- Investigate Integration TestInvestigate a failing integration test from a GitHub issue. Downloads logs/artifacts, analyzes the failure, examines relevant skills, and suggests fixes. TRIGGERS: investigate integration test, debug integration test, failing integration test, test failure investigation, diagnose test failure, analyze test issuemicrosoft/GitHub-Copilot-for-Azure255
- Markdown Token OptimizerAnalyzes markdown files for token efficiency. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file, file too large, optimize for AI, token efficiency, verbose markdown, reduce file sizemicrosoft/GitHub-Copilot-for-Azure255
- Microsoft FoundryBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, agent insights, pull agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agmicrosoft/GitHub-Copilot-for-Azure255
- Onboard PluginScaffold a new plugin and prepare it for distribution. WHEN: 'create a new plugin', 'scaffold a new plugin'microsoft/GitHub-Copilot-for-Azure255
- PresetIntelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (usmicrosoft/GitHub-Copilot-for-Azure255
- Python Appservice DeployDeploy Python (Flask/Django/FastAPI) code to Azure App Service Linux. WHEN: "Flask App Service", "Django App Service", "FastAPI App Service", "deploy Python to App Service". DO NOT USE FOR: Container Apps, Functions, non-Python, Terraform/Bicep/IaC, full infra — use azure-prepare.microsoft/GitHub-Copilot-for-Azure255
- SenseiIteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve skill routingmicrosoft/GitHub-Copilot-for-Azure255
- Skill AuthoringGuidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skill", "write a skill", "skill template", "skill structure", "review skill", "skill PR", "skill compliance", "SKILL.md format", "skill frontmatter", "skill best practices".microsoft/GitHub-Copilot-for-Azure255
- Skill ReviewerReview skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo conventions. WHEN: "review skill", "review skill PR", "review skill changes", "check skill quality", "skill PR feedback".microsoft/GitHub-Copilot-for-Azure255
- Vally EvalAuthor, validate, and run Vally evaluation suites for agent skills. TRIGGERS: create eval, write eval, add eval, run eval, validate eval, vally eval, eval.yaml, add stimulus, map test to eval, migrate test to eval, eval graders, eval scoring, add eval to CI.microsoft/GitHub-Copilot-for-Azure255
- Add Example AgentsAdd agents from the public microsoft/discovery GitHub repository to this workspace, either (a) locally for the Copilot app by emitting a `.agent.md` companion per agent (so each is invocable via `runSubagent`), (b) into a Microsoft Discovery project via `UpsertAgent` sourced fresh from upstream (binding pre-existing tool ARM resources when present, or building + pushing + registering them in Azure first when missing), or (c) promoting an agent already added to the local Copilot app (sourced frommicrosoft/discovery254
- Discovery CatalogInventory the contents of this Discovery catalog repo. Lists publishers, agents, starter-kits, and the tools shipped under each agent. Use this skill whenever the user asks what's in the catalog, who publishes what, what agents/tools/starter-kits exist, lists or counts of any of those, "show me the catalog", "do we have an agent for X", "what starter kits do we have", "list the publishers", "list tools per agent", or any inventory/discovery question about repo-resident assets — even if the user microsoft/discovery254
- Discovery Services Agent DeployerDeploy Discovery catalog agents end-to-end with one command: discover the agent, build and bind its tool when present, skip tool stages for agents without tools, deploy the agent, and optionally run validation. Use this skill whenever the user asks to deploy a Discovery agent, publish or rebuild an agent tool image, register a Discovery tool from a repo Dockerfile/tool.yaml, resume a failed deployment, or produce a dry-run deployment plan for an agent in this catalog.microsoft/discovery254
- Discovery Services Starter Kit DeployerDeploy Discovery catalog starter-kits end-to-end: validate kit.json agentRefs, build and deploy every referenced agent tool, deploy each referenced agent individually, and summarize deployed agents/tools plus customer-ready sample prompts. Use this skill whenever the user asks to deploy a Discovery starter-kit or deploy all agents listed in starter-kits/*/kit.json.microsoft/discovery254
- Dv AdminEnvironment-level Dataverse administration — bulk delete, retention/archival, organization settings, OrgDB settings, recycle bin, audit, and the 37 allowlisted PPAC toggles. Use when the user wants to clean up data at scale, configure audit, change environment settings, manage retention policies, or list/cancel ERP batch jobs.microsoft/Dataverse-skills236
- Dv ConnectOne-step setup and connection diagnostics for a Dataverse environment — installs tools, authenticates, registers MCP, writes `.env`, and verifies active profiles and linked ERP endpoints. Use when starting a new project, switching environments, fixing authentication, troubleshooting MCP, or checking existing Dataverse / Finance and Operations connectivity or linkage.microsoft/Dataverse-skills236
- Dv DataRecord-level CRUD and bulk operations — create, update, delete, upsert, CSV import, multi-table foreign-key loads, AI-generated sample data. Use when the user wants to write, modify, seed, or import data records into Dataverse tables, or plan or perform Finance and Operations (ERP) record writes and DMF package imports.microsoft/Dataverse-skills236
- Dv MetadataDataverse schema authoring and inspection — tables, columns, relationships, forms, and views. Use when the user wants to define, evolve, or inspect the data model — add a column, create a table, set up a lookup, customize a form, build a view, or list existing columns and relationships.microsoft/Dataverse-skills236
- Dv OverviewFoundational cross-cutting context for Dataverse / Power Platform work — scope and the skill map, the tool-capability reference, the safety rules, and the safe change lifecycle. Use when the user mentions Dataverse, Dynamics 365, Power Platform, CRM, or ERP; load this first for orientation. Specialist skills self-route via their own frontmatter triggers. Finance and Operations / F&O business-data requests also require this skill first, then dv-query for reads.microsoft/Dataverse-skills236
- Dv QueryBulk reads, multi-page iteration, and analytics over Dataverse data. Use when the user wants to read, list, filter, aggregate, group, join, or analyze records — including pandas DataFrame workflows and notebook exploration. Also covers ERP (Finance and Operations / F&O) business-data reads and runtime entity, schema, or action discovery; load dv-overview first, then this skill.microsoft/Dataverse-skills236
- Dv SecuritySecurity-role assignment, user access, application users, business units, and admin self-elevation in Dataverse environments. Use when the user wants to give someone access, grant a role, become an admin, or add a service principal.microsoft/Dataverse-skills236
- Dv SolutionDataverse solution lifecycle — create, export, import, promote across environments, and validate deployments. Use when the user wants to package customizations, deploy to another environment, or move work between dev / test / prod.microsoft/Dataverse-skills236
- Erp XppX++ code development lifecycle for Finance and Operations — scaffold models, author classes, custom services/APIs, and data entities, install matching SDKs, compile deployable packages, deploy packages, synchronize databases, and verify deployed artifacts. Use when the user explicitly requests creating, building, compiling, packaging, deploying, DB-syncing, or verifying X++ customizations, or an end-to-end ERP code change.microsoft/Dataverse-skills236
- Capability PatchSelected during the capability phase — adds new tools, exposes new parameters, fixes tool implementations, or removes infrastructure limitations to expand what the agent can domicrosoft/AutoSaddler233
- Capability PatchSelected during the capability phase to add tools, expose parameters, fix implementations, or remove infrastructure limitations that restrict the agent.microsoft/AutoSaddler233
- Causal DiagnosisUse before proposing a mutation to diagnose measured failures from evaluator outcomes, traces, history, and the controlling candidate surfaces.microsoft/AutoSaddler233
- DiagnoseUse to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patternsmicrosoft/AutoSaddler233
- History AnalysisUse to systematically analyze the full evolution history without output truncation — produces a structured summary of what matters for the current iterationmicrosoft/AutoSaddler233
- History AnalysisUse to systematically analyze the full evolution history without output truncation and produce a focused summary for selection, diagnosis, or reflection.microsoft/AutoSaddler233
- Patch VerificationUse after applying any patch to thoroughly verify the agent codebase has no bugs — checks syntax, imports, runtime behavior, docstrings, templates, hooks, and logical correctnessmicrosoft/AutoSaddler233
- Patch VerificationUse after applying a Meta-ARE patch to check syntax, imports, integration behavior, hooks, mutation scope, and result consistency.microsoft/AutoSaddler233
- Steering PatchSelected during the steering phase — refines agent behavior by modifying prompts, tool descriptions, or hook reminders without changing executable codemicrosoft/AutoSaddler233
- Steering PatchSelected during the steering phase to refine agent behavior through prompts, tool descriptions, or hook reminders without changing executable code.microsoft/AutoSaddler233
- Verification BaselineUse after applying a candidate change to verify its diff, scope, syntax, integration behavior, and consistency before returning it.microsoft/AutoSaddler233
- Emit SarifSerialize AI-detected security findings as SARIF v2.1.0 conforming to the AI-generated-findings profile, using the Sarif.Multitool emit verbs.microsoft/sarif-sdk227
- Publish To GhasUploads a finalized SARIF file to GitHub Advanced Security (GHAS) code scanning using the Sarif.Multitool publish-to-ghas verb, deriving the GitHub target, commit, and ref from the run's version-control provenance.microsoft/sarif-sdk227
- Publish To GhazdoUploads a finalized SARIF file to GitHub Advanced Security for Azure DevOps (GHAzDO) using the Sarif.Multitool publish-to-ghazdo verb.microsoft/sarif-sdk227
- Validate SarifValidates SARIF files against the SARIF 2.1.0 schema and the AI-generated-findings profile rules shipped by Sarif.Multitool.microsoft/sarif-sdk227
- Duroxide Code CoverageMeasure and improve code coverage in the Duroxide durable execution runtime. Use when asked about coverage, testing coverage, running llvm-cov, or improving test coverage percentages.microsoft/duroxide216
- Release PreparationPrepare and open a Duroxide release pull request, then create its version tag after merge and explicit approval. Use when asked to prepare a release, bump the crate version, draft release notes, validate a release candidate, or complete the public release handoff.microsoft/duroxide216
- Update Library TemplateMerges the latest Library.Template into this repo (at position of HEAD) and resolves conflicts.microsoft/vs-solutionpersistence208
- Rust Coding SkillUse whenever editing Rust in PET to write allocation-aware, cross-platform, byte-safe code with behavior-proving tests.microsoft/python-environment-tools207
- Rust Locator PatternsPET (Python Environment Tools) Rust coding conventions: locator ordering, thread safety, platform gating, JSONRPC rules, version detection, and path/symlink handling. Reference when writing or reviewing Rust code in this repo to avoid convention violations that cause review churn.microsoft/python-environment-tools207
- Rust PrecommitRun the mandatory PET Rust pre-commit checks (cargo fmt + cargo clippy -D warnings) before every commit. Invoke whenever you are about to commit Rust changes, after applying review feedback, or whenever you need to verify formatting and lint cleanliness.microsoft/python-environment-tools207
- Ground AdapterGround CXR findings using the trained MI2 adapter. Returns per-finding positive/possible/negative calls for the agent to use when writing the report.microsoft/healthcareai-examples204
- Ground ZeroshotGround CXR findings using MI2 zero-shot classification. Returns per-finding probabilities bucketed into positive/possible for the agent to use when writing the report.microsoft/healthcareai-examples204
- HelpEntry point for the MedImageInsight plugin, covering the getting-started walkthrough, how the skills work, what MI2 is, and troubleshooting.microsoft/healthcareai-examples204
- Shell UseDrive, inspect, assert on, record, and watch a real terminal from the command line with the shell-use CLI. Use when running shells (bash, zsh, fish, PowerShell, pwsh, cmd, xonsh, elvish, nushell) or TUI programs (vim, less, top, etc.) in a headless PTY; sending keystrokes, key combos, or mouse input; resizing, writing raw bytes, or signaling the child; waiting for a command to finish or the screen to settle; asserting on terminal text, colors, exit codes, output, or snapshots; capturing text or microsoft/shell-use192
- Code ReviewReview a GitHub pull request for problems and consistency with project conventions. Use when asked to review a PR, do a code review, check a PR for issues, or review pull request changes.microsoft/dcp191
- Update DependenciesUpdate packages that DCP executables depend on. This skill is used infrequently, usually just once at the start of a new development cycle. Should only be used when requested explicitly, never as part of a regular change or PR.microsoft/dcp191
- Agentic WorkflowsRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts.microsoft/nvx181
- Nvx BenchmarkBenchmark NVX on a local or SSH-connected Linux/KVM, Linux/MSHV, or Windows/WHP host and collect fresh performance results. Use for acceptance runs, canonical performance suites, p50 collection, benchmark artifacts, and platform performance comparisons.microsoft/nvx181
- Nvx Ci InvestigationInvestigate and fix NVX GitHub Actions failures, cancelled or hanging checks, runner and matrix failures, artifact handoff errors, and performance-gate failures. Use for workflow run URLs or IDs, red PR checks, superseded-run triage, exact-head log analysis, and platform-specific reproduction.microsoft/nvx181
- Nvx DebugDebug NVX on a local or SSH-connected Linux/KVM, Linux/MSHV, or Windows/WHP host. Use for boot failures, missing readiness markers, OpenVMM errors, benchmark acceptance failures, guest hangs, platform access errors, and detailed diagnostics.microsoft/nvx181
- Nvx Host ConnectSelect a developer-configured NVX host, connect over SSH, identify Linux/KVM, Linux/MSHV, or Windows/WHP support, verify its checkout, and prepare artifacts. Use before remote NVX work or when diagnosing configured SSH host prerequisites.microsoft/nvx181
- Nvx Openvmm PromotePromote an OpenVMM pull request or revision into NVX as a clean gitlink update. Use for OpenVMM pin updates, clean replacement PRs, source-equivalence checks, signed integration commits, dependency validation, and exact-head NVX CI validation.microsoft/nvx181
- Nvx RunRun NVX interactively on a local or SSH-connected Linux/KVM, Linux/MSHV, or Windows/WHP host. Use for boot smoke tests, guest shell sessions, virtio-fs mounts, networking, kernel command-line options, and clean guest shutdown.microsoft/nvx181
- Cargo Anvil AdoptionComplete cargo-anvil adoption in an existing Rust repository after the first cargo anvil run. Use when generated Anvil files coexist with legacy CI, recipes, scripts, tool configuration, or validation failures.microsoft/oxidizer178
- Code ReviewReview guidance for pull requests in this repository. Use when reviewing a pull request, to keep comments on evidence you can see rather than on predicted build outcomes, remembered API signatures, or assumed conventions.microsoft/oxidizer178
- Ama Logs Update Charts Release NotesPrepare an ama-logs release PR: bump the image tag (X.Y.Z) across Helm charts, manifests, and Dockerfiles, and add a formatted ReleaseNotes.md entry. Use when: cutting a new ama-logs release, '3.X.Y release notes', 'bump ciprod image tag', 'release PR for Docker-Provider', creating release notes for a new ciprod build. DO NOT USE FOR: MDSD or Windows AMA bumps in isolation, hotfix patches, or anything that does not increment the ciprod image tag.microsoft/Docker-Provider173