dataverse-python-usecase-builder
Generate complete solutions for specific Dataverse SDK use cases with architecture recommendations
54
30%
Does it follow best practices?
Impact
98%
2.39xAverage 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-usecase-builder/SKILL.mdQuality
Discovery
32%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 identifies a specific technology domain (Dataverse SDK) but is otherwise vague, lacking concrete actions, natural trigger terms, and any explicit 'Use when...' guidance. It reads more like a tagline than a functional description that would help Claude reliably select this skill from a large pool.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about Dataverse, Dynamics 365 plugins, Power Platform SDK, or Microsoft CRM development.'
List specific concrete actions such as 'create plugins, configure custom entities, implement CRUD operations, build workflows using the Dataverse SDK'.
Include natural keyword variations users might say: 'Dynamics 365', 'Power Platform', 'CRM SDK', 'Microsoft Dataverse', 'plugin registration', '.NET SDK for Dataverse'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Dataverse SDK) and a general action (generate complete solutions), but 'architecture recommendations' and 'specific use cases' are vague—it doesn't list concrete actions like 'create plugins, configure entities, build custom workflows'. | 2 / 3 |
Completeness | It describes a vague 'what' (generate solutions with architecture recommendations) but completely lacks a 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Dataverse SDK' which is a relevant keyword, but misses natural user terms like 'Dynamics 365', 'Power Platform', 'CRM', 'plugin', 'entity', or 'Microsoft Dataverse'. Users may not always say 'Dataverse SDK' specifically. | 2 / 3 |
Distinctiveness Conflict Risk | 'Dataverse SDK' provides some specificity that distinguishes it from generic coding skills, but 'generate complete solutions' and 'architecture recommendations' are broad enough to overlap with general software architecture or solution design skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-engineered and verbose, reading more like a general architecture guide than a focused skill for Claude. It explains many concepts Claude already knows (CRUD, ETL, singleton pattern, PEP 8), lists taxonomies without actionable guidance, and provides skeleton code rather than executable examples. The content would benefit greatly from being condensed to essential patterns and split into referenced sub-files.
Suggestions
Cut the 'Use Case Categories' section entirely—it's pure taxonomy that Claude can infer. Cut the 'Quality Checklist' as it restates standard practices Claude already follows.
Replace the skeleton implementation template (Phase 4) with 2-3 complete, executable examples for the most common patterns (e.g., a working transactional CRUD example and a working batch processing example).
Split detailed pattern implementations into separate referenced files (e.g., PATTERNS.md, EXAMPLES.md) and keep SKILL.md as a concise overview with navigation links.
Add explicit validation/verification steps in the workflow, especially for batch operations and data migration patterns (e.g., 'validate record count after bulk insert', 'verify relationship integrity').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~200+ lines. Explains concepts Claude already knows (what CRUD is, what ETL means, basic Python patterns like singletons). The use case categories section is pure taxonomy that adds no actionable value. The quality checklist restates standard coding practices Claude already follows. Much of this could be cut by 60-70%. | 1 / 3 |
Actionability | Contains some concrete code snippets (batch operations, file uploads, query patterns) but much of the code is template/skeleton with placeholder comments like '# Methods here' and 'pass'. The Phase 4 implementation template is not executable—it's a structural outline. The data model design example is illustrative but not copy-paste ready. | 2 / 3 |
Workflow Clarity | The 5-phase framework provides a clear sequence (Requirement Analysis → Data Model → Pattern Selection → Implementation → Optimization), but there are no validation checkpoints or feedback loops. For a skill involving data operations and bulk processing, the absence of explicit verify/retry steps between phases is a significant gap. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the content being long enough to warrant splitting. The use case categories, pattern details, and implementation templates could each be separate referenced files. No bundle files exist to support this, and no navigation structure is provided. | 1 / 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
07b34ec
- 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.