dataverse-python-quickstart
Generate Python SDK setup + CRUD + bulk + paging snippets using official patterns.
56
32%
Does it follow best practices?
Impact
100%
1.63xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/dataverse-sdk-for-python/skills/dataverse-python-quickstart/SKILL.mdQuality
Discovery
42%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description does a good job listing specific concrete actions (setup, CRUD, bulk, paging) and specifying the language (Python SDK), but it critically lacks any 'Use when...' guidance that would help Claude know when to select this skill. Additionally, it's unclear which SDK is being referenced, which reduces both trigger quality and distinctiveness.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for Python SDK code, API client setup, or needs CRUD/bulk/pagination examples.'
Specify which SDK or API platform this targets (e.g., 'Stripe Python SDK', 'AWS Boto3') to improve distinctiveness and reduce conflict with generic Python coding skills.
Include common user-facing trigger terms like 'pagination', 'API client', 'code examples', 'boilerplate', or 'REST API' that users would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'SDK setup', 'CRUD', 'bulk', 'paging snippets' and specifies 'Python' and 'official patterns'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Describes what it does (generate Python SDK snippets) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'when' is not even implied clearly, so scoring at 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Python SDK', 'CRUD', 'bulk', 'paging', 'snippets', but lacks common user variations (e.g., specific SDK names, 'API client', 'pagination', 'code examples', 'boilerplate'). Users might not naturally say 'paging snippets' or 'official patterns'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to Python SDK code generation with particular patterns (CRUD, bulk, paging), but 'Python SDK' is broad and could overlap with general Python coding skills or API-related skills. Without naming a specific SDK, it could conflict with multiple skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a high-level prompt rather than an actionable skill document. It lacks any concrete code examples, specific method signatures, or executable snippets for the Dataverse Python SDK, which is critical given that this is a preview library Claude may have limited training data on. The content describes what to generate but provides none of the actual patterns needed to do so correctly.
Suggestions
Add complete, executable Python code examples for each operation (client setup, CRUD, bulk, paging) since this is a preview SDK that Claude may not know well.
Include specific method signatures and parameter names from the official SDK (e.g., client.create, client.update, client.retrieve_multiple) so Claude can generate accurate code.
Add a validation step or expected output format so Claude can verify generated snippets are correct (e.g., expected response structure, error handling patterns).
Reference official documentation URLs or include an API reference section for the preview SDK's current capabilities and known limitations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary framing ('You are assisting with...') and descriptive bullet points that tell Claude what to do rather than showing it. The phrase 'Keep code aligned with official examples' is vague filler. | 2 / 3 |
Actionability | The skill provides no executable code, no concrete examples, no specific API calls or method signatures. It only describes what kinds of snippets to generate without showing any actual patterns, commands, or copy-paste ready code. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow, no validation steps, and no clear process to follow. The bullet points list topics but don't define an order of operations or any checkpoints for verifying correctness. | 1 / 3 |
Progressive Disclosure | The content is short and organized as a simple bullet list, which is acceptable for a brief skill. However, it lacks any references to external documentation, examples files, or API references that would help Claude produce accurate output for this preview SDK. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- github/awesome-copilot
- Commit
4020587
- 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.