A Skill-Mediated LLM Workflow for Migrating a.NET Monolith to Cloud-Deployed Microservices: a Controlled Case Study

Migrating a monolithic application to cloud-deployed microservices requires orchestrating a full sequence of dependent steps - decomposition, testing, review, and deployment - that current LLM-based coding assistants support only in isolation. We report a controlled, multi-case study of one composition pattern addressing this gap: ten Claude Code skills chained into a single end-to-end workflow for migrating.NET monoliths, evaluated on PetRescue (primary case) and Microsoft’s eShopOnWeb (transfer case, scored against the active dotnet/eShop reference). On PetRescue, nine of ten attempted skill-mediated runs completed, scoring 12.11 of 20 (60.6%, $\sigma =3.9\%$ ) on a pre-registered twenty-dimension structural rubric; the tenth exhibited a skill-invocation failure. A raw LLM with a fully-specified prompt scored 14.80 of 20 (74.0%, $\sigma =3.2\%$ ). All scores measure agreement with one independently-engineered expert reference, not absolute migration quality. Under a matched-specificity baseline with a deliberately vague one-sentence prompt, four of five attempted runs completed, scoring 12.75 of 20 (63.8%, $\sigma =2.5\%$ ); the fifth exited prematurely. We detected no significant difference between the skill-mediated and matched-specificity conditions ( $t=-1.77$ , $p \approx 0.11$ ; $N=9$ and $N=4$ successful runs). The 13.4-percentage-point skill-vs-baseline gap therefore decomposes into a significant 10.3-point prompt-specificity effect ( $t=-6.40$ , $p\lt 0.001$ ) and a 3.2-point skill-abstraction effect that does not reach significance at $\alpha =0.05$ . The transfer case reproduces the gap (−13.3 vs. −13.4 points) on a substantially different codebase. The workflow’s automated security check shows perfect recall (10/10) but 52.6% precision and 10% specificity on a matched 20-file corpus, consistent with automated DevOps hygiene rather than formal security validation. The two short-prompt conditions fail in qualitatively distinct ways (skill-invocation vs. premature exit). The contribution is not higher single-shot LLM output but reproducible workflow engineering: auditable SDLC orchestration, artefact-mediated state, mechanical pre-commit gating, and lower prompt-engineering burden. We publish skill scripts, both codebases, run logs, scoring code, the verifier changelog, and the injection corpus through GitHub and Zenodo.