---
title: "Agent Skills core and discovery"
canonical: "https://canmyagentuse.com/features/skills"
contentKind: "feature"
locale: "en"
description: "Discover and load standard SKILL.md packages, with current-track evidence for selected chat and coding harnesses."
llmSummary: "This atomic row covers recognizing, discovering, and loading standard SKILL.md packages. Scripts, assets, invocation, and scopes have separate sibling rows."
publishedAt: "2026-08-28T00:00:00.000Z"
updatedAt: "2026-08-28T00:00:00.000Z"
verifiedAt: "2026-08-28"
tags: ["runtime","skills","instructions","packaging"]
---

# Agent Skills core and discovery

This atomic row covers recognizing, discovering, and loading standard SKILL.md packages. Scripts, assets, invocation, and scopes have separate sibling rows.

- HTML: https://canmyagentuse.com/features/skills
- JSON: https://canmyagentuse.com/api/v1/features/skills.json
- Markdown: https://canmyagentuse.com/features/skills.md

Terminology basis: **Agent Skills specification** — https://agentskills.io/specification.

## Current support at a glance

Agent Skills core and discovery: 6 supported, 3 partial, 0 unsupported, 22 unreviewed across 31 cataloged products.

- Reviewed current products: 9 of 31
- Supported: 6
- Partial: 3
- Unsupported: 0
- Unreviewed: 22
- Not applicable: 0

Unknown or unreviewed means insufficient published evidence; it does not mean unsupported.

Agent Skills are reusable directories centered on `SKILL.md`, with optional scripts, references, and assets. The catalog treats basic discovery as narrower than full support for progressive loading, script execution, every install scope, or every extension field.

Sourced cells therefore retain beta, plan, policy, code-execution, and surface conditions. A skill package can contain executable code; documented loading does not imply that Can My Agent Use executed or security-reviewed third-party skills.

## Catalog context

- Category: [runtime](/categories/runtime.md)
- Specification: [agent-skills](/specs/agent-skills.md) — revision living
- Aliases: SKILL.md, skill packs, reusable workflows
- Family: [Agent Skills](/features/agent-skills.md)
- Siblings: [Agent Skills manual invocation](/features/skill-manual-invocation.md), [Agent Skills progressive loading](/features/skill-progressive-loading.md), [Agent Skills references and assets](/features/skill-references-assets.md), [Agent Skills scripts](/features/skill-scripts.md), [Project-scoped Agent Skills](/features/skill-project-scope.md), [User-scoped Agent Skills](/features/skill-user-scope.md)

## Compatibility assertions

Unknown means insufficient published evidence; it does not mean unsupported.

### ChatGPT (web)

- Harness: [ChatGPT](/harnesses/chatgpt-web.md)
- current: **Partial**
  - Target: hosted-observation — 2026-08-28 hosted documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (plan): personal availability is limited to eligible plans
  - Constraint (policy): workspace administrators control enablement and sharing
  - Evidence: [OpenAI — Skills in ChatGPT](https://help.openai.com/en/articles/20001066) — documented; observed 2026-08-28
  - Qualification note 1: Evidence checked 2026-08-28: ChatGPT supports OpenAI Skills following the Agent Skills open standard, but personal skill availability and administration vary by plan, workspace, and surface.
- preview: **Unknown**

### Claude (web)

- Harness: [Claude](/harnesses/claude-web.md)
- current: **Partial**
  - Target: hosted-observation — 2026-08-28 hosted documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): code execution must be enabled
  - Constraint (policy): organization controls can govern availability
  - Evidence: [Anthropic — What are skills?](https://support.claude.com/en/articles/12512176-what-are-skills) — documented; observed 2026-08-28
  - Qualification note 2: Evidence checked 2026-08-28: Claude can dynamically load Agent Skills across plans when code execution is enabled; organization controls and feature prerequisites still apply.
- preview: **Unknown**

### Gemini (web)

- Harness: [Gemini](/harnesses/gemini-web.md)
- current: **Unknown**
- preview: **Unknown**

### Copilot (web)

- Harness: [Copilot](/harnesses/copilot-web.md)
- current: **Unknown**
- preview: **Unknown**

### Grok (web)

- Harness: [Grok](/harnesses/grok-web.md)
- current: **Unknown**
- preview: **Unknown**

### Grok Bot (desktop)

- Harness: [Grok Bot](/harnesses/grok-bot-desktop.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Grok Bot desktop documentation and compatible-client listing; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): saved skills are available across Bots and packaged or private skills are managed through the desktop Plugins area
  - Constraint (policy): connector or login prerequisites and per-Bot enablement can limit a skill at runtime
  - Evidence: [xAI — Grok Bot skills and routines](https://docs.x.ai/grok-bot/skills-routines-and-automations) — documented; observed 2026-08-28
  - Evidence: [Agent Plugins — Compatible clients](https://agent-plugins.org/compatible-clients) — listed; observed 2026-08-28
  - Qualification note 9: Evidence checked 2026-08-28: xAI documents saved and packaged skills in Grok Bot, and the Agent Plugins compatible-client registry lists Grok Bot as loading Agent Skills. The cell establishes core discovery and loading, not every optional Agent Skills behavior.

### Perplexity (web)

- Harness: [Perplexity](/harnesses/perplexity-web.md)
- current: **Unknown**
- preview: **Unknown**

### Le Chat (web)

- Harness: [Le Chat](/harnesses/le-chat.md)
- current: **Unknown**
- preview: **Unknown**

### Devin (web)

- Harness: [Devin](/harnesses/devin-web.md)
- current: **Unknown**
- preview: **Unknown**

### Replit Agent (web)

- Harness: [Replit Agent](/harnesses/replit-agent.md)
- current: **Unknown**
- preview: **Unknown**

### ChatGPT (desktop)

- Harness: [ChatGPT](/harnesses/chatgpt-desktop.md)
- current: **Unknown**
- preview: **Unknown**

### Claude (desktop)

- Harness: [Claude](/harnesses/claude-desktop.md)
- current: **Unknown**
- preview: **Unknown**

### Cursor (desktop)

- Harness: [Cursor](/harnesses/cursor.md)
- current: **Supported**
  - Target: dated-documentation — current Cursor Agent Skills documentation; observed 2026-08-28
  - Environment: local-default
  - Evidence: [Cursor — Agent Skills](https://prod.cursor.com/docs/skills) — documented; observed 2026-08-28
  - Qualification note 4: Evidence checked 2026-08-28: Cursor documents automatic discovery, manual invocation, progressive loading, and project or user skill directories.
- preview: **Unknown**

### OpenWork Desktop (desktop)

- Harness: [OpenWork Desktop](/harnesses/openwork-desktop.md)
- current: **Supported**
  - Target: dated-documentation — current OpenWork skill documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): native workspace path is .opencode/skills
  - Constraint (policy): organization skill installation requires OpenWork Cloud
  - Evidence: [OpenWork — Import a skill](https://openworklabs.com/docs/start-here/do-work-with-it/import-a-skill) — documented; observed 2026-08-28
  - Qualification note 8: Evidence checked 2026-08-28: OpenWork Desktop documents SKILL.md creation, import, sharing, organization installation, and workspace loading through its OpenCode-backed runtime.

### Copilot Chat (desktop)

- Harness: [Copilot Chat](/harnesses/vscode-copilot.md)
- current: **Supported**
  - Target: dated-documentation — current VS Code Agent Skills documentation; observed 2026-08-28
  - Environment: local-default
  - Evidence: [Visual Studio Code — Use Agent Skills](https://code.visualstudio.com/docs/agent-customization/agent-skills) — documented; observed 2026-08-28
  - Qualification note 7: Evidence checked 2026-08-28: VS Code documents Agent Skills as generally available for GitHub Copilot in VS Code with project and personal directories and progressive loading.
- preview: **Unknown**

### Chrome WebMCP origin trial (desktop)

- Harness: [Chrome WebMCP origin trial](/harnesses/chrome-webmcp-preview.md)
- current: **Unknown**

### Windsurf (desktop)

- Harness: [Windsurf](/harnesses/windsurf.md)
- current: **Unknown**
- preview: **Unknown**

### Zed Agent (desktop)

- Harness: [Zed Agent](/harnesses/zed-agent.md)
- current: **Unknown**
- preview: **Unknown**

### Continue (desktop)

- Harness: [Continue](/harnesses/continue.md)
- current: **Unknown**
- preview: **Unknown**

### Cline (desktop)

- Harness: [Cline](/harnesses/cline.md)
- current: **Unknown**
- preview: **Unknown**

### JetBrains AI (desktop)

- Harness: [JetBrains AI](/harnesses/jetbrains-ai.md)
- current: **Unknown**
- preview: **Unknown**

### Warp (desktop)

- Harness: [Warp](/harnesses/warp.md)
- current: **Unknown**
- preview: **Unknown**

### Claude CLI (cli)

- Harness: [Claude CLI](/harnesses/claude-cli.md)
- current: **Partial**
  - Target: dated-documentation — current Claude Code documentation; observed 2026-08-28
  - Environment: preview-enabled
  - Constraint (preview): Claude Code support is beta
  - Evidence: [Anthropic — Use skills in Claude](https://support.claude.com/en/articles/12512180-use-skills-in-claude) — documented; observed 2026-08-28
  - Qualification note 3: Evidence checked 2026-08-28: Claude Code supports Agent Skills in beta, so the CLI cell is conditional rather than unqualified support.
- preview: **Unknown**

### ChatGPT CLI (cli)

- Harness: [ChatGPT CLI](/harnesses/chatgpt-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Codex CLI (cli)

- Harness: [Codex CLI](/harnesses/codex-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Codex documentation; observed 2026-08-28
  - Environment: local-default
  - Evidence: [OpenAI — Introducing the Codex app](https://openai.com/index/introducing-the-codex-app/) — documented; observed 2026-08-28
  - Qualification note 5: Evidence checked 2026-08-28: OpenAI documents skills as reusable capabilities for Codex across its local agent surfaces, including CLI workflows.
- preview: **Unknown**

### OpenCode (cli)

- Harness: [OpenCode](/harnesses/opencode.md)
- current: **Unknown**
- preview: **Unknown**

### Gemini CLI (cli)

- Harness: [Gemini CLI](/harnesses/gemini-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Gemini CLI Agent Skills documentation; observed 2026-08-28
  - Environment: local-default
  - Evidence: [Gemini CLI — Managing Agent Skills](https://geminicli.com/docs/cli/using-agent-skills/) — documented; observed 2026-08-28
  - Qualification note 6: Evidence checked 2026-08-28: Gemini CLI documents skill discovery tiers, installation, activation, and the Agent Skills directory structure.
- preview: **Unknown**

### Aider (cli)

- Harness: [Aider](/harnesses/aider.md)
- current: **Unknown**
- preview: **Unknown**

### Goose (cli)

- Harness: [Goose](/harnesses/goose.md)
- current: **Unknown**
- preview: **Unknown**

### Copilot CLI (cli)

- Harness: [Copilot CLI](/harnesses/copilot-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Amp (cli)

- Harness: [Amp](/harnesses/amp-cli.md)
- current: **Unknown**
- preview: **Unknown**