pydantic-models
Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2.
Install with Tessl CLI
npx tessl i github:microsoft/agent-skills --skill pydantic-modelsOverall
score
92%
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels across all dimensions. It clearly specifies the concrete pattern being implemented (multi-model with named variants), includes natural trigger terms users would use when needing this functionality, and explicitly states both what the skill does and when to use it. The specificity to Pydantic v2 and the named model variants makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants.' This clearly describes the specific model variants and pattern being implemented. | 3 / 3 |
Completeness | Clearly answers both what ('Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants') and when ('Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Pydantic models', 'API request/response schemas', 'database models', 'data validation', 'Python', 'Pydantic v2'. These cover common variations of how users would describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche targeting Pydantic v2 multi-model patterns with named variants (Base, Create, Update, Response, InDB). Unlikely to conflict with general Python or data validation skills due to the specific pattern and technology focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
88%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that efficiently communicates the multi-model Pydantic pattern with concrete, executable examples. The table summarizing model purposes is particularly effective. The main weakness is the integration steps lack validation guidance—there's no checkpoint to verify models work correctly before proceeding.
Suggestions
Add a validation step to the Integration Steps, such as 'Test models with sample data before integrating' or include a quick validation snippet
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude understands Pydantic and Python. No unnecessary explanations of what Pydantic is or how models work—just the pattern and examples. | 3 / 3 |
Actionability | Provides executable code snippets for each model variant, a clear template reference, and specific integration steps. The examples are copy-paste ready with real field definitions. | 3 / 3 |
Workflow Clarity | Integration steps are listed but lack validation checkpoints. For a pattern involving database models and API contracts, there's no mention of testing the models or validating the schema works correctly before deployment. | 2 / 3 |
Progressive Disclosure | Excellent structure with a quick start pointing to a template file, a clear table summarizing the pattern, and focused inline examples. Content is appropriately split with one-level-deep reference to the template. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 13 / 16 Passed | |
- 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.