Skip to content
Back to search

kilo-marketplace

Kilo Marketplace - A curated collection of Skills, MCP Servers, and Modes for enhancing AI agent capabilities across the Kilo ecosystem—including Kilo Code (VS Code extension), Kilo CLI, and compatible AI agents.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/kilo-org--kilo-marketplace/badge.svg)](/listings/kilo-org--kilo-marketplace)

HTML

<a href="/listings/kilo-org--kilo-marketplace"><img src="/api/listings/kilo-org--kilo-marketplace/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 171 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <h1 align="center">Kilo Marketplace</h1>
  2. A curated collection of **Skills**, **MCP Servers**, **Agents**, and **Plugins** for enhancing AI agent capabilities across the Kilo ecosystem, including Kilo Code (VS Code extension), Kilo CLI, and compatible AI agents.
  3. ---
  4. ## What is the Kilo Marketplace?
  5. The Kilo Marketplace is a community-driven repository of agent tooling prompts and configurations. It provides four types of resources that extend what AI agents can do:
  6. | Resource | Description |
  7. |----------|-------------|
  8. | **[Skills](#skills)** | Modular workflows and domain expertise that teach agents how to perform specific tasks |
  9. | **[MCP Servers](#mcp-servers)** | Standardized integrations that connect agents to external tools and services |
  10. | **[Agents](#agents)** | Specialized agent configurations for focused tasks and workflows |
  11. | **[Plugins](#plugins)** | Code that extends agent runtime behavior with hooks, custom tools, auth providers, and model providers |
  12. ---
  13. ## Contents
  14. - [Skills](#skills)
  15. - [What Are Skills?](#what-are-skills)
  16. - [Skill Structure](#skill-structure)
  17. - [Creating Skills](#creating-skills)
  18. - [MCP Servers](#mcp-servers)
  19. - [What Are MCP Servers?](#what-are-mcp-servers)
  20. - [Agents](#agents)
  21. - [What Are Agents?](#what-are-agents)
  22. - [Plugins](#plugins)
  23. - [What Are Plugins?](#what-are-plugins)
  24. - [Contributing](#contributing)
  25. - [License](#license)
  26. ---
  27. ## Skills
  28. ### What Are Skills?
  29. Skills are self-contained packages that extend an agent's capabilities with specialized knowledge and repeatable workflows. At their core, a skill is a folder containing a `SKILL.md` file with metadata and instructions that tell an agent how to perform a specific task.
  30. Skills follow the open [Agent Skills specification](https://agentskills.io/), making them interoperable across any compatible AI agent—not just Kilo.
  31. **Key benefits:**
  32. - **Self-documenting**: Easy to read, audit, and improve
  33. - **Interoperable**: Works across any agent implementing the Agent Skills spec
  34. - **Extensible**: Can include scripts, templates, and reference materials
  35. - **Shareable**: Portable between projects and developers
  36. ### Skill Structure
  37. Each skill is a folder containing a `SKILL.md` file with YAML frontmatter:
  38. ```
  39. skill-name/
  40. ├── SKILL.md # Required: Skill instructions and metadata
  41. ├── scripts/ # Optional: Helper scripts
  42. ├── references/ # Optional: Documentation
  43. ├── assets/ # Optional: Templates, resources
  44. └── examples/ # Optional: Example files
  45. ```
  46. ### Creating Skills
  47. **Basic Skill Template:**
  48. ```markdown
  49. ---
  50. name: my-skill-name
  51. description: A clear description of what this skill does and when to use it.
  52. ---
  53. # My Skill Name
  54. Detailed description of the skill's purpose and capabilities.
  55. ## When to Use This Skill
  56. - Use case 1
  57. - Use case 2
  58. - Use case 3
  59. ## Instructions
  60. [Detailed instructions for the agent on how to execute this skill]
  61. ## Examples
  62. [Real-world examples showing the skill in action]
  63. ```
  64. **Best Practices:**
  65. - Focus on specific, repeatable tasks
  66. - Include clear examples and edge cases
  67. - Write instructions for the agent, not end users
  68. - Document prerequisites and dependencies
  69. - Include error handling guidance
  70. ---
  71. ## MCP Servers
  72. ### What Are MCP Servers?
  73. MCP (Model Context Protocol) is a standardized communication protocol that allows AI agents to interact with external tools and services. Think of it as a universal adapter—any compatible agent can connect to any MCP server to access its functionality.
  74. MCP servers provide capabilities like:
  75. - File system access
  76. - Database queries
  77. - API integrations
  78. - External service connections
  79. **How it works:**
  80. 1. The AI agent (client) connects to MCP servers
  81. 2. Each server provides specific capabilities
  82. 3. The agent uses these capabilities through a standardized interface
  83. 4. Communication occurs via JSON-RPC 2.0 messages
  84. MCP servers can run locally on your machine or remotely as cloud services, depending on security requirements.
  85. Browse available MCP servers in the [`mcps/`](./mcps/) directory.
  86. MCP definitions can include companion skills that teach agents how to use the server. Authors list skill IDs in an optional `skills` field; the catalog generator resolves them to the same archives used by standalone skill installations. This is separate from setup `prerequisites` and dependency `requirements`. See [MCP Companion Skills](CONTRIBUTING.md#mcp-companion-skills) for a complete remote-server example, validation commands, and release order. Companion installation requires a client with bundle support.
  87. ---
  88. ## Agents
  89. ### What Are Agents?
  90. Agents are specialized configurations that define focused roles, workflows, and instructions for tasks such as documentation, code review, and testing.
  91. Browse available agents in the [`agents/`](./agents/) directory. The [`modes/`](./modes/) marketplace remains available only for legacy 5.x clients.
  92. ---
  93. ## Plugins
  94. ### What Are Plugins?
  95. Plugins extend Kilo with hooks, custom tools, auth providers, model providers, and runtime behavior. A plugin is published to npm or hosted in a public git repository, and each plugin is described by one `PLUGIN.yaml` file under `plugins/<id>/`.
  96. Plugins use the categories `business`, `data`, `development`, `observability`, `productivity`, `providers`, `search`, and `web-automation`.
  97. Plugins execute code with the user's permissions, so review the source before installation. Browse available plugins in the [`plugins/`](./plugins/) directory, and see [`plugins/README.md`](./plugins/README.md) for the manifest fields, supported source specifiers, and contribution workflow.
  98. ---
  99. ## Contributing
  100. We welcome contributions! Please read our [Contributing Guidelines](CONTRIBUTING.md) for details on:
  101. - How to submit new skills, MCP servers, or plugins
  102. - Quality standards
  103. - Pull request process
  104. - Code of conduct
  105. ### Quick Contribution Steps
  106. 1. Ensure your contribution is based on a real use case
  107. 2. Check for duplicates in existing resources
  108. 3. Follow the appropriate structure template
  109. 4. Test your contribution across platforms
  110. 5. Submit a pull request with clear documentation
  111. ---
  112. ## License
  113. This repository is licensed under the Apache License 2.0.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.