Anth Migration Deep Dive

What it does

When your agent uses it

• Switching from GPT-4 to Claude
• Migrating from Text Completions
• Building a multi-provider abstraction layer
• With phrases like migrate to claude

Example prompts

• “migrate to claude”
• “openai to anthropic”
• “switch from gpt to claude”
• “/anth-migration-deep-dive”

Requirements

• Python 3
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(npm:*), Grep

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Map request and response fields using the tables above, preserving semantics rather than assuming identical tokenization, tool behavior…
2. 2Move system instructions to the Anthropic system parameter, make max_tokens explicit, and validate alternating message roles and tool…
3. 3Run old and new providers in a shadow or replay lane with synthetic fixtures. Compare structured outcomes, latency, token/cost aggregates…
4. 4Release behind a feature flag to a small canary with a bounded budget and authorized destinations. Monitor for scope, retention, error, or…
5. 5Promote only after acceptance evidence is approved. If any invariant fails, disable the flag and restore the prior provider…

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(npm:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • platform.claude.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Anth Migration Deep Dive loads about 2k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 560 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~84

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 560 words, ~1,961 tokens.

name

anth-migration-deep-dive

description

Migrate to Claude API from OpenAI, Gemini, or other LLM providers. Use when switching from GPT-4 to Claude, migrating from Text Completions, or building a multi-provider abstraction layer. Trigger with phrases like "migrate to claude", "openai to anthropic", "switch from gpt to claude", "multi-provider llm".

allowed-tools

Read, Write, Edit, Bash(npm:*), Grep

compatibility

Designed for Claude Code

version

1.7.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, ai, anthropic

# === OpenAI ===
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": "You are helpful."},
        {"role": "user", "content": "Hello"}
    ],
    max_tokens=1024,
    temperature=0.7
)
text = response.choices[0].message.content

# === Anthropic ===
import anthropic
client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    system="You are helpful.",           # System prompt is separate
    messages=[
        {"role": "user", "content": "Hello"}
    ],
    max_tokens=1024,                     # Required (not optional)
    temperature=0.7
)
text = response.content[0].text

# OpenAI tools format
openai_tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}
    }
}]

# Anthropic tools format — flatter structure
anthropic_tools = [{
    "name": "get_weather",
    "description": "Get weather for a city",  # Required in Anthropic
    "input_schema": {"type": "object", "properties": {"city": {"type": "string"}}}
}]

from abc import ABC, abstractmethod

class LLMProvider(ABC):
    @abstractmethod
    def complete(self, prompt: str, system: str = "", **kwargs) -> str: ...

class AnthropicProvider(LLMProvider):
    def __init__(self):
        import anthropic
        self.client = anthropic.Anthropic()

    def complete(self, prompt: str, system: str = "", **kwargs) -> str:
        msg = self.client.messages.create(
            model=kwargs.get("model", "claude-sonnet-4-20250514"),
            max_tokens=kwargs.get("max_tokens", 1024),
            system=system,
            messages=[{"role": "user", "content": prompt}]
        )
        return msg.content[0].text

class OpenAIProvider(LLMProvider):
    def __init__(self):
        from openai import OpenAI
        self.client = OpenAI()

    def complete(self, prompt: str, system: str = "", **kwargs) -> str:
        messages = []
        if system:
            messages.append({"role": "system", "content": system})
        messages.append({"role": "user", "content": prompt})
        resp = self.client.chat.completions.create(
            model=kwargs.get("model", "gpt-4"),
            messages=messages,
            max_tokens=kwargs.get("max_tokens", 1024)
        )
        return resp.choices[0].message.content

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/anth-migration-deep-dive of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287