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...
bsp-fundamentals
by brake71Use this skill when the agent needs to navigate the 1C BSP (StandardSubsystems) 3.1.11 codebase, locate the right common module for a subsystem, decode module name suffixes like Klient/Server/KlientServer/VyzovServera/Globalnyi/PovtIsp/Sluzhebnyi/Pereopredelyaemyi, distinguish stable API from internal API by region markers, or pick the correct subsystem out of the ~70 top-level subsystems. Do not use for writing code that calls specific BSP methods (delegate to bsp-base-common, bsp-users-access, bsp-print-reports etc.).
bsp-forms-validation
by brake71Use this skill when the agent needs to lock editable attributes of a form object after write, attach a custom unlock command to a form, declare key attributes for a manager module, register additional attributes and additional info, integrate the standard property subsystem into a form, validate fills of additional attributes, or display a form-bound validation error. Do not use for one-off business-logic checks unrelated to the BSP property / lock-edit subsystems, for printing or reports (delegate to bsp-print-reports), for users and access (delegate to bsp-users-access), or for the platform-level message helper alone (delegate to bsp-base-common).
bsp-comms
by brake71Use this skill when the agent needs to send an outgoing email via a configured account, load incoming messages from an IMAP/POP3 mailbox, list available email accounts, send an SMS through a configured provider, send an email or SMS composed from a message template, open the integrated form for choosing a template or composing a new message from a subject, send a chat message through the 1C:Dialogue interaction system, create a message description for the interaction system, or check whether outbound email, SMS, or interaction-system discussions are available in the current configuration. Do not use for general utilities such as safe storage or string formatting (delegate to bsp-base-common), for printing reports that include attachments (delegate to bsp-print-reports), for background jobs that wrap long calls (delegate to bsp-longs-and-jobs), for contact-information addresses and phone numbers (delegate to bsp-contact-info), or for navigation across the BSP namespace (delegate to bsp-fundamentals).
bsp-contact-info
by brake71Use this skill when the agent needs to read or write contact information (address, phone, email) attached to a reference object, get a human-readable presentation string of an address, open a managed form to edit contact information inline, validate one or more addresses against the address classifier (KLADR / FIAS), look up a region code by its name, resolve OKTMO / OKATO / FIAS / IFNS codes for an address, parse a stored contact-info string and extract the region, city, index, or house, build a full address from its FIAS identifier, or convert between the JSON and XML internal representations of contact information. Do not use for unrelated common-module helpers (delegate to bsp-base-common), for printing address forms (delegate to bsp-print-reports), or for navigation across the BSP namespace (delegate to bsp-fundamentals).
bsp-backup
by brake71Use this skill when the agent needs to open the infobase backup form from a configuration command, save or load backup settings programmatically, read the current backup schedule or status as a user-facing string, generate a navigation link to the backup data processor, calculate the date of the next automatic backup, suppress backup-related warnings at application start in a non-standard scenario, or implement an override hook that disables backup notifications for specific client configurations. Do not use for routine object recording or safe storage (delegate to bsp-base-common), for scheduled job management (delegate to bsp-longs-and-jobs), for infobase version migration (delegate to bsp-update), or for full-text or DT-file operations outside the BSP backup subsystem.
bsp-users-access
by brake71Use this skill when the agent needs to identify the current user or the current external user of an infobase session, distinguish a regular user session from an external user session, check whether a user is a full-rights administrator, check whether a role is available to a user, check at record level (RLS) whether a user is allowed to read or modify a specific reference or record set, or open the access-rights settings form from a managed form. Do not use for password policies (delegate to bsp-base-common), for user creation in a configuration startup handler, or for platform-level authentication (the platform infobase user API is not wrapped by BSP - use the platform PolzovateliInformatsionnoiBazy object directly).
bsp-admin-tools
by brake71Use this skill when the agent needs to set or release an infobase connection lock, check whether a lock is active, get session lock parameters for a data area, find active connections to the infobase, put the infobase into user-termination mode or cancel it, open the administration parameters form, programmatically delete marked-for-deletion objects with referential integrity control, get a list of objects marked for deletion, find references to objects being deleted, check or toggle the scheduled-deletion mode, integrate deletion visibility into form lists, or implement before/after deletion hooks. Do not use for routine object recording (delegate to bsp-base-common), for scheduled job management unrelated to deletion (delegate to bsp-longs-and-jobs), for infobase updates (delegate to bsp-update), or for backup operations (delegate to bsp-backup).
bsp-base-common
by brake71Use this skill when the agent needs to display a user message bound to a form attribute, serialize or deserialize a value to/from XML or JSON, check whether a type is a reference or an object has a given attribute, read attribute values of a reference, check whether a configuration subsystem exists, store or read a password or other secret in the secure storage, format a string with parameters, split a string into substrings, parse a date from a string, create a temporary directory on the server, or open Windows Explorer from the client. Do not use for subsystem-specific APIs (delegate to bsp-users-access, bsp-print-reports, bsp-longs-and-jobs, etc.).
bsp-currencies-banks
by brake71Use this skill when the agent needs to obtain or recalculate a currency exchange rate, convert an amount from one currency to another, format a monetary amount in words, add currencies to the classifier by ISO numeric code, look up a bank by BIK or correspondent account, check why a bank is marked invalid, open a bank selection form from a field, get registration, contact, additional or bank-account details for an organization, or determine whether the organization catalog uses archives. Do not use for printing forms with amounts in words (delegate to bsp-print-reports), for bulk rate loading from infobase update handlers (unstable internal API), or for plain user-message display and serialization helpers (delegate to bsp-base-common).
bsp-print-reports
by brake71Use this skill when the agent needs to print a document or list of objects using a built-in print command from a managed form, register a new print form via manager-module ДобавитьКомандыПечати, override the global print subsystem settings, append custom logic to the print post-processing pipeline, find a report variant by report reference and key, open a report form by its variant reference, programmatically generate a report and read its ТабличныйДокумент, register a new report variant in ВариантыОтчетовПереопределяемый, or run heavy print/report generation in a background job without blocking the form. Do not use for connected-command infrastructure (delegate to bsp-commands-external), for general utility calls (delegate to bsp-base-common), for synchronous one-shot helper calls, or for direct file/excel export without the print framework.
bsp-external-components
by brake71Use this skill when the agent needs to connect a Native API or COM external component on the client or the server, install or update an external component delivered via the configuration, upload a component from a ZIP file, query component metadata (identifier, version, name), or override the set of dependent tables for OData export/import. Do not use for platform-level COM automation (unrelated to BSP), for direct file upload to the external components catalog, or for HTTP integration via web services.
bsp-perf-monitoring
by brake71Use this skill when the agent needs to instrument a 1C application code path with a key-operation time measurement, start or finish a long-operation benchmark with nested steps, register business-statistics values for the monitoring center, check whether the monitoring center is enabled, programmatically enable or disable the monitoring subsystem, or create a new key-operation entry in the catalog. Do not use for platform-level stopwatch utilities, for log-event writing, or for sending error reports to the 1C error accounting service.
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.