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...
tam-mapping
by Brite-NitesBuild TAM databases from scratch using a 7-phase methodology (Source Discovery → Keyword Expansion → Config → Collection → Dedup → Exclusion → Enrichment hand-off). Triggers "tam map", "build tam", "total addressable market", "scrape industry", "map the market", "build a lead database", "venue partnerships tam", "labs tam", "residential tam", "installer tam". Entity-routed — Nites residential (Google Maps ZIP), Supply installer (SAM.gov + Houzz + state license dbs), Labs venue partnerships (Spider.cloud + AI Ark + Discolike + IcyPeas + BlitzAPI + Prospeo + MillionVerifier). Phase 4.5 cross-workspace EB exclusion is MANDATORY (HARD-FAIL on either workspace unreachable). Phase 5 enrichment is pluggable per ADR-008. Distinct from `list-building` (BC-2717 — assumes a TAM already exists via dbt audience views).
setup-claude-md
by Brite-NitesGenerates a best-practices CLAUDE.md file for the project. Analyzes the codebase and applies Claude Code best practices for optimal agent performance. Use at project setup or after /create-issues.
greptile-gate
by Brite-NitesAfter a PR is opened (or on demand), read Greptile's 0–5 confidence score and converge the PR toward 5/5 — grill on intent, fix review findings, re-trigger Greptile, loop up to 3 rounds, then run a final independent review. Use during /workflows:ship right after the PR is created, or when the user asks to check the Greptile score, run the Greptile gate, or read/address the Greptile review on a PR. Skips gracefully when Greptile isn't on the repo.
flow-legacy-cross-reference
by Brite-NitesRetrofit-only sub-skill for the flow-architecture plugin (implements CDR-023). NEVER invoked from greenfield. Satisfies Q9's additive-only "cross-reference annotations" lock by appending an HTML-comment-bracketed `## FDA migration` section to every legacy Linear milestone description, mapping it to one or more FDA domains. Three-tier mapping cascade (flow-ID histogram -> title-fuzzy -> LLM semantic), marker-based idempotency, two-pass execution (generate review doc -> user edits + bumps `last_reviewed` -> re-invoke executes). End-to-end wall for M=27 legacy milestones: ~14s Tier 1 batched-body reads (Tier-1 budget assumes Linear MCP's `list_issues({milestone})` filter is reliable — see Section 1 caveat) + ~5-15s Tier 3 LLM fall-throughs (when 5-10 milestones don't hit Tier 2) + ~40.5s Pass 2 writes (3 calls/milestone) ≈ **~60-70s** when filter behaves; significantly more if the milestone-filter gotcha forces a per-child `get_issue` fallback.
flow-linear-scaffold
by Brite-NitesHeaviest-mutation sub-skill for the flow-architecture plugin (implements CDR-023). Writes per-domain Linear scaffolding — 1 milestone + N sub-flow parent issues + 5N discipline children + N Children-summary comments + 1 milestone description refresh = 2+7N writes per domain. Per-sub-flow execution unit, per-domain preview/approval. 3-layer idempotency (`.flow/scaffold-log/<domain>.md` append-only + per-sub-flow `list_issues` lookup + MCP error row flag). 100% per-issue fidelity-review coverage via background `Agent(general-purpose)` dispatch with sub-flow-boundary collection (every 6 issues). 1 mandatory pre-scaffold preview gate; conditional gates for failure recovery only. Sub-flow-atomic classified retry on failure (transient -> 1 retry + 2s backoff; permanent -> AskUserQuestion; cascading -> permanent + abort). Preview budget `(2+7N) × 500ms` -> N=10 ~36s, N=30 ~106s.
campaign-debrief
by Brite-NitesStructured 5-question post-campaign learning capture (Q1 hypothesis, Q2 result, Q3 what-worked, Q4 surprise, Q5 transferable) that assigns one of four objective campaign verdicts (SCALE / ITERATE / PAUSE / KILL per ADR-018) against concrete numeric thresholds and appends an entry to `docs/campaigns/{short_entity}/learnings.md`. Serves BDRs, RevOps, and marketing operators closing the loop between campaign execution and campaign intelligence. Triggers on debrief, campaign debrief, retro, log campaign, capture learnings. Receives primary input from `campaign-analysis` via `analysis-*.md`; retroactive path pulls metrics standalone from Email Bison when no analysis artifact exists. Hands off transferable learnings to `message-market-fit` (ITERATE Notes column), `product-marketing-context` (cross-entity propagation proposals), and `/workflows:handbook-drift-check` (handbook-contradiction signals). Append-only, forever. Under 5 minutes per debrief. Adapted from Revgrowth1/ai-gtm-workflows workflow 12 (MIT).
r4-nested
by Brite-NitesDemonstrates a nested reference chain. Use when testing the R4 lint rule.
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.