381,784 Collected SKILL.md files

Explore AI Agent Skills & Claude Prompts

Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.

search
expand_more
Active:
UBR-JMA
Showing 12 of 27 skills
UBR-JMA

caregiver-support

by UBR-JMA
star 0

Support for community stewards and members who are doing sustained caregiving work — for people with mental illness, addiction, physical disability, complex child needs, or aging. Covers: compassion fatigue vs. burnout vs. secondary traumatic stress, warning signs, role boundary collapse, sustainable caregiving practices, when and how to ask for relief, and the community's responsibility to care for its caregivers. Activate when a community member is doing significant caregiving and showing signs of depletion, when role boundaries have collapsed, when someone is afraid to ask for help, when a caregiver is in crisis themselves, or when the community needs to think structurally about how it shares caregiving load. Works within Louisoix as a subordinate function or can be invoked directly. Often works in tandem with trauma-informed-care, mental-health-first-response, and caregiver-support. The steward using this skill may themselves be the caregiver who needs support — this skill is explicitly for that too.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

economic-precarity

by UBR-JMA
star 0

Guide community members through economic precarity, labor justice, and mutual aid. Subordinate to Louisoix integrator. Use when community members face income instability, job loss, housing insecurity, benefits navigation, debt, economic shame, or class dynamics. Invoke directly or through Louisoix. Address systemic roots of inequality—never neutral about poverty and precarity.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

somatic-approaches

by UBR-JMA
star 0

Support community stewards and leaders in recognizing how the body holds trauma, stress, and emotion — and how to create conditions for nervous system healing without becoming therapists. Learn to read somatic signals others miss, understand why a calm presence is contagious, recognize when someone needs clinical support, and design communities where bodies feel safe. Part of the Louisoix integrating skill for community care advisors.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

trauma-informed-child-care

by UBR-JMA
star 0

Trauma-informed care for young children in community settings — specifically for non-parent caregivers working with children who may carry generational trauma, neurodivergence, or complex needs. Covers: what dysregulation looks like in young children vs. defiance, co-regulation as the primary intervention, how to build consistent caregiver responses across a non-parent caregiving network, generational trauma patterns in children, and when to involve parents or outside professionals. Activate when a community includes young children with complex caregiving needs, when non-parent caregivers are struggling to respond consistently to a child's behavior, when a child's distress is being interpreted as defiance or manipulation, or when caregivers need a shared framework so their responses don't contradict each other. Works within Louisoix as a subordinate function or can be invoked directly. Often works in tandem with neurodivergence-care, trauma-informed-care, and caregiver-support.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

louisoix

by UBR-JMA
star 0

Master integrating advisor for communities of care — draws on 27 specialist frameworks (restorative justice, trauma-informed care, organizational stewardship, neurodivergence, addiction recovery, mental health first response, grief and transition, youth development, economic precarity, LGBTQ+ affirmation, elder care, cultural competency, legal literacy, safety planning, somatic approaches, sex-positivity, trauma-informed child care, caregiver support, conflict prevention, chronic illness and disability, spiritual worldview diversity, parenting in community, community material analysis, dying and death accompaniment, political and movement dynamics, community dissolution, land and ecological stewardship) to provide holistic, synthesized guidance. Use for any community stewardship challenge: conflict and repair, governance and consensus, member crises, onboarding, community culture, procurement, budget, and shared resource decisions. When facing a situation that touches multiple dimensions at once — as commu

navigation main article SKILL.md
schedule Updated 2 months ago
UBR-JMA

community-dissolution

by UBR-JMA
star 0

Use when the community itself may not survive — founding schism, major exodus, or an existential question of whether to continue. Distinct from individual member departure (grief-transition) and governance failure that can be repaired (organizational-stewardship). Covers both dissolution and transformation into something new. Activate when stewards face: a founding conflict that cannot be bridged, multiple members leaving in a compressed period, explicit or implicit questions about whether to keep going, or the aftermath of rupture so significant that the community's future is genuinely in doubt. This skill treats dissolution as something that can be done well or badly, and provides the tools to do it well — including the decision of whether to continue, how to dissolve with integrity, how to rebuild after rupture, and the specific grief of mourning a community.

navigation main article SKILL.md
schedule Updated 2 months ago
UBR-JMA

cultural-competency

by UBR-JMA
star 0

Navigate power, privilege, and cultural difference in communities of care. This skill applies genuine anti-oppression analysis—not surface diversity talking points—to the real work of building equitable, inclusive communities. Grounded in structural analysis of how racism, classism, and other systems operate even in spaces explicitly committed to equity. Use this directly or as part of Louisoix integrator for community stewards.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

lgbtq-affirmation

by UBR-JMA
star 0

Deep, structural LGBTQ+ affirmation for communities of care. This skill moves beyond performative inclusion to genuine cultural and structural support — what it means to truly affirm LGBTQ+ members, how to respond to disclosure, what to do when identity shifts mid-life, how to navigate family rejection, how to support queer families and children, and how to hold disagreement without denying humanity. Works within Louisoix as a subordinate function or can be invoked directly. For stewards of consensus-based communities.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

parenting-in-community

by UBR-JMA
star 0

Navigating the specific complexities of raising children within a community of care — centered on parents and non-parent caregivers, not on the children themselves. Covers: authority and discipline boundaries for non-parents, building co-parenting agreements, navigating different parenting philosophies in community, when non-parents have concerns about a child or about parenting, when parents feel surveilled or judged, and how community membership shapes shared responsibility for children without undermining parental authority. Activate when parenting decisions are creating community friction, when there is ambiguity about who has authority over a child in community settings, when different parenting philosophies are in conflict, when a non-parent has concerns they don't know how to raise, or when a parent feels their parenting is being second-guessed by community members. Works within Louisoix as a subordinate function or can be invoked directly. Distinct from youth-development (which centers the child's e

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

restorative-justice

by UBR-JMA
star 0

Restorative justice advisory for community stewards navigating harm, accountability, and repair. Covers: circle practices, distinguishing harm from conflict, the harmed person's role as the measure of success, accountability vs. punishment, community witnessing, agreement-making, and when NOT to use restorative process. Activate when harm has occurred and repair — not punishment — is the goal. Distinct from general conflict resolution: use when there is a clear harmed party, when accountability and genuine repair are needed, when the community needs to witness and hold the process. The harmed person's sense of safety and repair is the measure of success — not the harm-doer's remorse or the community's comfort with resolution.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

safety-planning

by UBR-JMA
star 0

Safety planning for communities of care. When someone in your community faces genuine physical risk—from intimate partner violence, stalking, threats, or a member who poses danger—this skill guides you through assessment and response with clear-eyed honesty about what community can and cannot safely handle. Works within Louisoix or standalone. Say "Let's use the safety planning skill" when you need to navigate a safety situation with someone you care about.

navigation main article SKILL.md
schedule Updated 3 months ago
UBR-JMA

youth-development

by UBR-JMA
star 0

Develop intentional communities where children are full members. Navigate developmental stages, create meaningful coming-of-age rituals, include adolescent voices in governance, balance safety with freedom, and support young people's transition to adult community membership. Part of the Louisoix community care suite — invoke directly or use within Louisoix integration.

navigation main article SKILL.md
schedule Updated 3 months ago
Page 1 of 3

Browse Agent Skills by Occupation

23 major groups · 867 SOC occupations

Browse by Category

Explore agent skills organized by their primary use case

SKILLMD / CREATORS AND OCCUPATION CATEGORIES

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.

SEO KNOWLEDGE HUB & TECHNICAL OVERVIEW

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.

8 QUESTIONS

Frequently Asked Questions

A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.