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...
delivery-handoff
by mariourquiaCoordinates the transition from construction delivery to operating asset. Fires on Procore schedule_milestone `temp_co_received` or `final_co_received` (with units_ready_for_lease >= 1), or on AppFolio C/O recording (Handoff 8 in reference/connectors/_core/stack_wave4/lifecycle_handoffs.md). Drives TCO/CO recording, punchlist state review, retainage release schedule, rent-roll transition from lease-up plan to active, construction-sub vs operating-vendor rationalization, warranty package handoff, system as-built documentation acceptance, capex project closeout in Intacct, and dev_project_crosswalk closure (procore_project_id -> property_id linkage). Triggers lease_up_first_period once the AppFolio unit roster is active. Writes back to master_data crosswalks via approval. Handoff is not complete until every item lands within the tolerance band and development_lead signs off.
development-pipeline-tracking
by mariourquiaWeekly roll-up of the active development pipeline. Aggregates sites under contract, in entitlement, in design, in permitting, and in construction (by phase); tracks TCO/delivery target dates, baseline-vs-current schedule slip, baseline-vs-current cost slip, change-order trend, draw schedule status, contractor performance flags, lease-up readiness, and financing draw status. Groups by region and deal_lead. Flags critical-path slips beyond tolerance and escalates Dealpath/Procore/Intacct reconciliation blockers. Narrative-first with a KPI dashboard. Informational to recommendation severity: this pack produces a weekly tracker, not approvals. Gated actions (rebaseline, scope trim, contingency pull, change orders) remain in their own workflows (`schedule_risk_review`, `cost_to_complete_review`, `change_order_review`).
regional-manager-residential-multifamily
by mariourquiaMulti-property operations leader covering a portfolio region. Owns site performance, staffing, training, policy adherence, and escalation triage for a set of properties. Consolidates site scorecards, drives corrective actions on underperformers, and is the first gate on site-originated legal notices, evictions, concession exceptions, and above-threshold disbursements.
stacking-plan-builder
by mariourquiaGenerates text-based stacking plans from rent rolls, providing floor-by-floor visual layout of tenant occupancy, lease expiration, contiguous availability analysis, rollover concentration, and prospect pipeline overlay.
building-systems-maintenance-manager
by mariourquiaBuilding systems monitoring, preventive maintenance program management, equipment lifecycle tracking, inspection coordination, and compliance documentation. Covers HVAC, elevator, fire/life safety, roofing, and MEP systems. Triggers on 'PM schedule', 'maintenance plan', 'equipment replacement', 'building inspection', 'HVAC maintenance', 'elevator inspection', 'fire safety', 'deferred maintenance', or when given building systems data and maintenance history.
maintenance-supervisor-residential-multifamily
by mariourquiaOn-site maintenance leader. Owns work order triage, P1 life-safety SLA, turn production, preventive maintenance execution, and vendor dispatch inside approved rate cards and thresholds. Routes life-safety scope changes, licensed engineering judgments, and above-threshold dispatches per the approval matrix.
lead-to-lease-funnel-review
by mariourquiaDiagnostic review of the leasing funnel from lead through move-in. Identifies where the funnel is breaking (response time, tour conversion, application conversion, approval, move-in), quantifies exposure, surfaces fair-housing and screening-drift flags, and proposes a remediation plan with owner-specific target bands. Recurring weekly at the property level; invoked ad hoc when notice exposure or leased occupancy slips.
acquisition-handoff
by mariourquiaCoordinates the handoff from deal close to an operating asset. Fires when Dealpath emits the deal-close event (Handoff 1 + Handoff 3 in reference/connectors/_core/stack_wave4/lifecycle_handoffs.md). Drives AppFolio property setup, Intacct legal-entity dimension setup, vendor master rationalization, opening rent roll load, PMA execution if third-party managed, lender reporting registration, and data-platform property_master_crosswalk row creation. Produces a handoff checklist with per-item status, verifies completion within the handoff-lag tolerance band, and surfaces blockers for gated approval. Writes back to master_data crosswalks via approval before the handoff is marked complete.
human-readable-role-name
by mariourquiaOne paragraph: what the role does and when it triggers.
loan-document-reviewer
by mariourquiaReview CRE loan documents for covenant compliance, carve-out exposure, cash management tripwires, and borrower obligations. Branch by loan type (agency, CMBS, bank, bridge, construction, mezzanine), recourse structure, mezzanine/preferred equity interaction, and construction draw mechanics. Interrogate recourse type, mezz presence, assumption vs. new origination, and environmental concerns before reviewing. Triggers on 'review loan docs', 'covenant analysis', 'carve-out review', 'loan agreement', 'review the note', 'debt covenants', 'cash sweep trigger', 'transfer provisions', 'default and remedy', 'intercreditor', or when user provides draft or executed loan documents.
agency-loan-quote-analyzer
by mariourquiaAnalyzes Freddie Mac and Fannie Mae agency multifamily quotes (lease-up and stabilized) into a decision-ready package. Reconciles each quote's DSCR/LTV/LTPP sizing constraints, prices rate buy-downs and IO-vs-amortization trade-offs, models index-lock and rate-cap mechanics, maps lease-up holdback funding gates, audits replacement-reserve and escrow stipulations, applies recourse/guarantor and net-worth/liquidity tests, scores prepayment (yield maintenance vs defeasance vs declining penalty), and surfaces every quote caveat. Produces a side-by-side scenario matrix, a recommended base case, a funding-gate checklist, and a caveat list. Triggers on 'analyze this agency quote', 'compare Freddie vs Fannie', 'DUS quote', 'Optigo quote', 'lease-up agency loan', or when given one or more agency term sheets.
term-sheet-builder
by mariourquiaDraft and negotiate CRE financing term sheets from lender quotes. Branch by loan type (agency, CMBS, bank balance sheet, bridge, construction, mezzanine), borrower entity, and deal strategy. Interrogate rate preference, hold period, recourse tolerance, and stack complexity before drafting. Triggers on 'draft term sheet', 'lender quote', 'rate lock', 'negotiate terms', 'loan terms', 'prepayment', 'IO period', 'spread', 'carve-outs', or when user provides a lender quote for review.
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.