setup-datamodel
This skill should be used when the user asks to "create Dataverse tables", "set up the data model", "setup dataverse", "create tables for my site", "setup dataverse schema", "create the database", "build my data model", or wants to create Dataverse tables, columns, and relationships for their Power Pages site based on a data model proposal.
88
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 solid skill description with excellent trigger term coverage and clear 'when to use' guidance. Its main weakness is that the capability description could be more specific about what concrete actions are performed beyond creating tables, columns, and relationships. The description is somewhat front-loaded with trigger phrases, which while functional, could be better organized.
Suggestions
Add more specific concrete actions beyond 'create' — e.g., 'Generates Dataverse table definitions, configures column types and constraints, establishes entity relationships, and produces deployment scripts for Power Pages data models.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'create Dataverse tables, columns, and relationships' which names the domain and some actions, but doesn't list comprehensive specific actions beyond creation (e.g., no mention of configuring permissions, setting data types, defining constraints, etc.). | 2 / 3 |
Completeness | The description explicitly answers both 'what' (create Dataverse tables, columns, and relationships for Power Pages sites based on a data model proposal) and 'when' (with extensive explicit trigger phrases listed at the beginning). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create Dataverse tables', 'set up the data model', 'setup dataverse', 'create tables for my site', 'setup dataverse schema', 'create the database', 'build my data model'. These are varied and natural phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Dataverse tables for Power Pages sites. The combination of 'Dataverse', 'Power Pages', and 'data model proposal' makes this highly distinctive and unlikely to conflict with generic database or table creation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%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-structured, highly actionable skill for a complex multi-phase workflow. It excels at workflow clarity with explicit validation checkpoints, user approval gates, and error handling guidance. The progressive disclosure is excellent, keeping the main skill as an orchestration overview while delegating detailed API patterns and schemas to reference files. The main weakness is moderate verbosity — some information is repeated across phases and the 'Important Notes' section, and the progress tracking table could be more compact.
Suggestions
Remove the 'Important Notes' section or significantly trim it, as most of its content (token refresh, failure handling, decision points) is already stated in the individual phases where it's relevant.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300+ lines) but most content is necessary for the complex 8-phase workflow. However, there's some redundancy — token refresh is mentioned multiple times, the progress tracking table is somewhat verbose, and some descriptions repeat what's already clear from the phase structure. The 'Important Notes' section at the end largely restates things already covered in individual phases. | 2 / 3 |
Actionability | The skill provides concrete, executable commands throughout (specific node script invocations with exact API paths, JSON body references, PAC CLI commands). Each phase has clear actions with specific tool calls, API endpoints, and expected outputs. The manifest JSON example is copy-paste ready, and the summary table format is well-specified. | 3 / 3 |
Workflow Clarity | The 8-phase workflow is clearly sequenced with explicit validation checkpoints: pre-creation checks in Phase 5 verify existing tables before creating, Phase 8 includes publish-then-verify steps, and there are 4 explicit user decision points listed. The skill includes error handling guidance (report failures without rollback, check for 404 vs 200 responses) and a clear branching path in Phase 2. | 3 / 3 |
Progressive Disclosure | The skill effectively references external files for detailed content: `references/odata-api-patterns.md` for JSON body templates, `references/dataverse-prerequisites.md` for prerequisite steps, `agents/data-model-architect.md` for agent definition, and `references/datamodel-manifest-schema.md` for the manifest schema. All references are one level deep and clearly signaled with descriptive context. | 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 — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- microsoft/power-platform-skills
- Commit
66a61c6
- 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.