Official Provider SkillView repo
Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
Files1 files
SKILL.md81 lines
Loading editor…
Install
RecommendedOne command — your agent picks it up automatically.
Select an AI agent above to see the install command.
or
Manual Install
More stepsDownload the file and paste it into your agent's system prompt.
Skill details
Versionv1.0.0
Author.NET
Categoryai-ml
Skill IDdotnet/SqlClient/.github/skills/agentic-workflows
Related skills
Fetch Milestone PrsFetches all merged pull requests for a given GitHub milestone and saves their metadata as individual JSON files. Use this skill when asked to retrieve PRs for a milestone, gather PR data for release notes, or collect milestone PR metadata.Generate Mstest FilterGenerates well-formed MSTest filter expressions for dotnet test. Use this skill when asked to create a test filter, run specific tests, filter tests by name, class, category, or priority, or when the user describes tests they want to run selectively.Azdo Build InvestigatorInvestigate CI failures for dotnet/maui PRs — build errors, Helix test logs, and binlog analysis. Use when asked about failing checks, CI status, test failures, 'why is CI red', 'build failed', 'what's failing on PR', 'is this PR ready to merge', Helix failures, or device test failures.Learn From PrAnalyzes a completed PR to extract lessons learned from agent behavior. Use after any PR with agent involvement - whether the agent failed, succeeded slowly, or succeeded quickly. Identifies patterns to reinforce or fix, and generates actionable recommendations for instruction files, skills, and documentation.Verify Tests Fail Without FixVerifies tests catch the bug. Auto-detects test type (UI tests, device tests, unit tests) and dispatches to the appropriate runner. Supports two modes - verify failure only (test creation) or full verification (test + fix validation).Release NotesGenerate and maintain .NET release notes from `features.json`. Uses `generate-changes` for authoritative shipped-change data, `generate-features` for scoring/triage, `update-existing-branch` for incremental reruns on populated branches, `editorial-scoring` for the shared rubric, `api-diff`/`dotnet-inspect` for API verification, and a multi-model `review-release-notes` pass for final editorial QA.