HE

hermes-custom-vision-provider

Configures non-standard vision providers in the Hermes Agent, avoiding default provider limitations.

Install

mkdir -p .claude/skills/hermes-custom-vision-provider && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16954" && unzip -o skill.zip -d .claude/skills/hermes-custom-vision-provider && rm skill.zip

Installs to .claude/skills/hermes-custom-vision-provider

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Configure custom/OpenAI-compatible vision providers in Hermes Agent (Kimi, DeepSeek, Azure, etc.)
97 charsno explicit “when” trigger
Intermediate

Key capabilities

  • →Configure custom vision providers like Kimi or DeepSeek
  • →Specify base_url for custom OpenAI-compatible endpoints
  • →Reference API keys from environment variables
  • →Set model names for custom vision providers
  • →Debug vision authentication issues
  • →Restart the Hermes Gateway process

How it works

The skill configures the Hermes Agent's auxiliary vision settings by setting the provider to 'custom' and specifying the base_url, model, and api_key_env in the YAML configuration.

Inputs & outputs

You give it
YAML configuration for auxiliary vision provider settings
You get back
Hermes Agent routing API calls to the specified custom vision model

When to use hermes-custom-vision-provider

  • →Setup custom vision model
  • →Configure DeepSeek vision
  • →Debug vision authentication

About hermes-custom-vision-provider

Sets up custom OpenAI-compatible vision endpoints. Maps environment variables to providers, ensuring API calls correctly route to custom models like Kimi or DeepSeek.

Configure custom/OpenAI-compatible vision providers in Hermes Agent (Kimi, DeepSeek, Azure, etc.)

When not to use it

  • →When using the default OpenRouter auto-detection for vision providers
  • →When the provider is set to 'openai' for a custom endpoint
  • →When an empty string is used for api_key while api_key_env is also set

Limitations

  • →Using 'provider: openai' ignores base_url and api_key_env settings
  • →An empty string for 'api_key' overrides 'api_key_env'
  • →Some models like 'kimi-k2.5' require specific temperature settings not always supported by default

How it compares

This skill explicitly directs API calls to custom OpenAI-compatible vision endpoints, bypassing the default OpenAI provider's settings and allowing for flexible model integration.

Compared to similar skills

hermes-custom-vision-provider side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
hermes-custom-vision-provider (this skill)07moReviewIntermediate
fastapi-templates5206moNo flagsIntermediate
android-kotlin-development2688moReviewAdvanced
mcp-builder1367moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

fastapi-templates

wshobson

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

5201,086

android-kotlin-development

aj-geddes

Develop native Android apps with Kotlin. Covers MVVM with Jetpack, Compose for modern UI, Retrofit for API calls, Room for local storage, and navigation architecture.

268679

mcp-builder

anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

136215

fastapi-pro

sickn33

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.

79181

api-design-principles

wshobson

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

72170

telegram-bot-builder

davila7

Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.

106130

Search skills

Search the agent skills registry