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...
lima-vm-operations
by AeyeOpsThis skill should be used when the user asks about "Lima", "limactl", "lima.yaml", "lima start", "lima shell", "creating a Linux VM on Mac", "running Linux on Apple Silicon", "macOS Linux VM", "Apple Silicon VM", or wants to "install Lima", "configure a Lima VM", "edit lima config", "spin up an Ubuntu VM on my Mac", or "use Lima to run Docker on macOS". Also applies for "lima vmType vz", "lima vz vs qemu", "host.lima.internal", "socket_vmnet", "lima networking", "lima shared network", "lima bridged network", "virtiofs mount", "9p mount", "lima port forward", "lima mount writable", "limactl edit", "limactl validate", "limactl template", "lima Rosetta", "running x86 in lima", "lima debug startup", or any task involving spinning up, configuring, troubleshooting, or shelling into a Lima VM on an Apple Silicon Mac. Use this skill whenever Lima is mentioned even if the user doesn't explicitly ask for "help" — the right configuration choices (vz vs qemu, mount type, network mode) are non-obvious and easy to get wron
owasp-top-10
by AeyeOpsOWASP Top 10 vulnerabilities with detection patterns, code examples, and prevention checklists. Activate when: reviewing code for security, checking for OWASP vulnerabilities, performing security audits, fixing injection flaws, preventing XSS, securing authentication, checking access control.
glinet-slate7
by AeyeOpsComprehensive reference for the GL-iNet Slate 7 travel router (model GL-BE3600, Wi-Fi 7). Covers hardware specs, 2.5G ports, touchscreen interface, full admin panel menu structure, VPN client setup (WireGuard/OpenVPN; NordVPN, Mullvad, Surfshark, and 30+ providers), WireGuard/OpenVPN server setup, AdGuard Home, Tor, Tailscale, DDNS, network modes (Router/AP/Extender/WDS/Drop-in Gateway), SSH/CLI access with command reference, factory reset, firmware update, and U-Boot bricked-device recovery. Also covers the JSON-RPC admin API at /rpc (challenge/response auth, module/method discovery, reusable bash helper), programmatic WireGuard server provisioning via the wg-server module (add_peer, generate_peer, settings, leak verification, local-only Endpoint pattern), and Linux client-side WG with overlay-VPN stacking — including the two leak modes that appear when running Tailscale on top of a full-tunnel WG client (fwmark 0x80000 bypass and wg-quick catch-all shadowing the tailnet routes) plus the wg-quick PostUp/PreD
d2
by AeyeOpsAuthor D2 diagrams (the Terrastruct text-to-diagram language at https://d2lang.com). Use whenever the user wants to produce, edit, or render any kind of diagram with D2 — architecture, flowchart, sequence, ER/SQL schema, UML class, network topology, mind map, deployment, org chart, state machine, grid layout, mermaid-style flow, or anything similar — even when they don't say "D2" explicitly. Trigger on requests for `.d2` files, mentions of `d2`/`d2lang`, or open-ended diagramming tasks ("draw me a system diagram", "make a flowchart of X", "diagram the request flow", "give me an ER diagram for these tables"). Covers the full DSL — shapes, connections, containers, classes, vars, globs/filters, imports, layers/scenarios/steps, styling, themes, sketch mode, icons, markdown/LaTeX/code blocks, layout engines (dagre/elk/tala), CLI flags, and the specialized diagram shapes (sequence_diagram, sql_table, class, grid, hierarchy, c4-person, image, text/code).
qbo-coa
by AeyeOpsContains verified 15-AccountType-to-125-DetailType mapping tables with Form 1120 line-by-line tax mapping, system/protected account restrictions matrix (A/R single-default architecture, OBE clearing, Retained Earnings auto-calculation), and full QBO Account API CRUD reference with python-quickbooks batch patterns. QBO chart of accounts, account type selection, detail type, Prep for Taxes, C-corp equity, holding company COA template, CSV JE import account matching. Consult when creating or fixing QBO accounts, choosing account type or detail type, mapping accounts to Form 1120 lines, setting up C-corp equity (Common Stock, APIC, Treasury Stock, dividends), clearing Opening Balance Equity, troubleshooting Retained Earnings behavior, merging or consolidating duplicate accounts, hitting the 250-account limit, importing journal entries via CSV or API, diagnosing "Line Account Invalid" or "Account Does Not Exist" errors, recording federal income tax expense for a C-corp, or batch-creating accounts via the QBO API.
chart-of-accounts
by AeyeOpsContains verified C-corp COA procedures, account numbering decision trees, and Form 1120 tax-line mappings that produce more precise answers than reasoning from general training alone. Account type taxonomy (1xxx-9xxx), hierarchical grouping, book-tax differences, equity accounts (APIC, retained earnings, treasury stock), and COA restructuring. Consult when choosing account numbers, classifying accounts, mapping GL to tax lines, or asking "what account for X."
compliance-reporting
by AeyeOpsContains verified 1099 decision trees (NEC vs MISC classification, corrected filing Type 1/Type 2 procedures), B-notice response protocols, and sales/use tax nexus thresholds that produce more precise answers than reasoning from general training alone. W-9 reportability, backup withholding, e-file mandate, economic nexus, exemption certificates, use tax self-assessment, marketplace facilitator rules. Consult when asked "does this vendor need a 1099", resolving B-notices, preparing corrected filings, evaluating sales tax nexus, or determining filing thresholds by tax year.
tax-forms
by AeyeOpsContains verified Section 179/bonus depreciation annual limits tables (2007-2026+), Form 8949 adjustment code catalog (W/B/T/O/S/N/H with box selection A-F), and Form 1118 separate limitation category rules (GILTI/branch/passive/general with carryback-carryforward). MACRS property classes, mid-quarter convention triggers, capital loss carryback (3yr) and carryforward (5yr), wash sale rule for corporations, Form 5472 foreign-ownership ($25K penalty), IRC 267/482 transfer pricing methods (CUP/RPM/CPM/profit split), APA procedures, 1099-DIV/1099-B reconciliation, digital asset compliance (crypto/1099-DA/DeFi/staking). Consult when preparing any Form 1120 supporting schedule, choosing depreciation elections, computing capital gains netting, evaluating foreign tax credit limitations, documenting intercompany pricing, or classifying digital asset transactions.
payroll-recording
by AeyeOpsContains verified payroll journal entry templates, GL account mapping tables (6xxx expenses, 2xxx liabilities), and Form 941/940 liability reconciliation procedures that produce more precise answers than reasoning from general training alone. Gross wages, employer FICA/FUTA/SUTA, withholdings, garnishments, tax deposit entries, accrual wage splits, net-pay-only error correction, ADP/Gusto/Paychex provider integration. Consult when posting payroll to the ledger, e.g. "how do I record the full payroll journal entry" or "the payroll liability balance keeps growing."
categorization-rules
by AeyeOpsContains verified C-corp vendor-to-GL mapping table (13 vendor types with account numbers), Form 1120 tax-line expense sub-range assignments (5xxx-9xxx with line numbers), and CapEx/OpEx capitalization threshold decision tree. Deductible vs non-deductible classification (meals 50% IRC 274, entertainment 0% post-TCJA, penalties IRC 162(f)), operating/investing/financing for cash flow, bank feed rule engine logic, split transaction patterns, personal vs business separation. Consult when categorizing any transaction to a GL account, asking "what account does this go to," fixing a miscategorized charge, deciding whether to expense or capitalize a purchase, splitting a multi-category transaction, setting up bank feed auto-categorization rules, or separating deductible from non-deductible expenses.
practice-management
by AeyeOpsContains verified six-phase engagement lifecycle with quality gates (onboard through archive), capacity planning formula with extension-first surge strategy, and staff assignment criteria (competency, continuity, independence, workload balance). Engagement throughput, deadline calendar layering (external/internal/reminder triggers), seasonal workload distribution, WIP aging, cross-functional handoffs (BK to TX to FP), AICPA SQMS No. 1 engagement performance. Consult when planning work allocation across tax seasons, building or evaluating a master deadline calendar, balancing staff workloads or assigning engagement teams, designing engagement phase workflows or status tracking, coordinating cross-service-line handoffs, or assessing whether to extend vs. file on time.
accounting-method-changes
by AeyeOpsContains verified Form 3115 filing procedures (automatic vs non-automatic consent, duplicate filing requirements, signature rules, under-examination limitations), Section 481(a) adjustment computation tables (positive 4-year spread, negative 1-year recognition, acceleration events, NOL interaction ordering), and DCN catalog for common C-corp method changes (DCN 122 cash-to-accrual, DCN 7 Section 174 R&E capitalization/depreciation, DCN 12 UNICAP, DCN 239 advance payments, DCN 187 bad debts). IRC 446/481(a) method change framework, Rev. Proc. 2015-13 as modified by Rev. Proc. 2024-23, audit protection under Section 11.01, 5-year prior change restriction, window period eligibility, user fee schedule. Consult when filing Form 3115 for any accounting method change, computing a 481(a) adjustment for cash-to-accrual conversion or UNICAP adoption, determining whether a change qualifies for automatic consent, evaluating audit protection strategy for an impermissible method, timing a method change around NOL carryforw
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.