LIVE
Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|
SkillRisingofficial publisher

awesome-agent-skills (VoltAgent)

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires any-agent

Catalogue of more than one thousand multi-agent skills, organised by domain.

The broadest map of the territory; each skill still needs to be read before use.

Official site GitHub · 36,306 ★
Overall score
7.9 /10
Security: one caveat, see the card
Utility
8.0
Reliability
10.0
Security
One caveat
Ease
1 click · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Finding reliable instructions to extend an AI agent's capabilities takes time: auto-generated repositories are often low quality and poorly suited for real-world use. Awesome-agent-skills brings together more than 1,497 hand-picked skills published by real engineering teams or the community, with no bulk AI generation.

Each skill is an instruction file (SKILL.md) that the agent reads to acquire a specific behaviour: creating a Word document, querying a search API, crawling a web page, testing an application, or interacting with services such as Stripe, Supabase, Cloudflare, or Figma. The catalogue is organised by team or domain, with direct links to each skill.

This catalogue is aimed at developers using environments such as Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, Windsurf, or OpenCode, who want to extend their agents without starting from scratch. Official skills come from recognised teams: Anthropic, Google, Vercel, Stripe, Hugging Face, Microsoft, OpenAI, Figma, and many others.

This is not a plug-and-play tool: each skill must be read and understood before being handed to an agent, as some execute actions on real systems. Non-technical users or those looking for a ready-to-use solution without prior reading are not the intended audience.

What it offers

  • ·More than 1,497 hand-picked skills, organised by team or domain, covering document creation, web scraping, testing, search, and many other use cases.
  • ·Official skills published by recognised teams: Anthropic, Google, Vercel, Stripe, Microsoft, OpenAI, Figma, Hugging Face, Cloudflare, Supabase, and others.
  • ·Compatibility with many environments: Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, Windsurf, OpenCode, Antigravity.
  • ·Anthropic skills for handling Office files (Word, Excel, PowerPoint, PDF) and creating visual content.
  • ·Web crawling skills via Crawlbase: retrieval of raw HTML, clean Markdown, or screenshots from any URL.
  • ·Structured search skills via SerpApi, covering more than 130 engines including Google, Maps, Flights, Hotels, and Shopping.
  • ·Community section open to contributions, with documented quality standards for new skills.
  • ·Actively maintained repository with a public commit history allowing verification of content freshness.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
claude-code, codex, cursor
Host
any-agent
Licence
MIT
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Your data
Data stays local
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 November 2025

How to install awesome-agent-skills (VoltAgent)

1. Go to the GitHub repository: https://github.com/VoltAgent/awesome-agent-skills 2. Find the skill you are interested in using the contributor table or the collapsible sections of the README. 3. Click the skill link to access its page (officialskills.sh or direct GitHub repository) and read the SKILL.md file in full. 4. Check that the skill is compatible with your environment (Claude Code, Cursor, Codex, Gemini CLI, etc.) before activating it. 5. Follow the installation instructions specific to each skill: the path and activation method vary depending on the environment. 6. If you are unsure about the actions triggered by a skill, test it in an isolated environment before any production use.

In the same category

Whole category Frame (methods, guardrails) →