CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-cloud-migrate

Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud Run migration, Fargate to ACA, ECS/Kubernetes/GKE/EKS to Container Apps, Spring Boot to Container Apps, cross-cloud migration.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary router skill: lean, concrete, and well-sequenced, with a scenario table that maps cleanly onto a verified bundle of per-service reference files. The only gap is the absence of an explicit post-migration verification checkpoint before completion is reported.

Suggestions

Add an explicit validation checkpoint in the Steps section (e.g., after Migrate: verify the converted output builds/passes a basic smoke check before reporting 'Migration complete') to close the workflow_clarity gap.

Add a brief error-recovery loop for the assessment phase (what to do when a source service has no clear Azure mapping) so checkpoints guide recovery as well as progression.

DimensionReasoningScore

Conciseness

The ~43-line body is a lean router: rules, a compact scenario table, output convention, and five steps — no concept explanations and no padding. Every rule (e.g., Kubernetes DNS names in HTTP clients not resolving in Container Apps) carries non-obvious information; not 4 because nothing is trimmable without losing substance.

5 / 5

Actionability

Concrete, executable guidance throughout: exact MCP tool names ('mcp_azure_mcp_get_azure_bestpractices', 'mcp_azure_mcp_documentation'), an exact output-directory convention with its definition, a per-scenario reference table with real file paths, and a copy-ready user prompt ('Migration complete. Test locally or deploy to Azure?'). Not 4 because there are no gaps for its router role — absence of inline code is appropriate since detail is delegated to reference files.

5 / 5

Workflow Clarity

Five clearly sequenced steps with explicit gates: 'Follow phases sequentially — do not skip', assessment required before migration, 'Destructive actions require ask_user', and a progress-reporting rule with status tracking in migration-status.md. Not 5 because there is no explicit verification step (e.g., confirm migrated output compiles/passes a smoke check) before declaring 'Migration complete'; not 3 because checkpoints are explicit rather than implicit, and the workflow is non-destructive by design ('Never modify the source directory', output to a separate directory), so the missing-validation cap does not apply.

4 / 5

Progressive Disclosure

A clean overview that keeps rules and steps inline and pushes all detail to well-signaled, one-level-deep reference files organized per service (functions/app-service/container-apps), with every referenced path verified to exist in the bundle; runtime-specific detail is appropriately split into references/services/functions/runtimes/. Not 4 because navigation is easy and there are no organization gaps — the bundle structure matches the table exactly.

5 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 is exemplary: third-person voice, concrete actions, an explicit WHEN trigger clause with natural phrasings and abbreviations, and a well-defined migration niche. It clearly answers both what the skill does and when to use it, with no vague padding.

DimensionReasoningScore

Specificity

Quotes: 'Assess and migrate cross-cloud workloads to Azure with reports and code conversion' plus explicit source-to-target mappings ('Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps'). Multiple concrete actions with comprehensive coverage of all eight migration paths; not 4 because there are no gaps in the action or scenario coverage.

5 / 5

Completeness

Explicitly answers 'what' ('Assess and migrate cross-cloud workloads to Azure with reports and code conversion') and 'when' via a dedicated 'WHEN:' clause with concrete trigger phrases. Both are explicit, so it sits above the 4 anchor where the 'when' could be more specific.

5 / 5

Trigger Term Quality

The 'WHEN:' clause lists natural user phrasings — 'migrate Lambda to Functions', 'AWS to Azure', 'migrate Beanstalk', 'migrate Heroku', 'Cloud Run migration' — along with synonyms and abbreviations ('Fargate to ACA', 'ECS/Kubernetes/GKE/EKS'). Comprehensive natural-term coverage including abbreviations; not 4 because both colloquial phrasings and technical variants are present.

5 / 5

Distinctiveness Conflict Risk

Clear niche — cross-cloud migration to Azure — with triggers naming specific source/target service pairs (Lambda→Functions, Heroku→App Service, Fargate→ACA). Minimal conflict risk; not 4 because the service-specific triggers are unlikely to match unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 18 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 18 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
microsoft/GitHub-Copilot-for-Azure
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.