CtrlK
BlogDocsLog inGet started
Tessl Logo

pydantic-ai

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/pydantic-ai/SKILL.md

The canonical home for this skill is pydantic-ai in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced guide with copy-paste-ready code throughout, slightly penalized for a monolithic structure that inlines content which could be split into reference files.

Suggestions

Split the Examples and the per-step code into reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Add explicit validation/checkpoint notes between sequential steps (e.g. verify the agent runs before adding tools).

Tighten the eight-step tutorial by merging closely related steps to reduce length.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — it does not re-explain basic concepts — though the eight numbered steps plus three full examples leave a few sections that could be trimmed.

4 / 5

Actionability

Every section provides fully executable, copy-paste-ready code covering the common cases (minimal agent, structured output, tools, dependency injection, testing, streaming, multi-turn).

5 / 5

Workflow Clarity

Steps 1–8 form a clear sequence and the Common Pitfalls section supplies feedback loops for error recovery, but the steps themselves lack explicit validation checkpoints between them.

4 / 5

Progressive Disclosure

The ~340-line body is well-sectioned with headers but is entirely monolithic — no references/, scripts/, or assets/ bundle exists, so content that could live in separate files (full API reference, example gallery) is inlined.

3 / 5

Total

16

/

20

Passed

Description

62%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific third-person description that names concrete capabilities and a distinct framework, but it omits any explicit 'Use when...' trigger guidance and leans on technical jargon over natural user phrasing.

Suggestions

Append an explicit trigger clause, e.g. 'Use when building Python AI agents with PydanticAI, or when the user mentions PydanticAI, typed/structured LLM outputs, or RunContext/ModelRetry.'

Soften technical terms with natural synonyms users actually say (e.g. add 'typed LLM responses' alongside 'structured outputs').

Confirm completeness by ensuring both 'what' and 'when' are explicit in a single sentence.

DimensionReasoningScore

Specificity

The description names the domain (PydanticAI agents) and lists several concrete capabilities — 'type-safe tool use, structured outputs, dependency injection, and multi-model support' — but stops short of fully comprehensive coverage of the framework's surface.

4 / 5

Completeness

It clearly answers 'what' (build production-ready AI agents with PydanticAI and listed features) but provides no 'Use when...' trigger clause, which caps completeness at 3 per the rubric guidance.

3 / 5

Trigger Term Quality

It surfaces relevant terms like 'AI agents', 'tool use', and 'structured outputs', but leans technical ('dependency injection', 'multi-model support') and lacks common natural variations or synonyms a user would actually say.

3 / 5

Distinctiveness Conflict Risk

Naming the specific framework 'PydanticAI' carves out a clear niche with distinct triggers and minimal conflict risk against other generic agent skills.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.