Create a new model provider

VerifiedSafe

Create a new model provider following established patterns. Includes scaffolding, configuration, and testing.

Sby Skills Guide Bot
DevelopmentIntermediate
7/24/2026
Claude Code
#scaffold#model-provider#obot-tools#go#llm-integration

Recommended for

Automated summary

Scaffolds a new model provider for obot-tools by copying the OpenAI provider template and adapting it.

Strengths

  • Clear step-by-step procedure from template copy to validation test
  • Covers the key files: tool.gpt, Go code, index.yaml and environment variables
  • Includes a pre-commit checklist and concrete examples (Anthropic, Mistral)

Limitations

  • Assumes the obot-tools repo and the openai-model-provider folder already exist
  • Does not detail request/response mapping for non-OpenAI-compatible APIs
  • Reference templates must be loaded separately as Level 3 resources
When to use it

Use when adding support for a new LLM provider or a custom provider inside obot-tools.

When not to use it

Avoid it for editing an existing provider or for work outside the obot-tools ecosystem.

Security analysis

Safe
Quality score82/100

The skill is a scaffolding guide that copies an existing provider directory and edits configuration/Go code. The only executable snippets are a non-destructive `cp -r` and `go run . validate`, both of which operate on paths inside the repository. There is no secret exfiltration, no remote script execution, no destructive deletion, and no attempt to disable safety controls. It merely references read-only template resources.

No concerns found

How this analysis is made

Examples

Anthropic provider
Create an Anthropic model provider for obot-tools using the openai-model-provider template.
Mistral provider
Add Mistral AI support to obot-tools as a new model provider.
Custom provider
Scaffold a custom model provider in obot-tools with a new API base URL and API key auth.

name: new-provider description: Scaffold a new model provider for obot-tools version: 1.0.0 author: AI Team tags: [scaffold, obot, provider]

New Model Provider

Create a new model provider following established patterns.

When to Use

  • Adding support for a new LLM provider (Anthropic, Mistral, etc.)
  • Creating a custom model provider
  • Understanding model provider structure

Available Operations

  1. Scaffold: Create directory structure from template
  2. Configure: Set up tool.gpt and credentials
  3. Implement: Write provider-specific code
  4. Test: Validate the implementation

Instructions

Step 1: Gather Information

Required:

  • Provider name (e.g., "anthropic", "mistral")
  • API base URL
  • Authentication method (API key, OAuth)

Step 2: Copy Template

cp -r obot-tools/openai-model-provider obot-tools/{name}-model-provider

Step 3: Update tool.gpt

See references/tool-gpt-template.md for format:

  • Change Name: to {Name} Model Provider
  • Update Description:
  • Update credential if different auth method

Step 4: Update Go Code

  • Rename package
  • Update API endpoint
  • Adjust request/response mapping if API differs

Step 5: Update index.yaml

Add to modelProviders: section:

- name: {name}-model-provider
  description: {Name} model provider for Obot
  path: ./{name}-model-provider

Step 6: Test

cd obot-tools/{name}-model-provider
export OBOT_{NAME}_MODEL_PROVIDER_API_KEY=...
go run . validate

Resources

Load these Level 3 resources as needed:

  • references/tool-gpt-template.md - GPTScript template for model providers
  • references/provider-patterns.md - Common provider implementation patterns
  • assets/main.go.tmpl - Go main.go template

Examples

Example: Anthropic Provider

User asks: "Create an Anthropic model provider"

Response:

  1. Copy openai-model-provider
  2. Update Name to "Anthropic Model Provider"
  3. Update API endpoint to api.anthropic.com
  4. Adjust message format for Claude API
  5. Test with validate command

Example: Mistral Provider

User asks: "Add Mistral AI support"

Response:

  1. Copy openai-model-provider (Mistral is OpenAI-compatible)
  2. Update Name to "Mistral Model Provider"
  3. Update base URL to api.mistral.ai
  4. Minimal code changes (OpenAI compatible)
  5. Test with validate command

Checklist

Before committing:

  • [ ] tool.gpt has correct Name, Description, Tools
  • [ ] Environment variable follows pattern: OBOT_{NAME}_MODEL_PROVIDER_*
  • [ ] Implements OpenAI-compatible /v1/chat/completions endpoint
  • [ ] Error responses are user-friendly
  • [ ] Added to index.yaml
  • [ ] Tested with go run . validate

Notes

  • Most providers follow OpenAI-compatible format
  • Check if provider has OpenAI-compatible endpoint first
  • Environment variables follow pattern: OBOT_{NAME}_MODEL_PROVIDER_*

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/create-a-new-model-provider-mryiqi2w/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/create-a-new-model-provider-mryiqi2w' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-a-new-model-provider-mryiqi2w/download' --output '.skill-downloads/create-a-new-model-provider-mryiqi2w/SKILL.md.part' && mv '.skill-downloads/create-a-new-model-provider-mryiqi2w/SKILL.md.part' '.skill-downloads/create-a-new-model-provider-mryiqi2w/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/create-a-new-model-provider-mryiqi2w/SKILL.md' && test -s '.skill-downloads/create-a-new-model-provider-mryiqi2w/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/new-provider' && cp -R '.skill-downloads/create-a-new-model-provider-mryiqi2w' '.claude/skills/new-provider'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/create-a-new-model-provider-mryiqi2w'

openskills read 'create-a-new-model-provider-mryiqi2w'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/create-a-new-model-provider-mryiqi2w/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills