# VoltAgent/awesome-agent-skills

Source: [GitHub](https://github.com/VoltAgent/awesome-agent-skills)  
Feed7 permalink: https://feed7.dev/p/awesome-agent-skills-0vfknie  
Published: Unknown  
Trust: Needs Review (needs_review)

## Why Included

This directory collects reusable agent instructions from vendor teams and the community across major coding assistants. Treat it as a discovery index, then inspect each skill before adding it to a workflow.

## Source Summary

The repository indexes **1,000+ agent skills** from teams including Anthropic, Google, Vercel, Stripe, Cloudflare, Sentry, and others. It targets **Claude Code, Codex, Gemini CLI, Cursor** and additional assistants, covering documents, testing, infrastructure, APIs, databases, and frontend work.

## Practical Implication

Use it to find domain-specific instructions before writing a skill from scratch. Prefer vendor-authored entries for version-sensitive integrations, copy only the skills relevant to the current repository, and review their commands and assumptions before granting tool access.

## Agent-Ready Context

The repository indexes **1,000+ agent skills** from teams including Anthropic, Google, Vercel, Stripe, Cloudflare, Sentry, and others. It targets **Claude Code, Codex, Gemini CLI, Cursor** and additional assistants, covering documents, testing, infrastructure, APIs, databases, and frontend work.

Use it to find domain-specific instructions before writing a skill from scratch. Prefer vendor-authored entries for version-sensitive integrations, copy only the skills relevant to the current repository, and review their commands and assumptions before granting tool access.

The material describes the collection as hand-picked, but provides no common test results, security review, compatibility guarantee, or freshness policy for individual entries. Inclusion is therefore a discovery signal, not evidence that a skill is safe or effective in your harness.

## Connected Context

Feed7 judgment across 551 accumulated Signals:

This expands skill discovery across assistants and domains, but its scale sharpens the distinction between finding a workflow and trusting it. Against the prior candidates, it favors selective adoption, vendor-authored material for changing integrations, and repository-level review over wholesale installation; catalog inclusion cannot substitute for evaluation, security controls, or maintained team practices.

- [anthropics/claude-plugins-community](https://feed7.dev/p/claude-plugins-community-0vhi4d8) — Anthropic’s catalog provides a contrasting distribution model with automated scanning and approval, whereas this index offers broader cross-assistant discovery without common review guarantees.
- [addyosmani/agent-skills](https://feed7.dev/p/agent-skills-0d3lx1j) — The smaller lifecycle-focused pack contrasts with this broad index by providing a coherent set of evidence gates; discovery here still requires teams to assemble and govern their own workflow.
- [Agents, codebases, and teams — Aditya Khandelwal, Amazon AGI Lab](https://feed7.dev/p/agents-codebases-and-teams-aditya-khandelwal-amazon-agi-lab-1946kjc) — A large catalog becomes operationally useful only when selected skills are incorporated into maintained repository guidance, CI, review, and shared team practice as this candidate describes.
- [mukul975/Anthropic-Cybersecurity-Skills](https://feed7.dev/p/anthropic-cybersecurity-skills-1k6d1bw) — The security-specific catalog reinforces the consequence of scale: sensitive skills require selective routing, authorization, and supply-chain review rather than bulk installation.

## Context Map

- Layer: agent
- Domains: coding
- Topics: skills, tool-use, coding-agents

## Uncertainty

- The material describes the collection as hand-picked, but provides no common test results, security review, compatibility guarantee, or freshness policy for individual entries. Inclusion is therefore a discovery signal, not evidence that a skill is safe or effective in your harness.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.