contoso-migration-test
**WORKFLOW SKILL** — Execute end-to-end ContosoUniversity migration benchmark: clear output folder, run L1 script + L2 Copilot transforms, build, run Playwright acceptance tests, and generate a numbered run report. WHEN: "run contoso migration test", "test contoso university migration", "contoso migration benchmark", "run CU migration". INVOKES: bwfc-migrate.ps1, bwfc-migration skill, bwfc-data-migration skill, bwfc-identity-migration skill, migration-standards skill, dotnet CLI, Playwright tests.
92
88%
Does it follow best practices?
Impact
100%
3.03xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 an excellent skill description that clearly defines a specific workflow with concrete steps, explicit trigger phrases, and dependency information. It uses third person voice appropriately and provides enough detail to distinguish it from the sub-skills it invokes. The description is comprehensive without being unnecessarily verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: clear output folder, run L1 script + L2 Copilot transforms, build, run Playwright acceptance tests, and generate a numbered run report. Also names specific tools and scripts invoked. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute end-to-end migration benchmark with specific steps) and 'when' (explicit WHEN clause with four trigger phrases). Also lists invoked dependencies for additional context. | 3 / 3 |
Trigger Term Quality | Includes multiple natural trigger phrases users would actually say: 'run contoso migration test', 'test contoso university migration', 'contoso migration benchmark', 'run CU migration'. These cover common variations including the abbreviation 'CU'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very specific niche: ContosoUniversity migration benchmark workflow. The trigger terms are project-specific and unlikely to conflict with other skills. It also clarifies its relationship to sub-skills it invokes. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 workflow skill with strong actionability and clear multi-phase sequencing including validation checkpoints. The main weakness is moderate verbosity in Phase 2 where transform details are inlined despite referencing the skills that already contain those instructions. The critical rules table is an excellent addition that captures domain-specific gotchas concisely.
Suggestions
Trim Phase 2 'Key transforms to execute' section — those details live in the referenced migration skills and duplicating them here wastes tokens and risks drift
Remove 'Expected duration' annotations unless they serve as timeout thresholds for automated tooling
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and well-structured with tables and clear phases, but includes some unnecessary detail that Claude could infer (e.g., 'Expected duration' estimates, explaining what each migration skill does when Claude would load those skills anyway). The Phase 2 skill responsibility table is borderline redundant since Claude would read those skills directly. | 2 / 3 |
Actionability | Provides fully executable PowerShell commands, specific dotnet CLI invocations, exact environment variable settings, concrete connection strings, and precise file paths. The workflow is copy-paste ready with specific commands for each phase. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with clear sequencing (Phase 0-5), explicit validation checkpoints (Phase 3 build validation with iterative fix loop, Phase 4 acceptance tests with pass/fail recording), and a feedback loop for compilation errors. The L1→L2 handoff rule and 'report every run' rule ensure error recovery is documented. | 3 / 3 |
Progressive Disclosure | References REPORT-TEMPLATE.md and the four migration skills appropriately, but the Phase 2 content inlines substantial detail about key transforms that could be deferred to the referenced skills. The bundle has no files to verify references against, and only one external reference (REPORT-TEMPLATE.md) is provided despite mentioning 4 skills and multiple paths. | 2 / 3 |
Total | 10 / 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
- FritzAndFriends/BlazorWebFormsComponents
- Commit
147d0c4
- 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.