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...
secret-warn
by adelaidasofiaReal-time edit-time guardrails that catch API keys, code injection patterns, and unsafe pipe-to-shell installs the moment they're typed in the Claude Code tool-call loop — before commit, before CI, before any second-pass review. Ships a PreToolUse + PostToolUse hook, a Bash-tool guard, and a curated 11-rule regex catalog covering the most common secret shapes (AWS, Stripe, GCP, OpenAI, Anthropic, GitHub, Slack, JWT, PEM, generic high-entropy assignment) plus three injection-pattern classes. Use when the user mentions secret detection, gitleaks-equivalent during edit time, pre-commit secret scanning, API key safety, edit-time guards, security hooks in Claude Code, or wants real-time protection against unsafe MCP server installs. Do NOT use for full security audits (different scope), penetration testing, or DLP across non-Claude-Code surfaces.
insights
by adelaidasofiaWeekly and monthly journal insights -- pattern recognition, floor trends, life coach pushback, therapist observations, and advisory panel thoughts. Use /weekly for the current calendar week, /monthly for the current calendar month. Do NOT use for daily journal entries (use daily-journal), cross-session pattern extraction (use patterns), or operational reviews.
ingest-gmail
by adelaidasofiaPulls recent Gmail messages matching a label or query into the vault as queryable markdown. Use when the user says /ingest-gmail <label-or-query> [--days N], or asks to ingest, capture, sync, or pull a Gmail label or query into the vault. Writes one file per scope per day to External Inputs/Gmail/<label>/<date>.md. Truncates each message body to 500 chars to limit bulk PII. Idempotent: re-running on the same day overwrites cleanly. Do NOT use for sending email, replying, or non-Gmail sources.
coaching
by adelaidasofiaMulti-pass coaching session for processing a hard conversation, decision, or accumulated tension that won't fit in a daily journal. Runs panel passes with corrections, surfaces patterns to track over time, files a synthesized accountability record, and updates the rolling Panel Feedback Log. Use when the user wants honest panel feedback on a specific event (a difficult call, a decision they're second-guessing, accumulated friction with a person), wants to track whether they're growing on a specific theme over weeks/months, or wants the panel to run multiple passes with their corrections instead of one shot. Do NOT use for daily journal entries (use /journal), weekly/monthly reviews (use /weekly or /monthly), one-off panel reactions inside a journal (those run inline in /journal), or pattern detection across many sessions (use /patterns).
modern-python-substrate
by adelaidasofiaModern Python toolchain substrate. uv for installs and venvs, ruff for lint and format, ty for typecheck, pytest for tests, hypothesis for property-based tests, src/ layout, pyproject.toml as single source of truth, pre-commit hooks. Plus LLM-stack patterns when the codebase calls anthropic, openai, tiktoken, or similar SDKs (prompt caching, retries, streaming, token counting). Use when the user says /python-setup, "set up Python project", "modern Python toolchain", "switch from poetry to uv", "ruff config", "ty migration from mypy", "configure pytest", or starts a new Python codebase. Covers Python 3.11+ idioms.
synth-thread-to-sop
by adelaidasofiaRead a resolved Slack thread markdown export and synthesize a typed memory entry (decision, exception, or workflow) into Meta/. Trigger /synth-thread-to-sop <slack-thread-markdown-file>. Use when a thread captures a one-time decision, a documented deviation, or a repeatable procedure worth filing. Do NOT use for raw Slack ingestion (use the Slack ingest skill for that) or for PR sources (use /synth-pr-to-sop).
coach
by adelaidasofiaLongevity + fitness coach. Issues a daily workout prescription that reads from health-mcp (recovery, sleep, cycle phase, somatic state, lab status) and pairs with today's Floor (emotional state) from journal frontmatter. Tracks progressive overload per-lift. Programs deload every 4th week. Drops weekly plan into Google Calendar. Use when user says /coach, /coach today, /coach week, /coach profile, /coach log, asks "what should I do today", asks for a workout, asks for a longevity plan, or asks how to train. Pairs with health-context (already auto-fires) and insights (already body-track wired). The substrate's longevity-coach surface.
longitudinal
by adelaidasofiaMulti-year health-mcp pattern surface. Scans years of HealthKit + journal data, returns ONLY the strongest correlations (Briden noise filter). Use when the user asks for "patterns in my health data," "what does my body tell me," "correlations between mood and HRV," "Floor x body fingerprint," or runs /longitudinal. Do NOT use for single-day analysis (use /health-doctor), this-week patterns (use /weekly), or pattern extraction across journals only (use /patterns).
backfill-journal-body-context
by adelaidasofiaWalks every daily journal entry in a date range (default this year) and appends a "Body track" section BELOW the original verbatim content. Pulls health-mcp data for each date (HRV, RHR, sleep, cycle phase, lab status, recovery/sleep/strain scores) and weaves a Floor-paired interpretation. Idempotent (skips entries that already have the section). Use when user says /backfill-journal-body-context, asks to enrich journals with body data, says "backfill my journals with health" or wants existing journal entries paired with their Apple Health / Oura / Fitbit data retroactively.
health-context
by adelaidasofiaAuto-fires when the daily-journal, coaching, advisory-panel, patterns, or insights skills run. Pulls health context (HRV, sleep, recovery) from the health-mcp DuckDB and folds it into the active skill's prompt. Use when user invokes /journal, /coaching, /panel, /patterns, /weekly, /monthly, or any skill that benefits from biometric context. Read-only with respect to the vault. Skip silently if health-mcp is not registered or has no data.
ingest-health
by adelaidasofiaImports Apple Health data into the local DuckDB used by health-mcp. Three modes (XML export.zip, Simple Health Export CSV folder, Health Auto Export TCP-live). Use when the user says /ingest-health, asks to import health data, sync Apple Health, or set up the health connector. Idempotent: re-running on the same file is a no-op unless force=True. Reads only; never writes vault.
vertical-healthcare
by adelaidasofiaPre-configured healthcare vertical pack for the ai-brain-starter substrate. Ships typed-memory categories for patient-scoped facts, clinical decisions, PHI-tagged docs, BAA counterparties, and breach notification; HIPAA-aligned retention defaults plus per-state add-ons; connectors for Epic FHIR, Cerner FHIR, and Salesforce Health Cloud; decision-audit patterns for PHI handling against the 18 HIPAA identifiers and clinical-decision evidence chains. Use when onboarding a covered entity, business associate, or health system that needs the substrate to come pre-shaped to HIPAA, BAA, and clinical-decision audit obligations.
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.