Best Open Source AI Agent Skills

Discover the best open-source AI agent skills. Free, community-maintained SKILL.md files for every AI assistant and task.

Last updated: 2026-10-11

📋 Selection Criteria

We evaluate and rank skills using the following criteria to ensure you get the most reliable, useful, and safe agent capabilities.

🎯

Usefulness for Real Tasks

Skills that solve practical, everyday problems in the all domain.

🔧

Tool Compatibility

Skills compatible with multiple AI assistants including Claude, ChatGPT, and Cursor.

📖

Source Transparency

Open-source skills with clear GitHub repositories, documentation, and active maintenance.

⭐

Community Trust

Skills with strong GitHub stars, community adoption, and positive signal from the developer community.

📋

Clarity of Instructions

Well-structured SKILL.md files with clear prompts, examples, and usage guidelines.

🔒

Install Readiness & Safety

Skills that are easy to install and have been reviewed for security risk level.

📊 Quick Comparison

FeatureAIHowToSkills
Skill Count30
Search✅ Full-text search on AIHowToSkills
Install Support✅ macOS/Linux + Windows commands
Source Transparency✅ GitHub repos with stars & author info
Data Access✅ /skills.json API + /llms.txt
Best ForAI skill researchers
Pricing✅ Free & Open Source

🏆 Top 30 Best Open Source AI Skills

#1
.NET Self-Learning Architect
ClaudeGitHub Copilot learning

Senior .NET architect for complex delivery: designs .NET 6+ systems, decides between parallel subagents and orchestrated team execution, documents lessons learned, and captures durable project memory

⭐ 34.1k stars 🔒 Low risk github/awesome-copilot
#2

Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para proyectos de IA en español.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#3
007
Claude code

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#4

Ingeniero de Sistemas de Andru.ia. Diseña, redacta y despliega nuevas habilidades (skills) dentro del repositorio siguiendo el Estándar de Diamante.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#5

Estratega de Inteligencia de Dominio de Andru.ia. Analiza el nicho específico de un proyecto para inyectar conocimientos, regulaciones y estándares únicos del sector. Actívalo tras definir el nicho.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#6
2d-games
Claude game-development

2D game development principles. Sprites, tilemaps, physics, camera.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#7

AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style, summarize documents into decks, add AI voice narration, and export pages/audio. Use for

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#8
360-feedback-system
Claude productivity

360 feedback register: reviewer, subject, review cycle, visibility, due date and score, as CSV, SQL, JSON Schema or Notion on request. Use for 360 reviews or peer feedback cycles.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#9
3d-games
Claude game-development

3D game development principles. Rendering, shaders, physics, cameras.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#10
3d-ui
Claude code

Web and App implementation guide for 3D UI. Trigger when user wants actual 3D objects, perspective effects, and spatial depth.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#11
3d-web-experience
Claude design

Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing dep

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#12
A11Y
ClaudeGitHub Copilot code

Comprehensive web accessibility standards based on WCAG 2.2 AA, with 38+ anti-patterns, legal enforcement context (EAA, ADA Title II), WAI-ARIA patterns, and framework-specific fixes for modern web fr

⭐ 34.1k stars 🔒 Low risk github/awesome-copilot
#13
aas-compose-stack
Claude code

Preserve the coding agent's explicit AAS skill selection as a validated stack and optional evidence.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#14
aas-discover
Claude code

Discover AAS skills for an explicit task and compare their complete instructions without installing them.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#15
aas-review-stack
Claude code

Review AAS stack manifests, preview plans and selection evidence in Workbench without applying changes.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#16
Ab Test Setup
Claude data

Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#17
ab-testing
Claude testing

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test th

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#18
acceptance-orchestrator
Claude productivity

Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#19
access-matrix
Claude productivity

Access matrix of role-by-module permissions, with per-role scope, confidentiality level and SME tier, as CSV, SQL, JSON Schema or Notion on request. Use for access reviews.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#20
access-review
Claude code

Conduct periodic access reviews and certifications. Implement access governance and recertification workflows. Use when managing access compliance.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#21

You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#22
Accessibility Expert
ClaudeGitHub Copilot code

Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing

⭐ 34.1k stars 🔒 Low risk github/awesome-copilot
#23
Accessibility Runtime Tester
ClaudeGitHub Copilot code

Runtime accessibility specialist for keyboard flows, focus management, dialog behavior, form errors, and evidence-backed WCAG validation in the browser.

⭐ 34.1k stars 🔒 Low risk github/awesome-copilot
#24
accesslint-audit
Claude code

Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-C

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#25
accesslint-diff
Claude code

Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#26
accesslint-scan
Claude code

Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#27
accint-commitments
Claude code

Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#28
accint-frames
Claude code

Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#29
accint-solve
Claude code

Route agent work through AccInt's MCP memory loop: retrieve prior outcomes, resolve frames, and close commitments with evidence.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills
#30

Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.

⭐ 47.5k stars 🔒 Low risk sickn33/antigravity-awesome-skills

💡 How to Choose the Right Skill

🎯 Match Your Task

Consider what specific problem you're solving — code review, writing, data analysis, or workflow automation. Different skills excel at different tasks.

🔧 Check Tool Compatibility

Verify the skill works with your preferred AI assistant. Some skills are optimized for Claude, others for ChatGPT, Cursor, or Gemini.

📖 Review Source Quality

Check GitHub stars, author reputation, and last update date. Well-maintained skills with active repos are more reliable.

🔒 Assess Risk Level

Skills marked "Low" risk are safe plain-text prompts. "Medium" skills may run shell commands — review before installing. "High" skills need special caution.

❓ Frequently Asked Questions

What makes a great Best Open Source AI Skills?

The best best open source ai skills combine clear instructions, broad tool compatibility, active maintenance, and strong community trust. We evaluate each skill across usefulness, safety, and source transparency.

How do I install best open source ai skills?

Each skill page includes an install command for macOS/Linux and Windows. Copy the command, run it in your terminal, and the SKILL.md file downloads to your local skills directory.

Are these skills free to use?

Yes — every skill listed on AIHowToSkills is completely free and open-source. Most are from GitHub repositories under permissive licenses.

Do these skills work with AI assistants?

Yes — the skills listed here are compatible with major AI assistants including Claude, ChatGPT, Cursor, and Gemini. Each skill page shows exactly which tools it supports.

How are these skills ranked?

Skills are ranked by a combination of: usefulness for real tasks, tool compatibility, source transparency, GitHub stars, instruction clarity, and install readiness. See the selection criteria above for details.