Skip to content
Back to search

pydantic-skills

MarketplaceWorks with Claude CodeGitHub

Official Pydantic plugins for Logfire, Pydantic AI, and Pydantic.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pydantic-skills/badge.svg)](/listings/pydantic-skills)

HTML

<a href="/listings/pydantic-skills"><img src="/api/listings/pydantic-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Add this marketplace to Claude Code:

claude plugin marketplace add pydantic/skills

Then install a plugin:

claude plugin install logfire@pydantic-skills
claude plugin install ai@pydantic-skills
claude plugin install pydantic-ai-harness@pydantic-skills
claude plugin install pydantic@pydantic-skills

For Logfire, run `/logfire:connect` inside Claude Code to authenticate MCP and optionally configure native Claude telemetry. `/logfire:status` checks the two connections separately; `/logfire:disconnect` stops session capture without removing MCP or skills. See the [connection and capture requirements](plugins/logfire/#connect-once).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 59 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "pydantic-skills",
  4. "description": "Official Pydantic plugins for Logfire, Pydantic AI, and Pydantic.",
  5. "owner": {
  6. "name": "Pydantic",
  7. "email": "support@pydantic.dev"
  8. },
  9. "plugins": [
  10. {
  11. "name": "logfire",
  12. "description": "Instrument applications and infrastructure, investigate telemetry, and manage Pydantic Logfire workflows across Python, TypeScript, Rust, or any language.",
  13. "version": "0.1.7",
  14. "author": {
  15. "name": "Pydantic",
  16. "email": "support@pydantic.dev"
  17. },
  18. "source": "./plugins/logfire",
  19. "category": "monitoring",
  20. "homepage": "https://pydantic.dev/docs/logfire/guides/skills/"
  21. },
  22. {
  23. "name": "ai",
  24. "description": "Build production-grade AI agents with Pydantic AI — tools, capabilities, structured output, streaming, and testing patterns — and port existing agents over from LangChain, the OpenAI Agents SDK, Google ADK, Mastra, Agno, Pi, the Claude Agent SDK, and the Vercel AI SDK",
  25. "version": "0.1.0",
  26. "author": {
  27. "name": "Pydantic",
  28. "email": "support@pydantic.dev"
  29. },
  30. "source": "./plugins/ai",
  31. "category": "development",
  32. "homepage": "https://pydantic.dev/docs/ai/overview/coding-agent-skills/"
  33. },
  34. {
  35. "name": "pydantic-ai-harness",
  36. "description": "Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness — coding agents and sandboxed workspaces, Code Mode, sub-agents and planning, memory, context management, and guardrails — and port LangChain Deep Agents applications over to the harness",
  37. "version": "0.1.0",
  38. "author": {
  39. "name": "Pydantic",
  40. "email": "support@pydantic.dev"
  41. },
  42. "source": "./plugins/pydantic-ai-harness",
  43. "category": "development",
  44. "homepage": "https://pydantic.dev/docs/ai/harness/"
  45. },
  46. {
  47. "name": "pydantic",
  48. "description": "Validate and serialize data with Pydantic — modeling patterns, constraints, custom validators, coercion, and discriminated unions",
  49. "version": "0.1.0",
  50. "author": {
  51. "name": "Pydantic",
  52. "email": "support@pydantic.dev"
  53. },
  54. "source": "./plugins/pydantic",
  55. "category": "development",
  56. "homepage": "https://pydantic.dev/docs/validation/latest/get-started/"
  57. }
  58. ]
  59. }
README.md · README · 105 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Pydantic Skills
  2. Logfire, Pydantic AI, and Pydantic plugins for [Claude Code](https://claude.com/claude-code), [Codex](https://openai.com/codex), and [Cursor](https://cursor.com). Instrument your code with Logfire, query and export the resulting telemetry, build LLM agents with Pydantic AI, and validate data with Pydantic.
  3. ## Plugins
  4. | Plugin | Hosts | Description | Capabilities |
  5. | --------------------------------------------- | -------------------------- | --------------------------------------------------- | ------------------------------------------------------------------------------------ |
  6. | [logfire](plugins/logfire/) | Claude Code, Codex, Cursor | Add Logfire observability and query/debug telemetry | Claude commands `/instrument`, `/debug`, `/query`; Codex/Cursor skills and MCP tools |
  7. | [logfire-exporter](plugins/logfire-exporter/) | Codex | Export Codex activity traces to Logfire | Codex lifecycle hooks |
  8. | [ai](plugins/ai/) | Claude Code | Build AI agents with Pydantic AI | Pydantic AI skill docs |
  9. | [pydantic-ai-harness](plugins/pydantic-ai-harness/) | Claude Code | Extend Pydantic AI agents with harness capabilities | Pydantic AI Harness skill docs |
  10. | [pydantic](plugins/pydantic/) | Claude Code | Validate and serialize data with Pydantic | Pydantic skill docs |
  11. ## Install In Claude Code
  12. Add this marketplace to Claude Code:
  13. ```
  14. claude plugin marketplace add pydantic/skills
  15. ```
  16. Then install a plugin:
  17. ```
  18. claude plugin install logfire@pydantic-skills
  19. claude plugin install ai@pydantic-skills
  20. claude plugin install pydantic-ai-harness@pydantic-skills
  21. claude plugin install pydantic@pydantic-skills
  22. ```
  23. For Logfire, run `/logfire:connect` inside Claude Code to authenticate MCP and
  24. optionally configure native Claude telemetry. `/logfire:status` checks the two
  25. connections separately; `/logfire:disconnect` stops session capture without
  26. removing MCP or skills. See the [connection and capture requirements](plugins/logfire/#connect-once).
  27. ## Install In Codex
  28. Add the published Pydantic marketplace to Codex:
  29. ```bash
  30. codex plugin marketplace add pydantic/skills
  31. ```
  32. Then open Codex's plugin UI and enable the plugins you want from the **Pydantic** marketplace:
  33. - **Logfire** - installs Logfire skills and the hosted Logfire MCP server.
  34. - **Logfire Exporter** - installs Codex lifecycle hooks that export completed Codex turns and tool calls to Logfire.
  35. Configure **Logfire Exporter** with a Logfire write token in your environment or
  36. `${XDG_CONFIG_HOME:-~/.config}/logfire-exporter/config.env`. Restart Codex after configuration, and run `/hooks` if
  37. Codex asks you to review or trust the new hooks.
  38. To use the EU Logfire MCP endpoint in Codex without editing plugin files, replace the MCP entry and re-authenticate:
  39. ```bash
  40. codex mcp remove logfire
  41. codex mcp add logfire --url https://logfire-eu.pydantic.dev/mcp
  42. codex mcp login logfire
  43. codex mcp get logfire
  44. ```
  45. Start a new Codex conversation after switching so the MCP tools reload.
  46. ## Install In Cursor
  47. Install the Logfire plugin from the published [pydantic/skills](https://github.com/pydantic/skills) repository:
  48. ```bash
  49. git clone https://github.com/pydantic/skills.git
  50. mkdir -p ~/.cursor/plugins/local
  51. cp -R skills/plugins/logfire ~/.cursor/plugins/local/logfire
  52. ```
  53. Then restart Cursor or run **Developer: Reload Window**. The plugin configures:
  54. - display name **Logfire**
  55. - Logfire skills for instrumentation, querying, and UI-opening workflows
  56. - hosted Logfire MCP server from `mcp.json`
  57. The Logfire MCP server requires normal Logfire authentication, such as `logfire auth` or a suitable `LOGFIRE_TOKEN`.
  58. ## Cross-Agent Skills
  59. The `skills/` directory contains standalone SKILL.md files compatible with 30+ agents via the [agentskills.io](https://agentskills.io) standard - including Codex, Cursor, Gemini CLI, and Claude Code.
  60. Released skills are also published through the [Agent Skills Discovery](https://github.com/cloudflare/agent-skills-discovery-rfc) API at
  61. [`pydantic.dev/.well-known/agent-skills`](https://pydantic.dev/.well-known/agent-skills). After a change reaches `main` and passes this repository's sync check, CI asks
  62. `pydantic/unified-docs` to build and verify immutable, content-addressed artifacts from that exact commit. The generated discovery index and archives are deployment
  63. artifacts; do not maintain copies in this repository.
  64. | Skill | Description |
  65. | ------------------------------------------------------------------ | ----------------------------------------------------------------------------------- |
  66. | [logfire-setup](skills/logfire-setup/) | Set up Logfire by routing application, infrastructure, and eval projects |
  67. | [logfire-instrumentation](skills/logfire-instrumentation/) | Add Logfire observability to Python, JS/TS, and Rust apps |
  68. | [logfire-infrastructure](skills/logfire-infrastructure/) | Monitor hosts, containers, Kubernetes, databases, and cloud infrastructure |
  69. | [logfire-evals](skills/logfire-evals/) | Add dataset-based evaluations for AI and agent behavior |
  70. | [logfire-query](skills/logfire-query/) | Query and analyze Logfire traces, logs, spans, metrics, and activity data |
  71. | [logfire-ui](skills/logfire-ui/) | Open Logfire project pages, live views, traces, and Explore filters |
  72. | [logfire-coding-agents](skills/logfire-coding-agents/) | Record Claude/Codex sessions or configure coding-agent Gateway routing |
  73. | [logfire-frontend](skills/logfire-frontend/) | Browser errors, Web Vitals, and session replays |
  74. | [logfire-gateway](skills/logfire-gateway/) | Route application model calls through Pydantic AI Gateway |
  75. | [building-pydantic-ai-agents](skills/building-pydantic-ai-agents/) | Build LLM-powered agents with Pydantic AI — tools, capabilities, streaming, testing |
  76. | [pydantic-ai-harness](skills/pydantic-ai-harness/) | Extend Pydantic AI agents with harness capabilities: coding agents, Code Mode, sub-agents, memory |
  77. | [pydantic](skills/pydantic/) | Validate and serialize data with Pydantic models, constraints, and custom validators |

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.