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...
gabriel-petersson-topdown-mentor
by praxstackRecursive gap-filling mentor for engineers rebuilding technical depth through top-down, problem-first learning. Use when a learner wants deep intuitive understanding (not just answers) for DSA, Java internals, System Design, or design principles — especially via real projects like CodeCrafters, LeetCode, or code review. Runs a 5-step Recursive Gap-Filling Loop (identify the shape — probe current understanding — drill down recursively with mandatory visualizations — verify click through teach-back — connect to bigger picture), supports 5 response modes (EXPLORE default, UNSTUCK, REVIEW, SOLUTION, ESCALATE), and demands intermediate-state visualization for every algorithm, data structure, or system discussion. Triggers: 'help me understand', 'drill into', 'teach it back', 'make this click', 'top-down learning', 'recursive gap-filling', 'CodeCrafters stage', 'REVIEW:', 'SOLUTION:'.
transcribe-refiner
by praxstackClean and reconstruct raw auto-generated captions (Zoom, YouTube, Teams, Google Meet, Otter.ai, etc.) into readable, coherent transcripts. Use when the user provides raw caption files (.txt, .vtt, .srt), meeting transcripts with timestamps and speaker tags, or asks to clean up/refine a transcript. Handles: timestamp removal, speaker tag normalization, filler word removal, broken sentence reconstruction, transcription error correction, paragraph formation. Preserves every piece of substantive content while removing noise. Trigger phrases: 'clean this transcript', 'refine captions', 'fix this transcript', 'process Zoom captions', 'clean up meeting notes'.
chronicle
by praxstackPersonal journal intelligence that transforms raw, unorganized thoughts into structured diary entries with psychological analysis. Use when the user provides journal entries, diary text, stream-of-consciousness writing, voice memo transcriptions, or asks to process daily thoughts into a structured format. Produces narrative entries, gratitude extraction, multi-level psychological analysis (surface/medium/clinical), health pattern flags, therapeutic micro-actions, and bridge-to-tomorrow planning. Trigger phrases: 'journal entry', 'diary entry', 'process my thoughts', 'Chronicle', 'daily reflection', 'write up my day'.
mental-health-screening-companion
by praxstackMental-health screening and journaling companion. NOT a therapist or clinician. Supports self-reflection with validated screeners (PHQ-9, GAD-7, ASRS v1.1 Part A, C-SSRS) scored for personal awareness only, psychoeducation (CBT/DBT/ACT self-help), consent-based check-in pathways (crisis-first / brief / structured), and a session-journal template. Use when the user explicitly asks for a self-reflection check-in, wants to run a validated screener for personal tracking, needs psychoeducation on mood/ADHD/anxiety, or wants structured journaling around MDD / adult ADHD / comorbid anxiety. Always screens for suicidal ideation; surfaces 988 (US) and jurisdiction-matched crisis resources. Scores are for personal reflection, NOT clinical data. Keywords: mental health, screening, self-reflection, journaling, MDD, depression, adult ADHD, anxiety, CBT, DBT, ACT, PHQ-9, GAD-7, ASRS, C-SSRS, 988, crisis, psychoeducation.
transcribe-refiner
by praxstackClean and reconstruct raw auto-generated captions (Zoom, YouTube, Teams, Google Meet, Otter.ai, etc.) into readable, coherent transcripts. Use when the user provides raw caption files (.txt, .vtt, .srt), meeting transcripts with timestamps and speaker tags, or asks to clean up/refine a transcript. Handles: timestamp removal, speaker tag normalization, filler word removal, broken sentence reconstruction, transcription error correction, paragraph formation. Preserves every piece of substantive content while removing noise. Trigger phrases: 'clean this transcript', 'refine captions', 'fix this transcript', 'process Zoom captions', 'clean up meeting notes'.
ultra-reasoning-operator
by praxstackScope-calibrated ultra-rigor workflow for hard reasoning, high-risk code changes, architecture decisions, debugging with multiple plausible root causes, security-sensitive work, and user requests like "ultra reasoning", "think harder", "verify everything", "adversarial review", "war room", "deep check", "paranoid verifier", or "no hallucinations". Use to force evidence-first planning, assumption tracking, hypothesis falsification, adversarial self-review, verification gates, and clear uncertainty without overloading trivial tasks.
backend-pe-java
by praxstackPrincipal-engineer-grade Java backend design, implementation, and review. Covers JDK 21 LTS, virtual threads, Spring Boot 3 / Micronaut / Quarkus, reactive vs. imperative, JVM tuning, concurrency primitives, and Java-specific failure modes (connection pool starvation, GC pauses, blocking in reactive, boxing in hot paths). Use when designing, building, reviewing, refactoring, hardening, profiling, or debugging Java or Kotlin backend services. Trigger keywords - Java backend, JVM, Spring Boot, Micronaut, Quarkus, virtual threads, Project Loom, JPA, Hibernate, Kafka Java, JVM tuning, GC tuning, HikariCP, G1 ZGC, Resilience4j. Not for Android work.
lecture-alchemist
by praxstackTransform raw lecture transcripts (Zoom, YouTube, etc.) into structured, retention-optimized study notes. Use when the user provides a lecture transcript, class recording text, or asks to process/convert lecture notes. Handles WebDev, AI/ML, Web3, DSA, and general tech domains. Produces hierarchical topic breakdowns, cleaned code artifacts, intuition builders, flashcards, spaced repetition plans, and actionable study materials. Trigger phrases: 'process this transcript', 'convert lecture to notes', 'lecture notes', 'transcript to study material', 'Lecture Alchemist'.
tech-tutor-ren-nakamura-persona
by praxstackIntuition-first tech mentor who makes complex concepts click through visuals, analogies, and the 6-layer explanation framework. Use this skill when the user asks to "explain", "tutor", "teach", "mock interview", or needs intuition regarding DSA, System Design, or AI/ML.
professor-alex-interview
by praxstackFAANG and HFT interview mentor with a Principal Engineer + quantitative analytics background. Use when preparing for coding, system design, behavioral, or quantitative finance interviews at Google, Meta, Amazon, Apple, Microsoft, Netflix, Uber, Citadel, Two Sigma, Jump Trading, Tower Research, DRW, Hudson River Trading, or Virtu Financial. Defaults to guided-discovery skill-building (5 levels: clarifying questions — solution direction — methodological hints — implementation guidance — complete solution) with anti-gaming safeguards, and switches to full Solution Mode only on explicit command or verified time pressure. Covers DSA, system design, low-latency C++, concurrency, probability, statistics, derivatives pricing, portfolio theory, market microstructure, and behavioral STAR-framework prep. Triggers: 'interview prep', 'mock interview', 'FAANG prep', 'HFT prep', 'Professor Alex', 'SOLUTION:', 'GUIDE:', 'TIMELINE:'.
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.