Menu

Not in the top 1,000 by GitHub stars

DougTrajano/pydantic-ai-skills

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

Claude CodeCodexEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

examples/skills/arxiv-search/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → f80614610e86

No earlier version was observed for comparison.

Compare on GitHub

examples/skills/data-analysis/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → f80614610e86

No earlier version was observed for comparison.

Compare on GitHub

examples/skills/pydanticai-docs/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → f80614610e86

No earlier version was observed for comparison.

Compare on GitHub

examples/skills/web-research/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → f80614610e86

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit f80614610e86463fb05ab10daad9a417c4d5b096

git clone --filter=blob:none --no-checkout https://github.com/DougTrajano/pydantic-ai-skills.git .hotskills/dougtrajano-pydantic-ai-skills && git -C .hotskills/dougtrajano-pydantic-ai-skills checkout --detach f80614610e86463fb05ab10daad9a417c4d5b096 # Copy each selected skill directory from .hotskills/dougtrajano-pydantic-ai-skills into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/DougTrajano/pydantic-ai-skills.git .hotskills/dougtrajano-pydantic-ai-skills && git -C .hotskills/dougtrajano-pydantic-ai-skills checkout --detach f80614610e86463fb05ab10daad9a417c4d5b096 # Copy each selected skill directory from .hotskills/dougtrajano-pydantic-ai-skills into .agents/skills/<skill-name>/
381GitHub stars
0stars in 7 days
4skills in this repository
15commits in 30 days

Heat

1.6
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 2026381

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

arxiv-search

When your agent uses it

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields.

What it loads into context

Frontmatter

48 tokens

Always available to the agent

SKILL.md

374 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. When to Use This Skill
  2. Skill Scripts
  3. Output Format
  4. Dependencies

Scripts executed separately

  • scripts/arxiv_search.py

Files

  • SKILL.mdcore1,788 bytes
  • scripts/arxiv_search.pyruns1,829 bytes
Read SKILL.md

# arXiv Search Skill

This skill provides access to arXiv, a free distribution service and open-access archive for scholarly articles in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, systems science, and economics.

## When to Use This Skill

Use this skill when you need to:

- Find preprints and recent research papers before journal publication
- Search for papers in computational biology, bioinformatics, or systems biology
- Access mathematical or statistical methods papers relevant to biology
- Find machine learning papers applied to biological problems
- Get the latest research that may not yet be in PubMed
View the complete source on GitHub

Skills included

  • arxiv-search
  • data-analysis
  • pydanticai-docs
  • web-research

Repository facts

License
MIT
Created
Dec 18, 2025
Last pushed
Nov 6, 2026
Forks
29
Open issues
0
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes
  • examples/skills/pydanticai-docs/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • examples/skills/pydanticai-docs/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • examples/skills/pydanticai-docs/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • examples/skills/pydanticai-docs/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 63 signals by file

examples/skills/arxiv-search/scripts/arxiv_search.py

  • Executable scriptline 1
    #!/usr/bin/env python3

examples/skills/data-analysis/scripts/aggregate.py

  • Executable scriptline 1
    #!/usr/bin/env python3

examples/skills/data-analysis/scripts/profile_dataset.py

  • Executable scriptline 1
    #!/usr/bin/env python3

examples/skills/pydanticai-docs/SKILL.md

  • Network accessline 16
    Doc: <https://ai.pydantic.dev/>
  • Access to secretsline 62
    [Credential-related source omitted]
  • Network accessline 97
    | Topic | Reference file | Doc link | |---|---|---| | Message history / multi-turn conversations | `references/MESSAGES.md` | <https://ai.pydantic.dev/core-concepts/message-history/index.md> |
  • Network accessline 98
    |---|---|---| | Message history / multi-turn conversations | `references/MESSAGES.md` | <https://ai.pydantic.dev/core-concepts/message-history/index.md> | | Model / provider setup (all providers) | `references/MODELS.md` | <https://ai.pydan
  • Network accessline 99
    | Message history / multi-turn conversations | `references/MESSAGES.md` | <https://ai.pydantic.dev/core-concepts/message-history/index.md> |
  • Network accessline 100
    | Model / provider setup (all providers) | `references/MODELS.md` | <https://ai.pydantic.dev/models/overview/index.md> |
  • Network accessline 101
    | Toolsets (`FunctionToolset`, composition) | `references/TOOLS_AND_TOOLSETS.md` | <https://ai.pydantic.dev/tools-toolsets/toolsets/index.md> |
  • Network accessline 102
    | MCP server integration | `references/MCP.md` | <https://ai.pydantic.dev/mcp/client/index.md> |
  • Network accessline 103
    | Multi-agent applications | doc link only | <https://ai.pydantic.dev/guides/multi-agent-applications/index.md> |
  • Network accessline 104
    | Graphs (pydantic-graph) | doc link only | <https://ai.pydantic.dev/graph/graph/index.md> |
  • Network accessline 105
    | Evals (pydantic-evals) | doc link only | <https://ai.pydantic.dev/evals/evals/index.md> |
  • Network accessline 106
    | Durable execution | doc link only | <https://ai.pydantic.dev/durable_execution/overview/index.md> |
  • Network accessline 107
    | Retries | doc link only | <https://ai.pydantic.dev/core-concepts/retries/index.md> |
  • Network accessline 108
    | Testing (`TestModel`, `override`) | doc link only | <https://ai.pydantic.dev/guides/testing/index.md> |
  • Network accessline 109
    | Logfire integration | doc link only | <https://ai.pydantic.dev/integrations/logfire/index.md> |
  • Network accessline 110
    | Native tools (formerly builtin tools) | doc link only | <https://ai.pydantic.dev/tools-toolsets/native-tools/index.md> |
  • Network accessline 111
    | Streaming | doc link only | <https://ai.pydantic.dev/core-concepts/agent/index.md> |

examples/skills/pydanticai-docs/references/AGENT.md

  • Network accessline 69
    <https://ai.pydantic.dev/core-concepts/agent/index.md>
  • Network accessline 70
    <https://ai.pydantic.dev/api/agent/index.md>

examples/skills/pydanticai-docs/references/DEPENDENCIES.md

  • Access to secretsline 22
    [Credential-related source omitted]
  • Access to secretsline 29
    [Credential-related source omitted]
  • Network accessline 36
    async def main():     async with httpx.AsyncClient() as client:
  • Network accessline 37
    async with httpx.AsyncClient() as client:
  • Access to secretsline 38
    [Credential-related source omitted]
  • Network accessline 62
    <https://ai.pydantic.dev/core-concepts/dependencies/index.md>

examples/skills/pydanticai-docs/references/FUNCTION_TOOLS.md

  • Network accessline 66
    <https://ai.pydantic.dev/tools-toolsets/tools/index.md>
  • Network accessline 67
    <https://ai.pydantic.dev/tools-toolsets/tools-advanced/index.md>

examples/skills/pydanticai-docs/references/MCP.md

  • Network accessline 27
    server = MCPServerStreamableHTTP('http://localhost:8000/mcp')
  • Network accessline 55
    weather = MCPServerStreamableHTTP('http://localhost:3001/mcp', tool_prefix='weather')
  • Network accessline 56
    calc = MCPServerStreamableHTTP('http://localhost:3002/mcp', tool_prefix='calc')
  • Network accessline 75
    - Client guide: <https://ai.pydantic.dev/mcp/client/index.md>
  • Network accessline 76
    - Overview: <https://ai.pydantic.dev/mcp/overview/index.md>
  • Network accessline 77
    - API reference: <https://ai.pydantic.dev/api/mcp/index.md>

examples/skills/pydanticai-docs/references/MESSAGES.md

  • Network accessline 68
    <https://ai.pydantic.dev/core-concepts/message-history/index.md>
  • Network accessline 69
    <https://ai.pydantic.dev/api/messages/index.md>

examples/skills/pydanticai-docs/references/MODELS.md

  • Access to secretsline 9
    [Credential-related source omitted]
  • Access to secretsline 10
    [Credential-related source omitted]
  • Access to secretsline 11
    [Credential-related source omitted]
  • Access to secretsline 12
    [Credential-related source omitted]
  • Access to secretsline 13
    [Credential-related source omitted]
  • Access to secretsline 14
    [Credential-related source omitted]
  • Access to secretsline 15
    [Credential-related source omitted]
  • Access to secretsline 16
    [Credential-related source omitted]
  • Access to secretsline 18
    [Credential-related source omitted]
  • Access to secretsline 21
    [Credential-related source omitted]
  • Access to secretsline 38
    [Credential-related source omitted]
  • Access to secretsline 41
    [Credential-related source omitted]
  • Access to secretsline 44
    [Credential-related source omitted]
  • Network accessline 66
    - Overview: <https://ai.pydantic.dev/models/overview/index.md>
  • Network accessline 67
    - OpenAI: <https://ai.pydantic.dev/models/openai/index.md>
  • Network accessline 68
    - Anthropic: <https://ai.pydantic.dev/models/anthropic/index.md>
  • Network accessline 69
    - Google: <https://ai.pydantic.dev/models/google/index.md>
  • Network accessline 70
    - Groq: <https://ai.pydantic.dev/models/groq/index.md>
  • Network accessline 71
    - Mistral: <https://ai.pydantic.dev/models/mistral/index.md>
  • Network accessline 72
    - Bedrock: <https://ai.pydantic.dev/models/bedrock/index.md>
  • Network accessline 73
    - OpenRouter: <https://ai.pydantic.dev/models/openrouter/index.md>

examples/skills/pydanticai-docs/references/OUTPUT.md

  • Network accessline 51
    <https://ai.pydantic.dev/core-concepts/output/index.md>
  • Network accessline 52
    <https://ai.pydantic.dev/api/output/index.md>

examples/skills/pydanticai-docs/references/TOOLS_AND_TOOLSETS.md

  • Network accessline 67
    <https://ai.pydantic.dev/tools-toolsets/toolsets/index.md>
  • Network accessline 68
    <https://ai.pydantic.dev/api/toolsets/index.md>

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 63 facts

and 13 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativePath .claude/commands/upstream-watch.md.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md examples/skills/arxiv-search/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md examples/skills/arxiv-search/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md examples/skills/arxiv-search/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md examples/skills/arxiv-search/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

Fuenfgeld/pydantic-ai-skills

Production-ready Claude Code skills for building AI agents with Pydantic AI. Includes dependency injection, tools, validators, streaming, multi-agent orchestration, and evaluation…

10GitHub stars

KKKKhazix/khazix-skills

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

22kGitHub stars

Leonxlnx/taste-skill

tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals rese…

111.3kGitHub stars

coreyhaines31/marketingskills

Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

59kGitHub stars

wshobson/agents

Plugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and adapted to each tool by g…

42.3kGitHub stars

NVIDIA/skills

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

3.9kGitHub stars