZ child-poverty release.
household-hardship-nz
by thecolab-aiQuery New Zealand household material hardship, child and family poverty, income adequacy, housing affordability and rent burden, low-income household counts, and the Gini coefficient of income inequality from the Stats NZ Household Economic Survey "Household Wellbeing" release on data.govt.nz. Use for questions about NZ deprivation, cost-of-living stress, who is struggling to afford housing, hardship by region or ethnicity (including Maori households), or income inequality figures with confidence intervals.
msd-benefits-nz
by thecolab-aiQuery official New Zealand MSD benefit statistics - Jobseeker Support, Sole Parent Support, Supported Living Payment, Youth Payment, NZ Superannuation and Veteran's Pension recipient numbers by quarter, gender, ethnicity, age group, and Work and Income region. Use for working-age benefit numbers, main benefit counts, welfare/superannuation recipient breakdowns, and benefit trends. No API key or browser session required.
kmart
by thecolab-aiQuery Kmart NZ and AU product search, prices, SKU lookup, clearance/promotional snapshots, and store-location data. Read-only; no login, cart, checkout, or account actions.
rbnz-data
by thecolab-aiDiscover and fetch Reserve Bank of New Zealand public statistics datasets through data.govt.nz CKAN and browser-compatible rbnz.govt.nz public file/chart endpoints. Use when the task involves RBNZ exchange rates, wholesale interest rates, OCR/key graphs, retail mortgage/deposit rate charts, dataset metadata, resource URLs, downloadable XLSX series, or JSON chart-cache previews. Read-only; no authentication required.
deprivation-nz
by thecolab-aiLook up New Zealand small-area socioeconomic deprivation (NZDep2023) by SA1/SA2 code, place name, decile, or SA3 region - the standard index of relative poverty, material hardship, and disadvantage used for health, housing, school decile, child poverty, and funding analysis. No API key or login required.
companies-office-nz
by thecolab-aiSearch and inspect New Zealand Companies Register records through read-only public website endpoints. Use when the task involves NZ company lookup by name, company number, or NZBN; company status, incorporation date, entity type; director names and appointment dates; shareholder allocations and percentages; registered addresses; filing history and public documents; or any company governance data not covered by the NZBN Register skill. No login, API key, or account required. Read-only.
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.