kimi-integration
Step-by-step guide for integrating Moonshot AI (Kimi) and Kimi Code models into Clawdbot. Use when someone asks how to add Kimi models, configure Moonshot AI, or set up Kimi for Coding in Clawdbot.
Install
mkdir -p .claude/skills/kimi-integration && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8556" && unzip -o skill.zip -d .claude/skills/kimi-integration && rm skill.zipInstalls to .claude/skills/kimi-integration
About this skill
Kimi Model Integration
Complete guide for adding Moonshot AI (Kimi) and Kimi Code models to Clawdbot.
Overview
Kimi offers two separate model families:
- Moonshot AI (Kimi K2) - General-purpose models via OpenAI-compatible API
- Kimi Code - Specialized coding model with dedicated endpoint
Both require API keys from different sources.
Prerequisites
- Clawdbot installed and configured
- API keys (see Getting API Keys section)
Getting API Keys
Moonshot AI (Kimi K2)
- Visit https://platform.moonshot.cn
- Register an account
- Navigate to API Keys section
- Create a new API key
- Copy the key (starts with
sk-...)
Kimi Code
- Visit https://api.kimi.com/coding
- Register an account
- Navigate to API Keys section
- Create a new API key
- Copy the key (starts with
sk-...)
Note: Moonshot and Kimi Code use separate keys and endpoints.
Integration Steps
Option 1: Moonshot AI (Kimi K2 models)
Step 1: Set environment variable
export MOONSHOT_API_KEY="sk-your-moonshot-key-here"
Or add to .env file:
echo 'MOONSHOT_API_KEY="sk-your-moonshot-key-here"' >> ~/.env
Step 2: Add provider configuration
Edit your clawdbot.json config:
{
"agents": {
"defaults": {
"model": {
"primary": "moonshot/kimi-k2.5"
}
}
},
"models": {
"mode": "merge",
"providers": {
"moonshot": {
"baseUrl": "https://api.moonshot.cn/v1",
"apiKey": "${MOONSHOT_API_KEY}",
"api": "openai-completions",
"models": [
{
"id": "moonlight-v1-32k",
"name": "Moonlight V1 32K",
"contextWindow": 32768
},
{
"id": "moonshot-v1-8k",
"name": "Moonshot V1 8K",
"contextWindow": 8192
},
{
"id": "moonshot-v1-32k",
"name": "Moonshot V1 32K",
"contextWindow": 32768
},
{
"id": "moonshot-v1-128k",
"name": "Moonshot V1 128K",
"contextWindow": 131072
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"contextWindow": 200000
}
]
}
}
}
}
Step 3: Restart Clawdbot
clawdbot gateway restart
Step 4: Verify integration
clawdbot models list
You should see Moonshot models in the list.
Step 5: Use the model
Set as default:
clawdbot models set moonshot/kimi-k2.5
Or use model aliases in chat:
/model moonshot/kimi-k2.5
Option 2: Kimi Code (specialized coding model)
Step 1: Set environment variable
export KIMICODE_API_KEY="sk-your-kimicode-key-here"
Or add to .env:
echo 'KIMICODE_API_KEY="sk-your-kimicode-key-here"' >> ~/.env
Step 2: Add provider configuration
Edit your clawdbot.json config:
{
"agents": {
"defaults": {
"model": {
"primary": "kimicode/kimi-for-coding"
},
"models": {
"kimicode/kimi-for-coding": {
"alias": "kimi"
}
}
}
},
"models": {
"mode": "merge",
"providers": {
"kimicode": {
"baseUrl": "https://api.kimi.com/coding/v1",
"apiKey": "${KIMICODE_API_KEY}",
"api": "openai-completions",
"models": [
{
"id": "kimi-for-coding",
"name": "Kimi For Coding",
"contextWindow": 200000,
"maxTokens": 8192
}
]
}
}
}
}
Step 3: Restart Clawdbot
clawdbot gateway restart
Step 4: Verify integration
clawdbot models list
You should see kimicode/kimi-for-coding in the list.
Step 5: Use the model
Set as default:
clawdbot models set kimicode/kimi-for-coding
Or use model alias in chat:
/model kimi
Using Both Providers
You can configure both Moonshot and Kimi Code simultaneously:
{
"agents": {
"defaults": {
"model": {
"primary": "moonshot/kimi-k2.5"
},
"models": {
"kimicode/kimi-for-coding": {
"alias": "kimi"
},
"moonshot/kimi-k2.5": {
"alias": "k25"
}
}
}
},
"models": {
"mode": "merge",
"providers": {
"moonshot": {
"baseUrl": "https://api.moonshot.cn/v1",
"apiKey": "${MOONSHOT_API_KEY}",
"api": "openai-completions",
"models": [
{ "id": "kimi-k2.5", "name": "Kimi K2.5", "contextWindow": 200000 }
]
},
"kimicode": {
"baseUrl": "https://api.kimi.com/coding/v1",
"apiKey": "${KIMICODE_API_KEY}",
"api": "openai-completions",
"models": [
{ "id": "kimi-for-coding", "name": "Kimi For Coding", "contextWindow": 200000 }
]
}
}
}
}
Switch between models using aliases:
/model k25- Kimi K2.5 (general)/model kimi- Kimi for Coding (specialized)
Troubleshooting
Model not appearing in list
Check config syntax:
clawdbot gateway config.get | grep -A 20 moonshot
Verify API key is set:
echo $MOONSHOT_API_KEY
echo $KIMICODE_API_KEY
Authentication errors
- Verify API key starts with
sk- - Check key is valid on provider dashboard
- Ensure correct base URL for each provider
Connection issues
Test API endpoint directly:
curl -X POST "https://api.moonshot.cn/v1/chat/completions" \
-H "Authorization: Bearer $MOONSHOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "kimi-k2.5", "messages": [{"role": "user", "content": "test"}]}'
Model Recommendations
- Kimi K2.5 (
moonshot/kimi-k2.5) - Best for general tasks, 200K context - Kimi for Coding (
kimicode/kimi-for-coding) - Specialized for code generation - Moonshot V1 128K (
moonshot/moonshot-v1-128k) - Legacy model, 128K context
References
- Moonshot AI Docs: https://platform.moonshot.cn/docs
- Kimi Code API: https://api.kimi.com/coding/docs
- Clawdbot Model Providers: /home/eyurc/clawdbot/docs/concepts/model-providers.md
More by openclaw
View all skills by openclaw →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversUno Platform — Documentation and prompts for building cross-platform .NET apps with a single codebase. Get guides, sampl
Desktop Commander MCP unifies code management with advanced source control, git, and svn support—streamlining developmen
pg-aiguide — Version-aware PostgreSQL docs and best practices tailored for AI coding assistants. Improve queries, migrat
DeepWiki converts deepwiki.com pages into clean Markdown, with fast, secure extraction—perfect as a PDF text, page, or i
Supercharge your NextJS projects with AI-powered tools for diagnostics, upgrades, and docs. Accelerate development and b
Guide your software projects with structured prompts from requirements to code using the waterfall development model and
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.