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...
odoo-competitive-brief
by ViindooProduce a competitive intelligence brief for a Strategist / CEO — board-ready capability matrix vs Odoo, GTM moves (user-provided only), threat assessment, and recommended response. Standalone-first — works WITHOUT OSM. Fire when user mentions a competitor alongside strategic intent: "competitor brief on", "analyze competitor X", "competitive landscape analysis", "competitive update for board", "threat assessment for", "competitive intelligence update". Also fires on Vietnamese: "phân tích đối thủ X", "brief cạnh tranh cho ban lãnh đạo", "đánh giá mối đe doạ cạnh tranh". DO NOT trigger for: (a) sales talking-point objections ("they say Odoo can't do X") → odoo-objection-handling; (b) feature comparison drill-down between Odoo versions → odoo-version-diff; (c) detailed add-on diff → odoo-addon-diff; (d) marketing copy or campaign messaging about competitive positioning → odoo-content-draft or odoo-campaign-plan; (e) simple feature availability check → odoo-feature-check
odoo-deal-followup
by ViindooAnalyze deal health for Odoo or a custom distribution and generate next actions for a Sales AE or small-team founder running go-to-market solo. Accepts deal context (label, last contact, stage, prior commitments) + an optional email/note thread; produces (a) a risk score (red/yellow/green), (b) a next-best action, (c) a draft follow-up email in English or the thread's language. Trigger on: "deal stalled", "customer hasn't replied", "draft follow-up email", time signals ("it's been 3 weeks", "deadline this month"), ambiguous-status signals ("not sure what the customer is thinking"). Also fires on Vietnamese: "deal đang đứng im", "khách chưa trả lời", "soạn email follow-up", "cần hâm nóng lại deal". DO NOT trigger for: (1) Discovery/demo session summary -> use odoo-discovery-summary. (2) Responding to technical objections -> use odoo-objection-handling. (3) Verifying or proving Odoo features -> use odoo-capability-proof or odoo-feature-check. (4) Gap analysis or scope estimation -> use odoo-gap-analysis
odoo-demo-recording
by ViindooRecord a screen-capture video (MP4/GIF) of one Odoo workflow for a demo, sales walkthrough, or marketing clip — driving the live instance through a scripted click path and saving the result. Capture runs via pagecast/Playwright-video MCP (chrome-devtools drives the path; screenshot→GIF fallback when the recorder is unreachable). Use when the deliverable is a video of a live flow, not a static review or bug hunt. Pushy trigger: fire on "record a demo of this Odoo workflow", "capture a GIF of creating an invoice in Odoo", "capture a short MP4 for the website", "quay video demo Odoo", "tạo video hướng dẫn quy trình". Routing: stitch many scenes / multi-scene walkthrough into one video → odoo-produce-video; RATE how a screen looks → odoo-ui-review; broken screen → odoo-debug; compare two builds → odoo-visual-regression; write frontend code → odoo-coding; code audit → odoo-code-review
run-driver
by ViindooDepth-0 drive-to-done loop. Walks the RUN-DAG in `.odoo-ai/run-<id>.json` that intake's Phase P produced: picks the next ready node, resolves its gate tier (L0/L1/L2), dispatches it (Skill-tool a leaf skill | Skill-tool a spawner skill (it fans out its own agent) | hand a workflow to workflow-chaining), reads the step's Continuation Contract, updates the blackboard, and advances until the run reaches DONE / BLOCKED / NEEDS_CONTEXT. Invoked by intake after a RUN-DAG is approved, or to RESUME an existing active run. Never called directly by the user; never invoked from inside a subagent. Full schema + diagram: docs/reference/workflow-harness.md §8
workflow-chaining
by ViindooGeneric declarative workflow runner — reads one `workflows/<name>.workflow.yaml` file and executes its gated phase sequence according to the declared `team_pattern` (Pipeline, Fan-out/Fan-in, Expert-Pool, Producer-Reviewer, Supervisor, or Hierarchical). Dispatches each phase to a specialist skill via NL description-match, never via the Skill tool. Writes phase artifacts to the `output_dir` declared in the YAML and checkpoints state for resume. Invoked by the intake skill (or concierge) via NL-dispatch after a workflow is chosen at the soft-plan-gate — never called directly by the user
run-driver
by ViindooDepth-0 drive-to-done loop. Walks the RUN-DAG in `.odoo-ai/run-<id>.json` that intake's Phase P produced: picks the next ready node, resolves its gate tier (L0/L1/L2), dispatches it (Skill-tool a leaf skill | Skill-tool a spawner skill (it fans out its own agent) | hand a workflow to workflow-chaining), reads the step's Continuation Contract, updates the blackboard, and advances until the run reaches DONE / BLOCKED / NEEDS_CONTEXT. Invoked by intake after a RUN-DAG is approved, or to RESUME an existing active run. Never called directly by the user; never invoked from inside a subagent. Full schema + diagram: docs/reference/workflow-harness.md §8
odoo-deal-followup
by ViindooAnalyze deal health for Odoo or a custom distribution and generate next actions for a Sales AE or small-team founder running go-to-market solo. Accepts deal context (label, last contact, stage, prior commitments) + an optional email/note thread; produces (a) a risk score (red/yellow/green), (b) a next-best action, (c) a draft follow-up email in English or the thread's language. Trigger on: "deal stalled", "customer hasn't replied", "draft follow-up email", time signals ("it's been 3 weeks", "deadline this month"), ambiguous-status signals ("not sure what the customer is thinking"). Also fires on Vietnamese: "deal đang đứng im", "khách chưa trả lời", "soạn email follow-up", "cần hâm nóng lại deal". DO NOT trigger for: (1) Discovery/demo session summary -> use odoo-discovery-summary. (2) Responding to technical objections -> use odoo-objection-handling. (3) Verifying or proving Odoo features -> use odoo-capability-proof or odoo-feature-check. (4) Gap analysis or scope estimation -> use odoo-gap-analysis
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.