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...
agent-shift-settlement
by tobias363When the user/agent works with the agent shift lifecycle, cash-in/cash-out, daily-balance control, or end-of-day settlement (BIN-583) in the Spillorama bingo platform. Also use when they mention AgentShiftService, AgentSettlementService, AgentTransactionService, AgentTransactionStore, HallCashLedger, app_agent_shifts, app_agent_settlements, app_agent_transactions, daily-balance, control-daily-balance, close-day, settlement, machine-breakdown, MachineBreakdownTypes, Metronia, OK Bingo, Franco, Otium, Norsk Tipping (Dag/Totalt), Norsk Rikstoto (Dag/Totalt), Rekvisita, Servering/kaffe, Bilag, Bank, Gevinst overført, Drop-safe, Shift-diff, NOTE_REQUIRED, FORCE_REQUIRED, distribute winnings, transfer register ticket, dropsafe, B3.3, BIN-583. The settlement-popup is wireframe-paritet-critical (PDF 15+16+17 §15.8). Make sure to use this skill whenever someone touches AgentShiftService, AgentSettlementService, the machine-breakdown type, the close-day flow, or the threshold-rules — even if it looks like a small tweak
wallet-outbox-pattern
by tobias363When the user/agent works with wallet-mutating code, payout, ticket-purchase, idempotency-keys, REPEATABLE READ isolation, hash-chain audit, eller wallet-reconciliation. Also use when they mention WalletAdapter, walletAdapter, PostgresWalletAdapter, InMemoryWalletAdapter, app_wallet_outbox, app_event_outbox, app_compliance_audit_log, WalletOutboxRepo, WalletOutboxWorker, WalletAuditVerifier, IdempotencyKeys, REPEATABLE READ, hash-chain, audit-trail, ledger-events, casino-grade, mutation-test stryker, BIN-761, BIN-762, BIN-763, BIN-764, BIN-766, BIN-767, BIR-036, ADR-003, ADR-004. Make sure to use this skill whenever someone touches wallet-touch code, payout-services, ticket-purchase, eller compliance-ledger — even if they don't explicitly ask for it.
fysisk-bong-katalog
by tobias363When the user/agent works with PHYSICAL bingo bongs (papir-bonger) for Spill 1 — the supplier card catalog (kortnr → 25 tall), the CODE-128 barcode on each bong, bunt-registration/sales-scan flow, or resolving a sold/scanned physical bong to its bingo numbers for the live draw. Use when they mention fysisk bong, papir-bong, strekkode, barcode, kortnr, card_serial, bricknr, brick, bunt, blad, trippel/single bong, Liten/Stor bong, Trafikklys-bong, app_bingo_card_catalog, bingoCardCatalogParser, bongBarcodeParser, buntCardMapping, import-bingo-catalog, TecnoBingo/Sandens/Bengt Thell catalog, zbarimg, "scan øverste/nederste bong", "registrer bunt", "selg + avslutt runde", exclusive scan-ny-øverste, cross-bunt rest-overføring, Tremina-reserved serie, or the P7 pooled physical payout. This is the data/parsing layer that lets a physically-sold bong join the live Spill 1 draw and auto-validate against drawn balls — its §11 STAKE/price side is governed by the pengespillforskriften-compliance skill. Load this whenever
health-monitoring-alerting
by tobias363When the user/agent works with R7 health-endpoints or R8 alerting for the Spillorama bingo platform. Also use when they mention /api/games/spill[1-3]/health, GameRoomHealth, RoomAlertingService, R7, R8, BIN-814, BIN-815, health-endpoint, p95-latency, draw-stale, alerting, PagerDuty, Slack-alert, Spill 2 perpetual-loop, Spill 3 monsterbingo singleton. Defines per-room health snapshot schema, status-mapping, rate-limit, and the alert-pipeline that keeps live rooms self-reporting. Make sure to use this skill whenever someone touches the health routes, RoomAlertingService, or per-room observability hooks even if they don't explicitly ask for it — these are pilot-gating per the Live-Room Robustness Mandate.
live-room-robusthet-mandate
by tobias363When the user/agent works with rom-arkitektur, socket-events, draw-tick, ticket-purchase, wallet-touch fra rom-events, eller pilot-gating-tiltak (R1-R12). Also use when they mention RoomAlertingService, SocketIdempotencyStore, EngineCircuitBreakerPort, R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, R12, BIN-810, BIN-811, BIN-812, BIN-813, BIN-814, BIN-815, BIN-816, BIN-817, BIN-818, BIN-819, BIN-820, BIN-821, BIN-822, chaos-test, failover, klient-reconnect, idempotent socket-events, clientRequestId dedup, health-endpoint per rom, alerting Slack PagerDuty, DR-runbook, Evolution Gaming-grade oppetid, 99.95%, perpetual-loop leak, per-rom resource-isolation, stuck-game-recovery, monotonic stateVersion, RoomStateStore, SerializedRoomState, scheduledGameId-persistens, isHallShared-persistens, isTestHall-persistens, pendingMiniGame-persistens, spill3PhaseState-persistens, Redis-restart-recovery, Game1GhostRoomSweepService, ghost-room-sweep, spøkelsesrom, teardown-løs cancel, ADR-0019, ADR-0020, ADR-0022. Make sure to
debug-hud-gating
by tobias363Gate-strategi for debug-HUD + event-log-panel i Spillorama spillerklient. Use when the user or agent works with debug-HUD, event-log-panel, debug-gating, isDebugHudEnabled, mountDebugHud, DebugEventLogPanel, ConsoleBridge, FetchInstrument, ErrorHandler, FetchBridge, EventTracker, EventStreamer, or anything related to player-shell debug-overlay synlighet. Use this whenever someone touches `packages/game-client/src/games/game1/Game1Controller.ts`'s mountDebugHud-block, `packages/game-client/src/games/game1/debug/*` debug-modulene, or considers changing how debug-HUD aktiveres — even if they don't mention debug-gating directly.
audit-hash-chain
by tobias363When the user/agent works with the hash-chain audit-trail used for Lotteritilsynet-traceability in the Spillorama bingo platform. Also use when they mention AuditLogService, app_audit_log, app_compliance_audit_log, app_regulatory_ledger, app_daily_regulatory_reports, wallet_entries, prev_hash, curr_hash, entry_hash, event_hash, signed_hash, previous_entry_hash, REGULATORY_LEDGER_GENESIS, WALLET_HASH_CHAIN_GENESIS, canonicalJsonForEntry, canonicalJsonForLedgerEntry, canonicalJsonForDailyReport, computeEntryHash, computeLedgerEventHash, computeDailyReportSignedHash, hash-chain, BIN-764, ADR-0004, ADR-0015, RegulatoryLedgerStore, RegulatoryLedgerService, DailyRegulatoryReportService, RegulatoryLedgerHash, WalletAuditVerifier, PostgresWalletAdapter.hashChain, walletAuditVerify cron, wallet-integrity-watcher, audit-trail integrity, casino-grade audit, immutable ledger, §71-rapportering, pengespillforskriften §71, daily regulatory report, parallel-write to canonical ledger. Hash-chain integrity is what lets Lotteri
tv-screen-design
by tobias363When the user/agent works with the public hall-TV display for Spill 1 — the 1920×1080 stage, its states (venteskjerm/nedtelling/aktiv-trekning/vinn-en-rad/fullt-hus/stoppet/vinnere), the header, the Trukket-counter, the pattern table, the jackpot strip, or the felt-atmosphere decor. Also use when they mention TVScreenPage, WinnersPage, tv-screen.css, tvStageDecor, tvScreenSocket, tvFullscreenControl, TvScreenService, PHASE_NAMES, .tv-stage-header, .tv-header-counter, .tv-screen-body, .tv-active-wrap, .tv-patterns, .tv-pat-row, .tv-draw-area, .tv-big-ball, .tv-drawn-strip, .tv-jp-strip, .tv-jp-mini-row, .tv-phase-banner, scaleStage, screenFor, buildDrawingBody, renderState, nextGameDisplayPort, getNextGameDisplayForTvHall, /api/tv/:hallId/:tvToken/state, /api/tv-group/:groupSlug/state, the tv-design preview pages (apps/admin-web/public/tv-design/*), or 16:9/fullscreen TV concerns. Make sure to use this skill whenever someone touches `apps/admin-web/src/pages/tv/*` or `apps/backend/src/game/TvScreenService.ts`
anti-fraud-detection
by tobias363When the user/agent works with anti-fraud / velocity / bot-detection signals on wallet mutations in the Spillorama bingo platform (BIN-806 / A13). Also use when they mention AntiFraudService, AntiFraudWalletAdapter, app_anti_fraud_signals, fraud-risk, FRAUD_RISK_CRITICAL, FRAUD_RISK_HIGH, VELOCITY_HOUR, VELOCITY_DAY, AMOUNT_DEVIATION, MULTI_ACCOUNT_IP, BOT_TIMING, antiFraudContext, pre-commit decoration, velocity-check, bot-detection, multi-account-IP, AML red-flag, RedFlagPlayersReport, AmlService.flag, money-mule. Anti-fraud rides on top of the casino-grade wallet via the AntiFraudWalletAdapter pattern — it never blocks legitimate play, but it MUST throw pre-commit on critical risk and ALWAYS fail open on DB-errors. Make sure to use this skill whenever someone touches WalletAdapter wrapping, anti-fraud signal evaluation, or AML red-flag emission — even if the change looks like "just a velocity tweak" — because mis-tuning can either flood ops or silently miss money-mule rings.
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.