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...
exercise-tracking-planning
by NanoRhinoTracks workouts, estimates calories burned, gives fitness feedback, AND designs personalized exercise/training programs. Use when user logs a workout, describes physical activity, uploads fitness tracker data, asks for a weekly exercise summary, OR requests a workout plan, training program, exercise routine, or fitness schedule. Trigger phrases include "I ran...", "I did...", "just finished...", "log my workout", "went to the gym", "played basketball", "walked for...", "swam...", "lifted weights", "make me a workout", "design a training plan", "I want to start working out", "help me build a program", "exercise plan", "gym routine", "training split", "I need a fitness program", "what should I do at the gym", "how should I train" (and equivalents in any language). Even casual mentions of physical activity ("took the stairs", "biked to work") should trigger this skill. Also trigger when user uploads or pastes data from fitness devices (Apple Watch, Garmin, Strava, etc.) or asks for a weekly exercise summary. Whe
meal-planner
by NanoRhinoPersonalized meal planning skill that creates sustainable, calorie-controlled weekly meal plans based on a user's weight loss targets and dietary preferences. Supports multiple diet modes including Balanced/Flexible, Low-Carb/Keto, Mediterranean, Intermittent Fasting (16:8, 5:2), High-Protein, and Plant-Based. Use this skill whenever the user asks for meal plans, diet plans, what to eat, food recommendations, weekly menus, macro-based eating plans, or recipe suggestions tied to weight loss goals. Also trigger when the user mentions wanting help with meal prep, portion control, healthy eating habits, or asks "what should I eat to lose weight." This skill builds on top of the weight-loss-planner skill — it expects a daily calorie target and weight loss context to already exist (from a prior plan or USER.md), but can also operate standalone if the user provides their calorie target directly. Adapts foods, units, and restaurant recommendations to the user's country/region, inferred from language or user input.
weight-loss-planner
by NanoRhinoPersonal nutritionist skill for weight loss goal-setting and milestone planning. Creates personalized Markdown reports with BMI analysis, TDEE-based calorie targets, and phased milestone roadmaps. Use this skill when the user mentions weight loss goals, diet planning, calorie targets, BMI, TDEE, or asks for a weight loss plan. Also trigger when user wants to calculate how long to reach a target weight.
restaurant-meal-finder
by NanoRhinoOn-demand restaurant meal recommendation skill. When the user asks "what should I eat?" or wants dining suggestions, this skill first establishes the user's location, searches for nearby restaurants and delivery options, caches them locally, and then recommends specific calorie-appropriate meals from those real restaurants. The restaurant list is persisted so repeat queries don't require re-searching. Use this skill whenever the user asks for restaurant recommendations, what to order when eating out, nearby dining options that fit their diet, or fast-food / takeout / convenience store meal suggestions. This skill complements the meal-planner (which builds restaurant options into weekly plans) by handling real-time, on-the-spot dining decisions grounded in the user's actual nearby options.
jdcloud-oss-upload
by NanoRhinoUpload local files to JD Cloud OSS and get presigned URLs (15 min expiry). Use when needing to share local files via URL, send images to chat channels that require public URLs, or upload any file to cloud storage. Supports images, PDFs, videos, and any file type.
habit-builder
by NanoRhinoDesigns and manages healthy habits for sustainable weight loss. Atomic Habits / Tiny Habits methodology. Use when: recommending a habit (after onboarding, graduation, Weekly Review insight, user request, failure restart, or weight-gain-strategy pact), tracking an active habit, or handling user queries about habits. Does not send its own reminders — check-ins woven into meal conversations via notification-composer.
personal-data-query
by NanoRhinoQuery personal health and diet data. Use when user asks about today's intake, daily progress, calorie summary, or 'how am I doing today'. Trigger phrases: 'how many calories today', 'what did I eat', 'today's progress', '今天吃了多少', '今天还剩多少', '今日进度', '今天怎么样了'. Do NOT trigger for logging food or recording weight — those go to diet-tracking-analysis and weight-tracking respectively.
streak-tracker
by NanoRhinoCalculates consecutive meal-logging streak and returns pending milestone data. Called BY other skills only — not a standalone conversation skill. WHEN to call: - notification-composer (Stage 1 only): during meal reminder Generation Flow step 4. If pending_milestone is not null, the milestone celebration becomes the opening line. If current_streak >= 2, use daily streak opening. - weekly-report: include current streak in the weekly summary section. - User explicitly asks about their streak ("what's my streak", etc.). WHEN NOT to call: - During recall phase (Stage 2/3/4) — no streak check, no streak mention. - During normal conversation — never proactively bring up streak unless the user asks or a milestone is pending at meal reminder time. - After a streak breaks — say nothing about it. DELIVERY: woven into meal reminders by notification-composer as the opening line. This skill never sends messages directly — only provides data. Returns: JSON with current_streak, pending_milestone, milestones_celebrated.
weight-gain-strategy
by NanoRhinoDetect and respond to upward weight trends after weigh-ins or when the user asks why their weight is increasing. Use for: (1) consecutive weight increases detected by post-weigh-in deviation checks, (2) explicit weight-gain questions like 'why am I gaining weight' or '体重怎么涨了'. Provides graduated support from reassurance to cause analysis to temporary adjustment strategies. Do not use when emotional distress needs higher-priority support or when weight-focus should be avoided (history_of_ed / avoid_weight_focus flags).
diet-tracking-analysis
by NanoRhinoTracks what users eat, estimates calories and macros, manages daily calorie targets, and gives practical feedback based on cumulative daily intake. Trigger when user sends a photo, logs food, describes a meal, mentions what they're about to eat or drink, or sets a calorie target. Also trigger for past-tense reports ('I had...', 'I ate...'). Even casual mentions ('grabbing a coffee') should trigger. NOT for general behavioral patterns without specific food (e.g. 'I skip breakfast', '我喝水很少') — defer to habit-builder.
miniprogram-migration-followup
by NanoRhinoFollow-up onboarding for users who migrated from the WeChat miniprogram (小犀牛AI健康) to WeCom. The miniprogram version of onboarding skips the long-term coaching setup (meal schedule, daily reminders, check-in flow introduction) because the miniprogram cannot send cron messages. When such a user adds the WeCom bot and sends their first message, this skill runs a short follow-up to fill those gaps. Trigger when all three conditions hold: (1) workspace has `.from-miniprogram.json`, (2) workspace does NOT have `.migration-followup-completed`, (3) user has just sent a message. Do NOT trigger on every subsequent message.
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.