# Agent Skills

> Source: https://aiwiki.ai/wiki/agent_skills
> Updated: 2026-10-30
> Fact-checked: 2026-10-30
> Categories: AI Agents, Anthropic, Developer Tools
> License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) - attribute to "AI Wiki (aiwiki.ai)"
> Cite as: AI Wiki. "Agent Skills." aiwiki.ai, 30 Oct 2026. https://aiwiki.ai/wiki/agent_skills
> From AI Wiki (https://aiwiki.ai), the free encyclopedia of artificial intelligence. Reuse freely with attribution.

**Agent Skills** are a lightweight, open format for extending [AI agents](https://aiwiki.ai/wiki/ai_agents) with specialized knowledge and workflows. A skill is a folder containing a single `SKILL.md` file plus optional scripts, reference documents, and assets. The `SKILL.md` file holds a short block of metadata and a set of plain-language instructions that tell an agent how to perform a particular task, from filling PDF forms to following a company's brand guidelines. The format was created by [Anthropic](https://aiwiki.ai/wiki/anthropic), first shipped inside [Claude](https://aiwiki.ai/wiki/claude) products in October 2025, and then released as a cross-vendor open standard in December 2025 [1][3][11]. On October 22, 2026, Anthropic donated the standard to the [Agentic AI Foundation](https://aiwiki.ai/wiki/agentic_ai_foundation) (AAIF) under the [Linux Foundation](https://aiwiki.ai/wiki/linux_foundation), saying that more than 70 agent platforms had integrated it by then, including [ChatGPT](https://aiwiki.ai/wiki/chatgpt), [Cursor](https://aiwiki.ai/wiki/cursor), [GitHub Copilot](https://aiwiki.ai/wiki/github_copilot), and [Visual Studio Code](https://aiwiki.ai/wiki/visual_studio_code) [6][9].

<figure class="w-56">
<img src="/images/site-2026-10-28-agent_skills-logo-973b008ae91c-tile.png" alt="Agent Skills logo" width="480" height="141" />
<figcaption>Agent Skills logo, from the official website <a href="https://agentskills.io/">agentskills.io</a>. Trademark of its owner.</figcaption>
</figure>

The basic idea is to keep procedural knowledge outside the model's weights. Instead of retraining a model every time it needs to learn a new workflow, a skill packages that workflow as a version-controlled folder the agent reads on demand [3][4]. This makes capabilities portable: a skill authored once can run on any compatible agent, and a team can keep its conventions in a shared repository or internal marketplace that colleagues use from whichever compatible agent they prefer [3][10].

## The SKILL.md format

Every skill lives in its own directory, and the only mandatory file is `SKILL.md`. The file begins with YAML frontmatter followed by Markdown instructions. The specification published at agentskills.io defines a small set of fields [3]:

| Field | Required | Constraints |
| --- | --- | --- |
| `name` | Yes | 1-64 characters; lowercase letters (`a-z`), numbers (`0-9`), and hyphens only; no leading, trailing, or consecutive hyphens; must match the parent directory name |
| `description` | Yes | 1-1024 characters; describes what the skill does and when to use it |
| `license` | No | License name or a reference to a bundled license file |
| `compatibility` | No | 1-500 characters if present; notes environment needs such as the intended product, required packages, or network access |
| `metadata` | No | Map from string keys to string values, for properties the spec does not define |
| `allowed-tools` | No | Space-separated string of pre-approved tools; marked experimental, and support varies between agents |

A minimal skill needs only the two required fields. The Markdown body below the frontmatter has no format restrictions; the spec recommends step-by-step instructions, examples of inputs and outputs, and common edge cases. It also recommends keeping the main `SKILL.md` under 500 lines, moving detailed reference material into separate files, and keeping file references one level deep from `SKILL.md` [3].

The field set has not changed since the specification was first published on December 18, 2025. Later edits clarified wording: in 2026 the spec made explicit that `name` may contain digits, described `allowed-tools` as a space-separated string, stated that the optional directories are not an exhaustive list, and repeated in its field table that `metadata` is a map of string keys to string values [22]. As of late October 2026 the specification had no numbered versions or tagged releases [22]. Individual clients can go beyond the shared fields. Anthropic's documentation says [Claude Code](https://aiwiki.ai/wiki/claude_code) "extends the standard" with features such as invocation control, running a skill in a subagent, and dynamic context injection [24], and Anthropic's own products add rules of their own, for example barring the reserved words `anthropic` and `claude` from skill names [23].

Alongside `SKILL.md`, a skill can bundle three conventional folders: `scripts/` for executable code the agent can run, `references/` for documentation it can read when needed, and `assets/` for templates, images, or data files. Any other files or directories are also allowed. Files are referenced by relative path from the skill root. A typical layout looks like this [3]:

```
pdf-processing/
  SKILL.md          # required: metadata + instructions
  scripts/          # optional: executable code
  references/       # optional: documentation
  assets/           # optional: templates, resources
  ...               # optional: any additional files or directories
```

The specification's maintainers also publish `skills-ref`, a reference library whose `skills-ref validate` command checks that a skill's frontmatter is valid and follows the naming rules [3].

<figure class="embedvideo">
<iframe src="https://www.youtube-nocookie.com/embed/fOxC44g8vig" title="Claude Agent Skills Explained"></iframe>
<figcaption>"Claude Agent Skills Explained", official video from Anthropic, published November 26, 2025. <a href="https://www.youtube.com/watch?v=fOxC44g8vig">Watch on YouTube</a>.</figcaption>
</figure>

## How skills load: progressive disclosure

The mechanism that makes skills practical is progressive disclosure, which loads detail in three stages so that an agent can keep many skills available without flooding its [context window](https://aiwiki.ai/wiki/context_window) [1][3]:

1. **Discovery.** At startup the agent loads only the `name` and `description` of every available skill, roughly 100 tokens per skill according to the spec. In Anthropic's implementation this metadata is pre-loaded into the [system prompt](https://aiwiki.ai/wiki/system_prompt). It is just enough for the model to know when a skill might be relevant.
2. **Activation.** When a task matches a skill's description, the agent reads the full `SKILL.md` body into context. The spec recommends keeping this under 5,000 tokens.
3. **Execution.** The agent follows the instructions, loading bundled files or running scripts only if and when the task calls for them.

Because the heavy material stays on disk until a specific task pulls it in, an agent can keep many skills on hand with only a small context footprint [3]. Anthropic's engineering team adds that agents with a filesystem and code execution tools do not need to read a whole skill into context, so "the amount of context that can be bundled into a skill is effectively unbounded" [1]. In Anthropic's documentation, when Claude runs a bundled script, only the script's output enters the context window, not its code [23].

## Relationship to the Model Context Protocol

Agent Skills are frequently compared to the [Model Context Protocol](https://aiwiki.ai/wiki/model_context_protocol) (MCP), another open standard that Anthropic introduced in 2024. The two are complementary rather than competing. MCP is a protocol that connects an agent to external tools, data sources, and services, while skills are a packaging format for procedural knowledge about how to carry out a task. When it launched skills, Anthropic said it would "explore how Skills can complement Model Context Protocol (MCP) servers by teaching agents more complex workflows that involve external tools and software" [1]. A skill can describe a multi-step process that calls several MCP tools in sequence, while MCP handles the actual connections. A 2026 survey of the field treats the "complementary roles of skills and MCP" as part of the architectural foundations of skill-equipped agents [4]. The two standards now share a governing body: Anthropic donated MCP to the AAIF in December 2025 and Agent Skills in October 2026 [6][9].

## Where skills work

Anthropic shipped Agent Skills across its own products first. At launch on October 16, 2025, skills ran in the Claude apps (for Pro, Max, Team, and Enterprise users), in Claude Code, in the [Claude Agent SDK](https://aiwiki.ai/wiki/claude_agent_sdk), and on the Claude Developer Platform [1][11]. On December 18, 2025, Anthropic let Team and Enterprise administrators provision skills centrally for their organizations and opened a directory of partner-built skills from Notion, Canva, Figma, Atlassian, and others [7][8]; [Zapier](https://aiwiki.ai/wiki/zapier), Cloudflare, Sentry, and Vercel also contributed launch statements [8]. Developers on the API use skills through the `/v1/skills` endpoint, where they run in a sandboxed container without network access or runtime package installation [8][23]. Anthropic's product-specific features are covered in [Claude Skills](https://aiwiki.ai/wiki/claude_skills).

Anthropic also maintains a public repository, `anthropics/skills`, which it describes as "Anthropic's implementation of skills for Claude." It contains a skill template and example skills spanning document creation (docx, pdf, pptx, xlsx), development tasks, and design work. The repository originally held the specification too, but that file now points to agentskills.io. Many of its skills are open source under Apache 2.0, while the document-creation skills are shared as source-available reference implementations rather than open source [2].

## Open standard and ecosystem

On December 18, 2025, Anthropic republished the format as an open standard for cross-platform portability, under its own GitHub organization (`agentskills`) and domain (agentskills.io) [1][6][8]. Anthropic said that within weeks of the October launch, developers had published thousands of skills on GitHub and written loaders for Codex, Cursor, and [OpenCode](https://aiwiki.ai/wiki/opencode) [6].

OpenAI's support predated the open standard. On December 12, 2025, Simon Willison reported that ChatGPT's Code Interpreter had gained a `/home/oai/skills` folder of document skills and that OpenAI's [Codex CLI](https://aiwiki.ai/wiki/codex_cli) had merged experimental support for skills about two weeks earlier [14]. Other vendors followed with official support over the next several weeks:

| Product | Developer | Support announced | Details |
| --- | --- | --- | --- |
| GitHub Copilot | GitHub | December 18, 2025 | Copilot coding agent, Copilot CLI, and agent mode in VS Code Insiders; picks up skills already set up in `.claude/skills` [12] |
| [OpenAI Codex](https://aiwiki.ai/wiki/openai_codex) | OpenAI | December 19, 2025 | CLI and IDE extensions; skills installed per user in `~/.codex/skills` or per repository in `.codex/skills` [15] |
| Visual Studio Code (stable) | Microsoft | January 8, 2026 | Version 1.108, experimental; reads skills from `.github/skills` or `.claude/skills` [13] |
| [Gemini CLI](https://aiwiki.ai/wiki/gemini_cli) | Google | January 7, 2026 | Experimental support in preview builds (v0.23.0); enabled by default in releases later that month [17] |
| Cursor | Cursor | January 22, 2026 | Cursor 2.4, in the editor and CLI [16] |

As of October 30, 2026, the client showcase on agentskills.io listed 46 products. They include JetBrains' Junie, [Kiro](https://aiwiki.ai/wiki/kiro), Goose, Amp, Factory, Roo Code, OpenHands, Letta, Databricks Genie Code, Snowflake Cortex Code, TRAE, Mistral AI Vibe, Tabnine, Spring AI, Laravel Boost, Pulumi Neo, Nous Research's Hermes Agent, and [OpenClaw](https://aiwiki.ai/wiki/openclaw) [3]. Anthropic's own count, given at the October 2026 donation, was more than 70 agent platforms [6]. Because a skill is a folder of files, tools can share them directly: GitHub Copilot and VS Code read the `.claude/skills` directory that Claude Code uses [12][13].

Registries grew alongside the clients. On January 20, 2026, [Vercel](https://aiwiki.ai/wiki/vercel) released `skills`, a command-line installer (`npx skills add <package>`), together with skills.sh, a directory and leaderboard for skill packages. By launch day it had been used to install skills on agents including Amp, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Goose, Kiro, and OpenCode [18]. By October 2026, Anthropic said 1 million skills had been published and nearly 280 million installed [6]; the AAIF put it as a million skills listed on skills.sh in seven months, installed nearly 280 million times [10].

A February 2026 data-driven study by George Ling, Shanshan Zhong, and Richard Huang analyzed 40,285 publicly listed skills from a major marketplace. It found that skill content is heavily concentrated in software-engineering workflows, with widespread overlap between skills aimed at the same intent and a pronounced supply-demand imbalance across categories [5].

## Donation to the Agentic AI Foundation

On October 22, 2026, Anthropic announced that it was donating Agent Skills to the Agentic AI Foundation, the Linux Foundation directed fund it had co-founded with Block and OpenAI in December 2025 and to which it had already given MCP [6][9]. The Linux Foundation announced Agent Skills the same day as one of four new AAIF projects, alongside Open Responses (contributed by OpenAI), OpenEnv (Hugging Face), and OpenSandbox (Alibaba), at the AGNTCon + MCPCon North America conference in San Jose. The additions brought the foundation to 10 hosted projects, up from three at launch [9].

**What was donated.** Anthropic said it was handing over "the Agent Skills name and logo, the GitHub organization, and the agentskills.io domain" [6]. The GitHub organization holds the specification, its documentation site, and the `skills-ref` reference library [22]. The AAIF describes the specification as open source under Apache 2.0 and CC BY 4.0, matching the repository's split between code (Apache 2.0) and documentation (CC BY 4.0) [10][22]. Anthropic's separate `anthropics/skills` repository of example skills is its own implementation and was not among the listed assets [2][6]. Anthropic said developers can keep using the standard or contribute to it without joining the AAIF [6].

**Governance.** According to Anthropic, "Engineers from Anthropic, Google, OpenAI, and other companies will maintain the standard as individuals, with David Soria Parra and Mahesh Murag as Lead Maintainers" [6]. The AAIF said the project would be guided by "a multi-company Technical Steering Committee" with core maintainers drawn from multiple organizations who serve as individuals [10]. Anthropic proposed an initial roadmap covering "versioned releases, a formal proposal process, and security guidance for people who write and install skills," with feedback on proposed specification changes gathered through the project's Discord [6]. These are proposals: as of October 30, 2026, no versioned release had been published [22].

**Statements.** David Soria Parra, Anthropic's co-creator and lead maintainer of MCP, said in the Linux Foundation release: "Without the right context, even the most intelligent agents fall short. We launched Agent Skills a year ago to give developers and enterprises alike an open standard to make their agents more capable. Today, we're donating Agent Skills to the AAIF to ensure that anyone building with skills can shape what's next" [9]. Manik Surtani, the AAIF's CTO and co-founder, said: "A year ago, AAIF launched with three projects and a bet that agentic AI needed a neutral home to thrive. Today we host 10" [9]. Angie Jones, vice president of the AAIF, wrote on the foundation's blog: "That's why a neutral home is the right next step for Agent Skills" [10]. Her post pointed to companies already sharing skills internally: at Block, engineers use an internal marketplace of hundreds of skills with agents including Goose, Codex, Claude, and Amp [10].

## Security and governance

Letting an agent read instructions and execute scripts from a downloaded folder carries obvious risks. Anthropic's guidance is to install skills only from trusted sources and to thoroughly audit anything from a less-trusted source, paying particular attention to code dependencies, bundled resources such as scripts, and any instruction or code that tells the agent to connect to potentially untrusted external network sources [1]. Its documentation warns that, depending on what access Claude has, "malicious Skills could lead to data exfiltration, unauthorized system access, or other security risks" [23]. The `allowed-tools` field is one early attempt to constrain what a skill may do, though the spec marks it experimental [3].

Empirical work has started to quantify the problem. In January 2026, Yi Liu and colleagues analyzed 31,132 skills collected from two marketplaces and reported that 26.1% contained at least one vulnerability, across prompt injection, data exfiltration, privilege escalation, and supply-chain risks. Skills that bundled executable scripts were 2.12 times more likely to be vulnerable than instruction-only skills [19]. A February 2026 survey by Renjun Xu and Yang Yan cited that figure and proposed a Skill Trust and Lifecycle Governance Framework, a four-tier, gate-based permission model that ties a skill's provenance to what it is allowed to do [4]. The data-driven analysis by Ling and colleagues also flagged non-trivial safety risks among skills that can take state-changing or system-level actions [5].

Malicious skills have also appeared in public registries. In early February 2026, Koi Security reported that it had audited all 2,857 skills on ClawHub, the third-party skill registry for OpenClaw, and found 341 malicious ones. It traced 335 of them to a single campaign, dubbed ClawHavoc, that used fake "prerequisite" installs to deliver the Atomic macOS Stealer (AMOS) infostealer [21]. On February 5, 2026, Snyk reported a scan of 3,984 skills from ClawHub and skills.sh: 36.82% (1,467 skills) had at least one security flaw, and human review confirmed 76 malicious payloads [20]. As of October 2026, Anthropic's documentation describes an optional skill content-scanning feature for Claude Enterprise organizations covering custom skills uploaded in claude.ai and Claude Cowork [23]. Security guidance for skill authors and users is one of the three items on the roadmap Anthropic proposed when it donated the standard to the AAIF [6].

## Significance

Agent Skills matter because they decouple capability from model training. New behaviors can be added, audited, versioned, and shared as ordinary files, which suits enterprise workflows where teams want consistent, reviewable procedures rather than opaque model updates. The standard also follows the path Anthropic took with MCP: introduced inside its own products, opened to other vendors, and then placed under the Agentic AI Foundation's vendor-neutral governance [6][9]. Neutral governance answers the question of who controls the format. It does not settle the open questions that the AAIF roadmap and the security research point to, such as versioning and the vetting of third-party skills, since the same portability that drove adoption is also what lets an untrusted folder run on dozens of different agents.

## References

1. Anthropic. "Equipping agents for the real world with Agent Skills." Anthropic Engineering, October 16, 2025 (updated December 18, 2025). https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
2. Anthropic. "anthropics/skills" repository (Anthropic's example skills; the specification now lives at agentskills.io). GitHub. https://github.com/anthropics/skills
3. Agent Skills. "Overview," "Specification," and "Client Showcase." agentskills.io, accessed October 30, 2026. https://agentskills.io/home , https://agentskills.io/specification and https://agentskills.io/clients
4. Xu, Renjun; Yan, Yang. "Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward." arXiv:2602.12430, February 2026. https://arxiv.org/abs/2602.12430
5. Ling, George; Zhong, Shanshan; Huang, Richard. "Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality." arXiv:2602.08004, February 8, 2026. https://arxiv.org/abs/2602.08004
6. Anthropic. "Donating Agent Skills to the Agentic AI Foundation." October 22, 2026. https://www.anthropic.com/news/donating-agent-skills-to-the-agentic-ai-foundation
7. Lardinois, Frederic. "Agent Skills: Anthropic's Next Bid to Define AI Standards." The New Stack, December 18, 2025. https://thenewstack.io/agent-skills-anthropics-next-bid-to-define-ai-standards/
8. Anthropic. "Skills for organizations, partners, the ecosystem." Claude blog, December 18, 2025. https://claude.com/blog/organization-skills-and-directory
9. The Linux Foundation. "Agentic AI Foundation Announces Four New Projects: Agent Skills, Open Responses, OpenEnv, and OpenSandbox." Press release, October 22, 2026. https://www.linuxfoundation.org/press/agentic-ai-foundation-announces-four-new-projects-agent-skills-open-responses-openenv-and-opensandbox
10. Jones, Angie. "Agent Skills: Sharing Team Expertise Across AI Agents." Agentic AI Foundation blog, October 22, 2026. https://aaif.io/blog/agent-skills-sharing-team-expertise-across-ai-agents
11. Anthropic. "Introducing Agent Skills." Claude blog, October 16, 2025. https://claude.com/blog/skills
12. GitHub. "GitHub Copilot now supports Agent Skills." GitHub Changelog, December 18, 2025. https://github.blog/changelog/2025-12-18-github-copilot-now-supports-agent-skills/
13. Microsoft. "December 2025 (version 1.108)." Visual Studio Code release notes, January 8, 2026. https://code.visualstudio.com/updates/v1_108
14. Willison, Simon. "OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI." Simon Willison's Weblog, December 12, 2025. https://simonwillison.net/2025/Dec/12/openai-skills/
15. OpenAI. "Agent skills in Codex." Codex changelog, December 19, 2025. https://developers.openai.com/codex/changelog
16. Cursor. "Subagents, Skills, and Image Generation" (Cursor 2.4). Changelog, January 22, 2026. https://cursor.com/changelog/2-4
17. Google. Gemini CLI release notes (v0.23.0, January 7, 2026; v0.25.0, January 20, 2026; v0.26.0, January 27, 2026). https://geminicli.com/docs/changelogs/
18. Vercel. "Introducing skills, the open agent skills ecosystem." Vercel changelog, January 20, 2026. https://vercel.com/changelog/introducing-skills-the-open-agent-skills-ecosystem
19. Liu, Yi; Wang, Weizhe; Feng, Ruitao; et al. "Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale." arXiv:2601.10338, January 15, 2026. https://arxiv.org/abs/2601.10338
20. Snyk. "Snyk Finds Prompt Injection in 36%, 1467 Malicious Payloads in a ToxicSkills Study of Agent Skills Supply Chain Compromise." Snyk blog, February 5, 2026. https://snyk.io/blog/toxicskills-malicious-ai-agent-skills-clawhub/
21. eSecurity Planet. "Hundreds of Malicious Skills Found in OpenClaw's ClawHub." February 3, 2026. https://www.esecurityplanet.com/threats/hundreds-of-malicious-skills-found-in-openclaws-clawhub/
22. Agent Skills. "agentskills/agentskills" repository (specification source, commit history, and license). GitHub, accessed October 30, 2026. https://github.com/agentskills/agentskills
23. Anthropic. "Agent Skills" overview. Claude Platform documentation, accessed October 30, 2026. https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
24. Anthropic. "Extend Claude with skills." Claude Code documentation, accessed October 30, 2026. https://code.claude.com/docs/en/skills

