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...
weekly-report-format
by mgoodman60Generate polished weekly owner/PM summary reports from daily report data. Use when the user asks to "generate a weekly report", "weekly summary", "owner report", "weekly owner report", "PM report", "send the weekly", "weekly update", or wants to aggregate daily reports into a weekly narrative.
environmental-compliance
by mgoodman60Environmental compliance management for construction projects. Covers LEED v4.1 construction administration, SWPPP permit compliance and inspections, hazardous materials management (asbestos, lead, mold, contaminated soil), construction waste management and diversion tracking, dust and air quality control, noise ordinance compliance, silica exposure prevention, and environmental incident response. Beyond basic BMP installation (see field-reference/bmp-field-guide.md). Triggers: "environmental", "LEED", "SWPPP", "hazmat", "hazardous materials", "asbestos", "lead paint", "waste management", "dust control", "noise", "environmental compliance", "recycling", "diversion", "VOC", "silica", "EPD", "HPD", "spill", "contaminated soil", "mold", "air quality", "noise variance", "waste diversion", "C&D waste".
safety-management
by mgoodman60Comprehensive safety management system for construction projects. Handles incident tracking, OSHA reporting (300/300A/301), toolbox talks, JSA/JHA creation, site safety inspections, permits, emergency planning, and safety metrics/KPIs. Integrates with schedule for activity-based hazards and daily reports for safety observations. Triggers: "incident", "near miss", "toolbox talk", "jsa", "jha", "job safety analysis", "inspection", "osha", "recordable", "first aid", "hot work", "confined space", "permit", "safety metrics", "trir", "dart", "emr", "emergency plan", "safety meeting".
bim-coordination
by mgoodman60BIM coordination and model-based field management for construction superintendents. Manage clash detection workflows, model-to-field verification, 4D scheduling integration, laser scanning and point cloud operations, drone surveys, digital twin closeout handoff, and LOD specification tracking. Track clash reports, model reviews, field verifications, scan records, drone flights, and coordination meetings through a structured data model. Integrates with morning-brief, daily-report, rfi-preparer, look-ahead-planner, closeout-commissioning, and drawing-control. Triggers: "BIM", "model", "clash", "clash detection", "Navisworks", "Revit", "coordination", "4D", "laser scan", "point cloud", "drone", "digital twin", "LOD", "BIM execution plan", "BxP", "model review".
drawing-control
by mgoodman60Manage drawing revisions, ASI incorporation, superseded sheet flagging, and current-set verification. Ensures the field always works from the latest approved drawings. Tracks distribution, validates references in daily reports and RFIs, and alerts on obsolete sheet usage. Triggers: "revision", "ASI", "current sheet", "superseded", "drawing log", "drawing distribution", "obsolete drawing", "sheet update", "field set", "current set", "drawing status", "new revision", "void drawing", "latest drawing", "which revision", "update the drawings", "drawing register".
cobie-export
by mgoodman60Generate Construction Operations Building Information Exchange (COBie) compliant spreadsheets from existing project intelligence data. Maps extracted data into the 18 standard COBie worksheet format for facility management handover. Critical for healthcare facilities where ongoing maintenance and asset management are regulatory requirements. Exports as multi-tab Excel workbook. Triggers: "COBie", "COBie export", "facility handover", "asset register", "O&M data", "building information exchange", "commissioning data", "facility management data", "asset data", "COBie spreadsheet", "handover data", "building handover".
inspection-tracker
by mgoodman60Track inspections and permits through the construction lifecycle. Handles scheduling, result logging, re-inspection tracking, permit management, and status reporting. Healthcare-specific: state health dept inspections, life safety, ADA compliance. PEMB-specific: anchor bolt, high-strength bolt, moment connection special inspections. Integrates with morning brief and look-ahead. Triggers: "inspection", "schedule inspection", "log inspection", "inspection status", "permit", "failed inspection", "re-inspect", "upcoming inspections", "special inspection".
quality-management
by mgoodman60Formal Quality Management System (QMS) with three-phase inspection checklists (pre-installation, installation, post-installation) organized by CSI division and trade. Provides specification compliance verification, Inspection and Test Plans (ITP), corrective action tracking, and quality metrics reporting. Integrates with inspection-tracker, sub-performance, and daily reports. Triggers: "quality checklist", "QMS", "pre-install checklist", "three-phase inspection", "quality verification", "ITP", "inspection test plan", "quality control", "quality assurance", "QA/QC", "pre-install", "post-install", "quality report", "first-time quality", "rework tracking".
quantitative-intelligence
by mgoodman60Bridge between all measurement sources (DXF geometry, visual plan analysis, construction takeoff, text extraction) and the project intelligence data store. Builds a complete sheet cross-reference index mapping every detail callout, section cut, schedule reference, and spec reference across the entire plan set. Calculates derived quantities (concrete volumes, room areas, material totals, fixture counts) by pulling data from multiple sheets through assembly chains. Stores quantities with source attribution and flags discrepancies when sources disagree by >10%. Triggers: "how much concrete", "total flooring", "room areas", "material quantities", "what quantities", "how many outlets", "cubic yards", "square footage", "takeoff to project", "cross-reference sheets", "assembly chain", "which sheets reference", "detail callout index", "multi-sheet calculation", "aggregate quantities", "quantity discrepancy".
sub-performance
by mgoodman60Objective, data-driven subcontractor performance scorecards based on five weighted dimensions: Schedule Adherence (25%), Quality (25%), Safety (20%), Responsiveness (15%), and Professionalism (15%). Aggregates data from daily reports, inspections, PPC tracking, safety records, and RFI/submittal turnaround. Enables informed bidding decisions, back-charge documentation, and performance improvement conversations. Triggers: "sub scorecard", "subcontractor performance", "rate sub", "sub evaluation", "vendor performance", "trade performance", "sub rating", "contractor scorecard", "performance review", "back charge", "sub report card".
project-data-intel
by mgoodman60Comprehensive Project Data Intelligence dashboard — the single source of truth for ALL extracted project data. Template-based architecture with 40+ sections covering building data, quantities, financials, specifications, project controls, spatial analysis, and AI rendering. Triggers: "/data", "show me all the data", "project intelligence", "room browser", "quantity dashboard", "material calculator", "bid comparison", "project brain dashboard", "show everything we know", "data dashboard", "what data do we have".
change-order-tracker
by mgoodman60Track change orders from initiation through resolution. Handles CO creation, status updates, cost/schedule impact tracking, and CO log generation. Integrates with morning brief (pending COs) and weekly report (CO summary). Triggers: "change order", "CO", "PCO", "COR", "add a change order", "CO status", "CO log", "pending change orders".
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.