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...
bc-isolated-storage-generator
by fernandoartalfGenerate Isolated Storage implementations for Business Central with security best practices. Creates a setup table (Access = Internal), a management codeunit (Access = Internal), and optionally a setup page — wired to IsolatedStorage.Set/Get/Delete with user-chosen DataScope and a GUID secret key in a locked Label. Supports encryption via CryptographyManagement. Use when: create isolated storage, generate secret storage, store password securely, store API key, store client secret, store token, store credential, replace Service Password table, encrypted storage, DataScope, secure storage, credential vault, OAuth secret, bearer token storage, personal access token.
bc-pricing-refactor
by fernandoartalfGuides AL developers through refactoring Business Central legacy sales pricing (Sales Price table 7002 / Sales Line Discount table 7004) to the new Price List architecture (Price List Header table 7000 / Price List Line table 7001). Use this skill when asked to: migrate pricing customizations, extend the new Price Calculation engine, understand the PriceCalculation interface, map old codeunits to new ones, scaffold price list AL objects, or plan the Feature Management enablement strategy for the New Sales Pricing Experience. Triggers: "refactor prices", "migrate sales price", "new pricing experience", "Price List Header", "Price List Line", "extend price calculation", "PriceCalculation interface", "legacy pricing BC", "tabla 7002", "tabla 7000", "Feature Update pricing".
bc-telemetry-generator
by fernandoartalfInstruments Business Central AL codeunits with Application Insights telemetry using the System Application Telemetry codeunit. Analyzes an existing codeunit supplied by the user, generates a dedicated Feature Usage Telemetry codeunit (or extends an existing one) with helper procedures for LogStart/LogEnd with automatic duration, LogError with call stack, LogFeatureUsage, and LogPerformanceWarning. Adds Telemetry.LogMessage calls with consistent event IDs (PREFIX-NNN), meaningful custom dimensions (Dictionary of [Text, Text]), proper Verbosity levels (Normal, Warning, Error, Critical), correct DataClassification (SystemMetadata, CustomerContent, EndUserIdentifiableInformation), and TelemetryScope::ExtensionPublisher. Covers five telemetry categories — lifecycle events (started/completed), error tracking (validation/posting failures), performance monitoring (slow operation warnings with threshold comparison), feature usage analytics (discount types, payment methods, order size distribution), and contextual tele
bc-al-code-reviewer
by fernandoartalfReviews Business Central AL extension code against a prioritized convention stack: AppSource validation requirements, CodeCop/PerTenantExtensionCop analyzer rules, alguidelines.dev community standards, and al-copilot-skills catalogue patterns. Audits five categories that the AL compiler does not catch: naming and structure, performance anti-patterns, extensibility contract, SaaS readiness, and AppSource blockers. Produces a structured review report with severity-classified findings and a prioritized fix list. Use this skill whenever you want to review AL code before a PR, before AppSource submission, before deploying to a customer, when onboarding a new developer, when inheriting legacy AL code, or when a senior developer needs to audit an extension. Also trigger when the user says 'review my code', 'check this extension', 'is this AppSource ready', 'code quality', 'AL best practices', or 'what is wrong with this'.
onprem-remote-deploy
by fernandoartalfAL app deployment to remote Business Central OnPrem servers. Use when deploying .app files from VS Code to a BC server via WinRM, SSH, SMB, or RDP tsclient-pull when network access is restricted.
documentation-bc-phase-plan-generator
by fernandoartalfCreate the full set of per-phase implementation plan files in the `openspec/plans/` folder from an approved Business Central technical spec, following the PLAN-PHASE template structure. For each phase listed in the spec's §8 Phase Overview, generates one `SPEC-NNN-phase-<N>-<phase-name>.plan.md` file with frontmatter (id, title, version, spec, user_story, ccn, phase, status, estimated_hours, branch, depends_on, related_docs, assignee, created_date, approved_date), and the mandatory body sections (References, Goal, Branch, Tasks as checkbox list each citing the AC it satisfies, Exit criteria, Out of scope for this phase, Notes for the AL Developer, Dependencies linking prerequisite phases and downstream consumers, Testing notes). All phases are generated in a single invocation so the developer has the full execution backlog after spec approval. Use whenever the user asks to create, draft, generate, or write phase plans, implementation plans, phase breakdown, plan files, task plans, or a development backlog for
bc-reports
by fernandoartalfStandards and guardrails for authoring Business Central reports in AL and RDLC. Use when creating or modifying Report objects (.Report.al), RDLC layouts (.rdlc/.rdl), or request pages. Covers AL report structure, DataItem hierarchy, RDLC layout sizing, SetData/GetData index management, body width validation, and rendering best practices.
bc-setup-wizard-generator
by fernandoartalfGenerates assisted setup wizard pages for Business Central setup tables following Guided Experience patterns. Creates NavigatePage with step-based navigation using visibility controls, banner images (WIP/Finished from Media Repository), temporary source table, footer actions (Back/Next/Finish with InFooterBar), OnOpenPage trigger (InitRecord, EnableControls, LoadSetupBanner), OnQueryClosePage trigger with unsaved changes confirmation, navigation procedures (NextStep with Step Option variable, EnableControls with Case statement, SetControlsStepXX boolean updates), commit procedure using TransferFields pattern, and registration codeunit with OnRegisterAssistedSetup event subscriber for Guided Experience. Integrates with Assisted Setup page and Extension Management. Supports multi-step workflows with welcome step, configuration step(s), and review/finish step. Uses InstructionalText for user guidance. Completes setup via GuidedExperience.CompleteAssistedSetup. Use when creating setup wizards, implementing assist
bc-job-queue
by fernandoartalfGuides AL developers through creating, parameterizing, executing, retrying, and diagnosing Business Central Job Queue workloads. Use when asked to enqueue codeunits or reports, pass parameters through Job Queue Entry, schedule recurring jobs, run or restart failed entries, compare Job Queue with TaskScheduler or StartSession, or add telemetry and diagnostics around background processing. Triggers: "job queue", "enqueue", "ScheduleJobQueueEntry", "Parameter String", "RunJobQueueEntryOnce", "Restart", "task scheduler", "job queue telemetry", "background session", "failed job".
bc-setup-table-generator
by fernandoartalfGenerates setup table and page objects for Business Central following singleton pattern. Creates setup tables with single-record pattern, primary key field, setup page with auto-initialization on OnOpenPage, GetRecordOnce codeunit helper for performance, and common setup field patterns (Enable/Disable toggles, Default values, Number Series references, Path fields, User IDs). Handles DrillDownPageID and LookupPageID for seamless navigation. Supports multi-tenant and cloud-ready patterns. Use when creating setup tables, implementing module configuration, adding settings tables, creating admin configuration pages, building extension setup, or implementing singleton setup patterns for Business Central.
bc-api-query-generator
by fernandoartalfGenerates API query objects for Business Central that expose data via OData/REST endpoints using the QueryType = API pattern. Creates queries with single or multiple dataitems (table joins), proper API properties, column mappings, aggregation methods (Sum, Count, Average, Min, Max), filters, DataItemLink joins (InnerJoin, LeftOuterJoin, CrossJoin), and DataItemTableFilter. Supports multi-version APIs, date filters, and dimension columns. Use when asked to create an API query, generate a query endpoint, build a read-only API from joined tables, expose aggregated data via API, create reporting queries, or implement OData query endpoints.
bc-field-propagation
by fernandoartalfPropagates custom fields from source documents and journal lines to posted documents, archived documents, and ledger entries in Business Central. Selects between Pattern A (TransferFields — zero code, same Field ID on all TableExts) or Pattern B (EventSubscriber with dedicated codeunit per module) based on whether the posting codeunit uses TransferFields. Use when asked to add a field to Sales/Purchase/Transfer documents that must appear on posted invoices, shipments, credit memos, or archives; when propagating fields from Item Journal Line to Item Ledger Entry or Capacity Ledger Entry; when copying fields from Gen. Journal Line to Cust./Vendor/G/L Ledger Entry; when extending any BC posting chain with custom data. Trigger phrases include "add field to posted document", "copy field from header to invoice", "propagate field to ledger entry", "field propagation", "TransferFields custom field", "posting chain field extension".
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.