New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Migrating Claude Agent SDK To Pydantic AI

by pydantic in pydantic/pydantic-ai

Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.

OfficialMITAuto-check passedAgent Workflows

Install Migrating Claude Agent SDK To Pydantic AI

skills CLI
$ npx skills add pydantic/pydantic-ai --skill migrating-claude-agent-sdk-to-pydantic-ai -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pydantic/pydantic-ai migrating-claude-agent-sdk-to-pydantic-ai --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pydantic/pydantic-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pydantic_ai_slim/pydantic_ai/.agents/skills/migrating-claude-agent-sdk-to-pydantic-ai .claude/skills/migrating-claude-agent-sdk-to-pydantic-ai && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
migrating-claude-agent-sdk-to-pydantic-ai
GitHub stars
21k
Token cost
~1.6k tokens
SKILL.md length
765 words
Files
4 (incl. references)
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.

  • Works in 4 steps: Read repository instructions,… → Trace one real request from query() or… → Separate these source contracts when… → …
  • Source code imports claudeagentsdk
  • SKILL.md covers Trace the source before…, Choose the smallest target, Apply high-risk gates and Implement and prove one…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Migrating Claude Agent SDK To Pydantic AI is an agent skill from pydantic/pydantic-ai, published by the product's own GitHub organization. Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports claudeagentsdk or relies on Claude Code's agent loop, sessions, built-in tools, hooks, permissions, skills, or subagents. Do not use for the Anthropic Messages SDK or Claude Managed Agents.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/RESEARCH-AND-MAPPING.md` and `references/VERIFICATION-AND-CUTOVER.md`).

It sits in Agent Workflows, covering Autonomous loops and Subagents. It works with Pydantic AI, Claude Agent SDK and Python. The repository describes itself as: How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. The licence is MIT.

When your agent uses it

  • Source code imports claudeagentsdk
  • Relies on Claude Codes agent loop
  • The Anthropic Messages SDK
  • Claude Managed Agents

Example prompts

  • “/migrating-claude-agent-sdk-to-pydantic-ai”

Requirements

  • Python 3

Workflow steps

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

  1. Read repository instructions, dependencies, tests, and the runtime entrypoint. Record the installed Claude Agent SDK, bundled Claude Code…
  2. Trace one real request from query() or ClaudeSDKClient through prompts, tools, events, results, state, persistence, approvals, and side…
  3. Separate these source contracts when present
  4. Record each observed contract, its owner, semantic difference, and executable proof. An unobserved Claude Code feature is not migration…

What it can do on your machine

Read from SKILL.md and the folder at commit 69ea1e5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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.

Context cost

Migrating Claude Agent SDK To Pydantic AI loads about 1.6k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 765 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.7k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 pydantic/pydantic-ai at commit 69ea1e5, republished under its MIT licence (© pydantic). 765 words, ~1,602 tokens.

Download SKILL.mdSave it as .claude/skills/migrating-claude-agent-sdk-to-pydantic-ai/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
migrating-claude-agent-sdk-to-pydantic-ai
description
Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports `claude_agent_sdk` or relies on Claude Code's agent loop, sessions, built-in tools, hooks, permissions, skills, or subagents. Do not use for the Anthropic Messages SDK or Claude Managed Agents.

Migrate Claude Agent SDK to Pydantic AI

Preserve observable behavior, not the Claude Code process or API shape. Migrate the smallest complete caller path and keep application infrastructure in place.

Trace the source before choosing a target

  1. Read repository instructions, dependencies, tests, and the runtime entrypoint. Record the installed Claude Agent SDK, bundled Claude Code CLI, Pydantic AI, and Harness versions.
  2. Trace one real request from query() or ClaudeSDKClient through prompts, tools, events, results, state, persistence, approvals, and side effects that callers use. Establish a focused baseline or characterization test.
  3. Separate these source contracts when present:
    • fresh query() calls, live ClaudeSDKClient continuation, disk/external-store resume, transcript forks, and file rewind;
    • tool availability, automatic approval, policy callbacks, and OS/container isolation;
    • completed messages, raw token deltas, lifecycle events, and terminal results;
    • conversation history, workflow checkpoints, model-owned plans, long-term memory, and workspace state;
    • model-directed subagents from application-owned loops, queues, retries, and schedulers.
  4. Record each observed contract, its owner, semantic difference, and executable proof. An unobserved Claude Code feature is not migration scope.

Read Research and concept mapping for the detected source features. Read Verification and cutover before implementation.

Choose the smallest target

  • Core: use pydantic_ai.Agent for model calls, the agent loop, typed dependencies, tools, outputs, normalized messages, generic hooks, streaming, MCP, approvals, usage limits, instrumentation, and durable-runtime integrations.
  • Harness: add pydantic-ai-harness only for observed reusable policy such as coding filesystem/shell tools, repository context, planning, memory, model-directed subagents, model-agnostic context management, or Agent Skills. Harness capabilities compose through the core agent loop; Harness is not a second runtime.
  • Application: retain authentication, service clients, databases, queues, schedulers, deployment, product state, session lookup, tenant policy, and existing transports unless the requested slice includes them.
  • Gap: name behavior that no supported public seam preserves, explain its impact, and test a bounded adapter. Do not create a lookalike ClaudeSDKClient or emulate Claude transcript files merely to hide a difference.

The normal migration is one reusable Agent, application services supplied through typed dependencies, ordinary Pydantic AI tools, a typed output when the caller expects structure, and application-owned storage of result.all_messages() when later turns need context. Preserve the existing public request/response/event boundary with a small adapter while callers migrate.

Show full SKILL.md (403 more words)Show less

Apply high-risk gates

  • allowed_tools in the Claude Agent SDK means auto-approval, not exclusive availability and not isolation. Map availability, approval, policy, and sandboxing independently.
  • Pydantic AI message_history explicitly replays normalized messages. conversation_id correlates runs; it is not a Claude session-resume token. Prove restart and fork behavior rather than renaming IDs.
  • Pydantic AI approval defers a validated tool call. The application still owns authenticated authorization, identity, and audit, and the protected effect must not run before approval.
  • Map hooks by firing point, inputs, ordering, mutation, blocking, and error behavior. Claude hook matchers may run concurrently. Pydantic AI runs before_* hooks in capability order, after_* hooks in reverse order, and nests wrap_* hooks with the first capability outermost. Require a golden trace for any hook-visible contract.
  • Map consumer intent for streaming. Pydantic AI output streaming, run-event streaming, and graph iteration are different surfaces; none promises the Claude SDK message taxonomy.
  • Use Harness SubAgents only for model-directed delegation. Keep deterministic orchestration and verification loops in application code.
  • Harness Skills supplies on-demand SKILL.md instructions; verify resources and scripts separately instead of assuming Claude Code skill or plugin loading parity.
  • Harness command controls are best-effort policy, not an OS security boundary. For untrusted execution, use ModalSandbox where it fits or retain application-owned container, VM, or sandbox isolation.
  • File rewind, Claude Code prompt presets, plugin packaging, raw stream-event identity, and dynamic MCP control are gaps unless the migrated caller actually needs them and a public target seam is proven.

Implement and prove one vertical slice

  1. Preserve the supported caller boundary and replace only the agent-owned internals.
  2. Start core-only. Add the narrowest Harness capabilities only after a source contract requires them.
  3. Test inputs, typed outputs, errors, event order, tool arguments/results, approval decisions, state across turns, and side effects at that boundary. Use deterministic models and fake application services for offline tests; add a focused recorded/live test only when provider behavior is the contract.
  4. For resume, durability, approvals, concurrent tools, or external effects, test interruption/restart, lineage, authorization, and idempotency at the exact boundary promised by the source.
  5. Remove claude-agent-sdk only after no retained path imports it, spawns Claude Code, reads its transcripts, or consumes its event/result types.

Explain any consequential semantic change before implementing it: state the source behavior, target behavior, caller impact, recommended choice, and remaining risk.

Completion

Apply the completion criterion in Verification and cutover. Label evidence from fakes, recordings, and live providers accurately.

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

Files

SKILL.md and 3 other files (references) in pydantic_ai_slim/pydantic_ai/.agents/skills/migrating-claude-agent-sdk-to-pydantic-ai of pydantic/pydantic-ai.

  • SKILL.md
  • agents/openai.yaml
  • references/RESEARCH-AND-MAPPING.md
  • references/VERIFICATION-AND-CUTOVER.md

Open the folder on GitHubat commit 69ea1e5

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in pydantic/pydantic-ai, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Migrating Claude Agent SDK To Pydantic AI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Migrating Claude Agent SDK To Pydantic AI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Migrating Claude Agent SDK To Pydantic AI this skillpydantic/pydantic-ai21k—~1.6kAutomated safety check: PassMIT
Pydantic AI Harnesspydantic/skills140—~1.9kAutomated safety check: PassMIT
Agentic Developmentalinaqi/maggy707—~5.9kAutomated safety check: PassMIT
Generate AI Rulesdivar-ir/ai-doc-gen767—~1.2kAutomated safety check: PassMIT
Claude Statusbarleeguooooo/claude-code-usage-bar378—~2.6kAutomated safety check: PassMIT
Goal Prompt Builderwin4r/goal-prompt-builder229—~3.1kAutomated safety check: PassMIT

Similar skills

  • Pydantic AI Harness

    pydantic/skills

    Official

    Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- Code Mode (collapse many tool calls into one sandboxed Python execution), a filesystem and shell…

    140 GitHub stars~1.9k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • Agentic Development

    alinaqi/maggy

    Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)

    707 GitHub stars~5.9k tokensUpdated 17 days ago
    AI & LLM EngineeringAuto-check passed

  • Generate AI Rules

    divar-ir/ai-doc-gen

    Generate AI assistant configuration files for a repository — CLAUDE.md, AGENTS.md, and Cursor rules (.cursor/rules/.mdc) — from codebase analysis.

    767 GitHub stars~1.2k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Claude Statusbar

    leeguooooo/claude-code-usage-bar

    Manage cs (claude-statusbar) — switch theme/style/density, override severity colors, preview combinations, run doctor, reset config, install, upgrade (cs upgrade — the only supported upgrade path)…

    378 GitHub stars~2.6k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Goal Prompt Builder

    win4r/goal-prompt-builder

    Build high-quality /goal commands for OpenAI Codex CLI 0.128+ that maximize audit-friendliness and minimize false-completion.

    229 GitHub stars~3.1k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • Harness 24h

    thu-nmrc/OpenHarness

    A production-grade framework for long-running, autonomous agents based on Harness Engineering principles.

    118 GitHub stars~3.6k tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check passed

More from pydantic/pydantic-ai

All 20 skills in this repo

  • Pydantic AI Harness

    pydantic/pydantic-ai

    Official

    Adds optional capabilities to Pydantic AI agents from pydantic-ai-harness, led by Code Mode, which runs many tool calls as one sandboxed Python script.

    21k GitHub stars~4.9k tokensUpdated today
    Auto-check passed

  • Building Pydantic AI Agents

    pydantic/pydantic-ai

    Official

    Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns.

    21k GitHub stars~8.2k tokensUpdated today
    Auto-check passed

  • Complete Partial PR

    pydantic/pydantic-ai

    Official

    Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point.

    21k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Testing Skill

    pydantic/pydantic-ai

    Official

    Record, rewrite, and debug VCR cassettes for HTTP recordings.

    21k GitHub stars~839 tokensUpdated today
    Auto-check: notes

  • Migrating Agno To Pydantic AI

    pydantic/pydantic-ai

    Official

    Migrate Python Agno applications to Pydantic AI and, only when needed, Pydantic AI Harness.

    21k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Deep Agents to Pydantic AI Migration

    pydantic/pydantic-ai

    Official

    Migrates Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness while preserving the application's observed behavior.

    21k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Migrating Claude Agent SDK To Pydantic AI

What does Migrating Claude Agent SDK To Pydantic AI do?

Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness. Migrating Claude Agent SDK To Pydantic AI is an agent skill from pydantic/pydantic-ai, published by the product's own GitHub organization. Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.

When should I use Migrating Claude Agent SDK To Pydantic AI?

Migrating Claude Agent SDK To Pydantic AI fits situations like: source code imports claudeagentsdk; relies on Claude Codes agent loop; the Anthropic Messages SDK; Claude Managed Agents.

How do I install Migrating Claude Agent SDK To Pydantic AI in Claude Code?

Run `npx skills add pydantic/pydantic-ai --skill migrating-claude-agent-sdk-to-pydantic-ai -a claude-code`. Or copy the skill folder (pydantic_ai_slim/pydantic_ai/.agents/skills/migrating-claude-agent-sdk-to-pydantic-ai in pydantic/pydantic-ai) into .claude/skills/migrating-claude-agent-sdk-to-pydantic-ai in your project. Claude Code loads it when a task matches its description.

How do I install Migrating Claude Agent SDK To Pydantic AI in Codex?

Run `npx skills add pydantic/pydantic-ai --skill migrating-claude-agent-sdk-to-pydantic-ai -a codex`. Or copy the skill folder (pydantic_ai_slim/pydantic_ai/.agents/skills/migrating-claude-agent-sdk-to-pydantic-ai in pydantic/pydantic-ai) into .agents/skills/migrating-claude-agent-sdk-to-pydantic-ai in your project. Codex loads it when a task matches its description.

Can I use Migrating Claude Agent SDK To Pydantic AI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pydantic/pydantic-ai --skill migrating-claude-agent-sdk-to-pydantic-ai -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/migrating-claude-agent-sdk-to-pydantic-ai, .gemini/skills/migrating-claude-agent-sdk-to-pydantic-ai, .github/skills/migrating-claude-agent-sdk-to-pydantic-ai and .opencode/skills/migrating-claude-agent-sdk-to-pydantic-ai in your project.

What does Migrating Claude Agent SDK To Pydantic AI need to run?

SKILL.md names no scripts, command-line tools or credentials: Migrating Claude Agent SDK To Pydantic AI is instructions for the agent only. Our summary lists: Python 3.

Does Migrating Claude Agent SDK To Pydantic AI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Migrating Claude Agent SDK To Pydantic AI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Migrating Claude Agent SDK To Pydantic AI use?

Migrating Claude Agent SDK To Pydantic AI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Migrating Claude Agent SDK To Pydantic AI use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Migrating Claude Agent SDK To Pydantic AI?

Skills that share tags, products or a category with Migrating Claude Agent SDK To Pydantic AI: Pydantic AI Harness (pydantic/skills, 140 stars), Agentic Development (alinaqi/maggy, 707 stars), Generate AI Rules (divar-ir/ai-doc-gen, 767 stars) and Claude Statusbar (leeguooooo/claude-code-usage-bar, 378 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Migrating Claude Agent SDK To Pydantic AI?

pydantic (a GitHub organization, an official publisher) maintains it in pydantic/pydantic-ai, which has 20,537 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 11, 2026.

Source: pydantic/pydantic-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.