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...
service-manual-all
by UNCTAD-eRegistrationsGenerate user manuals for ALL citizen-facing services of an eRegistrations country instance, plus a catalog index page. Use when the user says "document Lesotho", "generate all manuals", "create manuals for the whole instance", or names a country/instance without specifying a single service. Do NOT use for a single service (use /service-manual) or for technical analysis (use /eregistrations-docs).
prepare-instance-for-live
by UNCTAD-eRegistrationsGenerate `prepare-instance-for-live.sh` — a self-contained bash script that prepares a prelive eRegistrations instance for go-live by clearing all runtime/published artifacts. Drops and recreates the Camunda and ds-backend (`display_system`) Postgres databases (Camunda's `schema-update: true` re-bootstraps the engine schema on restart; Django runs migrations on startup), re-applies the post-recreate privileges the apps need (`pg_trgm` extension on display_system; read-only GRANTs to the statistics role on camunda), drops the Mongo `formio` database, and deletes the `_id: 'activeservices'` document from `documents.settings`. Service-block-scoped discovery against `docker-stack.yml` extracts per-instance Postgres DB names + owner roles + the statistics role name. Live backends are terminated via `pg_terminate_backend` before each `DROP DATABASE`. Idempotent. Typed instance-name confirmation rail. Admin users are not touched — they re-sync from Keycloak on next login.
upgrade-2-16-to-2-17
by UNCTAD-eRegistrationsUpgrade a single eRegistrations instance under `Conf-<UPPER_ENV>/compose/<country>/docker-stack.yml` from 2.16 to 2.17, where `<env>` is one of dev/test/preview/prelive/live. Bumps unctad image tags from `:BETA` to `:2.17`, applies the BPA/DS/GDB service renames that landed in 2.17, pins floating `:DEV` tags for statistics, ds-frontend, gdb to `:2.17`, version-bumps `EREGISTRATIONS_VERSION` and `BUILD_TYPE`, and bumps Opensearch from 2.12.0 to 2.19.4. Strict mode — aborts on anything unexpected. Env-aware anomaly thresholds for `BUILD_TYPE` and `EREGISTRATIONS_VERSION`. Detects legacy Wildfly-style Keycloak config and aborts with guidance (KC overhaul is out of scope here — it was completed during the 2.15 cycle on most instances). LIVE invocations require a retype-country confirmation rail (skipped in chain mode). Two invocation modes: standalone (creates branch, pushes, opens PR) and chain mode (`CHAIN_MODE=1 CHAIN_BRANCH=<name>`, commits to orchestrator-managed branch). Swarm-stack (docker-stack.yml) shape
cas-to-keycloak-prepare-realm
by UNCTAD-eRegistrationsPrepare a Keycloak realm JSON configuration file by substituting all `*_PLACEHOLDER` tokens in the canonical starter-conf template with concrete values (realm code, domain, OAuth client IDs, generated client-secret UUIDs, SMTP config). Writes the realm.json to the target country's `Conf-<ENV>/compose/<country>/`. Phase 0b in the cas-to-keycloak orchestrator chain.
upgrade-2-13-to-2-14
by UNCTAD-eRegistrationsUpgrade a single eRegistrations instance under `Conf-<UPPER_ENV>/compose/<country>/docker-stack.yml` from 2.13 to 2.14, where `<env>` is one of dev/test/preview/prelive/live. This is the largest mechanical step in the chain: bumps every `unctad/<service>:$<VAR>_VER` (or pinned semver) image to `:RC` (the platform tag introduced in 2.14), drops the legacy Keycloak `/auth` path from internal and public URLs across `bpa-frontend`, `bpa-backend`, `camunda`, `mule`, `ereg-cms-frontend`, `statistics-backend`, `statistics-frontend`, renames `MONGO_URI` → `RH_MONGO_URI` on `restheart`, bumps `EREGISTRATIONS_VERSION` and `BUILD_TYPE` to the values the rest of the chain expects (non-dev: `2.14` / `RC`; dev: `DEV` / `DEV`). **Keycloak Quarkus migration is mandatory** — when Wildfly env vars are detected on the keycloak service block, the skill replaces them with the Quarkus block (`KC_DB_*`, `KC_HOSTNAME*`) without prompting; this is a hard requirement of the 2.14 baseline, not an optional cleanup. Conditionally adds an
upgrade-2-15-to-2-16
by UNCTAD-eRegistrationsUpgrade a single eRegistrations instance under `Conf-<UPPER_ENV>/compose/<country>/docker-stack.yml` from 2.15 to 2.16, where `<env>` is one of dev/test/preview/prelive/live. Bumps unctad image tags from `:RC` to `:BETA`, version-bumps `EREGISTRATIONS_VERSION` and `BUILD_TYPE` env vars, renames `RESTHEART_URL` to `RESTHEART_PUBLIC_URL` on bpa-backend, adds GDB integration env vars, and adds `RESTHEART_PASSWORD` to camunda. Strict mode — aborts on anything unexpected. Env-aware anomaly thresholds for `BUILD_TYPE` and `EREGISTRATIONS_VERSION`. LIVE invocations require a retype-country confirmation rail before commit (skipped in chain mode — the orchestrator does it once up front). Two invocation modes: standalone (creates branch, pushes, opens PR) and chain mode (`CHAIN_MODE=1 CHAIN_BRANCH=<name>`, commits to orchestrator-managed branch, no push, no PR). Swarm-stack (docker-stack.yml) shape only — instances still on docker-compose.yml must run /docker-swarm-migration first.
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.