microsoft.
200 skills across 45 repos
- 100/100
accordant-async-operations
How to model background work, step functions, and polling - use this skill when testing async workflows, job queues, or operations that complete in the background
- 100/100
accordant-concurrency
How to test for race conditions using concurrent tests and linearizability - use this skill when testing concurrent operations or finding race condition bugs
- 100/100
accordant-cross-language
Testing systems not written in .NET - trace-based conformance testing, JSON test plan export, and executing from any language. Use when the user's system is in Python, Go, Java, Rust, C++, or any non-.NET language, or when they ask about trace validation or exporting test cases.
- 100/100
accordant-operations
How to define operations with Apply and Execute methods - use this skill when creating spec operations or understanding the Apply/Execute pattern
- 100/100
accordant-overview
What Accordant is, when to use model-based testing, and core concepts - use this skill when starting with Accordant or explaining its purpose
- 100/100
accordant-patterns
Common patterns in Accordant - response-dependent state, request derivations, error handling, and HTTP integration
- 100/100
accordant-quickref
Quick reference and cheatsheet for Accordant API - use this skill for quick syntax lookup or code snippets
- 100/100
accordant-state
How to design state models in Accordant - use this skill when defining what your system tracks between operations
- 100/100
accordant-test-generation
How Accordant generates and runs tests - use this skill when configuring test generation, understanding state graphs, or running tests
- 100/100
accordant-troubleshooting
Common mistakes and debugging tips for Accordant specs - use this skill when tests fail unexpectedly or specs don't behave as expected
- 100/100
0-acs-full-scan
Full ACS deprecation impact assessment orchestrator. Runs the complete workflow — auth check, subscription selection, ACS resource scan, channel detection (fast or full), impact analysis, and report generation. ACS-specific, no PowerShell script required.
- 100/100
1-acs-resource-scan
Scan Azure subscriptions for Azure Communication Services (ACS) resources (Microsoft.Communication/CommunicationServices). ACS-specific version of azure/3-azure-resource-scan with resource type pre-filled.
- 100/100
1-azure-auth-check
Verify Azure authentication status and display connection information (tenant, account, subscription context). Works with any Azure product or service.
- 100/100
2-acs-channel-detect
Fast, resource-based detection of ACS channels (Email, Phone Numbers). Detects Email via EmailServices/Domains child resources and Phone Numbers via purchased phone Numbers under each ACS resource. Note: SMS, Chat, Call Automation, Job Router, Advance Messaging, and Rooms require metrics — use 3-acs-metrics-collect for complete detection.
- 100/100
2-azure-subscription-select
Interactive subscription selection workflow. Choose specific subscription(s) or scan all accessible subscriptions. Works with any Azure product or service.
- 100/100
3-acs-metrics-collect
Comprehensive ACS usage detection via Azure Monitor metrics. All configured ACS channels are pre-mapped (Email, SMS, Chat, Call Automation, Job Router, Advance Messaging, Rooms). Configurable lookback period of 1-93 days.
- 100/100
3-azure-resource-scan
Scan Azure subscriptions for specific resource types. Interactive prompts allow scanning any Azure product (ACS, Storage, Compute, Databases, etc). Returns resource inventory across selected subscriptions.
- 100/100
4-acs-impact-analyze
Map detected ACS channel usage to the appropriate Retirement Guide or Breaking Change Guide. Links each impacted resource to Microsoft migration resources per channel.
- 100/100
4-azure-channel-detect
Fast, resource-based feature detection for Azure resources. Detects features/channels by examining related child resources (domains, endpoints, configurations). Works with any Azure product where features are exposed as sub-resources.
- 100/100
5-acs-report-generate
Generate ACS deprecation impact reports in CSV, Markdown, or JSON format. Pre-configured with ACS channel columns, migration guide links, and ACS-specific report sections.
- 100/100
5-azure-metrics-collect
Comprehensive feature/usage detection via Azure Monitor metrics. Collects usage data over configurable lookback period (1-93 days). Works with any Azure product that emits metrics to Azure Monitor.
- 100/100
6-azure-impact-analyze
Calculate severity and migration effort for Azure resources with detected features. Configurable severity thresholds based on usage patterns and business impact. Works with any Azure product deprecation scenario.
- 100/100
7-azure-report-generate
Generate comprehensive reports (CSV, Markdown, JSON) for Azure resource impact assessments. Export detailed findings, statistics, and recommendations. Works with any Azure product deprecation analysis.
- 90/100
agent-academy-mission-builder
>
- 100/100
agent-academy-report
Generate a full Agent Academy feedback report — extracting feedback from Excel files and GitHub issues, analyzing sentiment, generating charts, and producing a single styled PDF with a cover page, management summary, and detailed analysis. Use this skill when the user asks to generate an Agent Academy report, create a feedback analysis, build a course completion report, or wants to analyze Agent Academy survey data. Also triggers when the user mentions Agent Academy feedback, course grades, sentiment analysis of Agent Academy data, or exporting Agent Academy results to PDF.
- 100/100
agent-academy-stargazers
>
- 100/100
align-cli-webapp-reports
Compare CLI visual readiness report with local webapp report for a given repo, identify differences in checks/rendering/scoring, and fix them
- 100/100
area-instructions
Generate a concise .instructions.md file for a specific area of a codebase, scoped to files matching certain patterns.
- 95/100
agents-sdk-dotnet
>
- 100/100
agents-sdk-dotnet-activityhandler-migration
Use when migrating a Microsoft 365 Agents SDK agent that uses ActivityHandler or TeamsActivityHandler to AgentApplication. This is ONLY for DotNet projects that uses `Microsoft.Agents.*` packages. Triggered by Agents SDK bots that subclass ActivityHandler or TeamsActivityHandler that need to be modernized to AgentApplication routing.
- 100/100
agents-sdk-dotnet-debugging
>
- 100/100
agents-sdk-dotnet-otel
>
- 80/100
agents-sdk-provision
>
- 100/100
agents-sdk-python-otel
>
- 80/100
agents-sdk-typescript
>
- 100/100
agents-sdk-typescript-debugging
>
- 100/100
agents-sdk-typescript-otel
>
- 100/100
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
- 100/100
agent-conduct
Shared hard rules enforced across all squad agents
- 100/100
architectural-proposals
Create proposal in docs/proposals/ with structured format
- 80/100
aspire-cli-install
Migrating .NET Aspire repos from workload install to CLI script install
- 100/100
aspire-package-upgrade
Upgrading .NET Aspire packages to latest stable/preview versions
- 100/100
amplifier-agent
Integrate Amplifier Agent into applications using its Python or TypeScript library or OpenAI-compatible HTTP face. Use for installation, sessions, streaming, tools, MCP, skills, approvals, configuration, and integration troubleshooting.
- 100/100
amplifier-agent-bugfix
Triage and fix an amplifier-agent bug, from report to verified fix. Covers intake, ruling out non-code causes, root-cause pinning, checking the behavior against the contracts, the coverage-gap gate, red/green regression with evaluations and tests, scoped verification, and quality regressions where contracts hold but output got worse. Stops before commit and release.
- 100/100
amplifier-agent-new-feature
Develop a new amplifier-agent feature from idea to verified behavior. Covers orientation against the contracts, planning, updating every public description, red/green development driven by an evaluation task and supporting tests, the widening verification ladder, and a hands-on human check. Stops before commit and release.
- 90/100
add-amplifier-agent
Use amplifier-agent (Microsoft's modular agent runtime — bundled providers, swappable orchestrators, MCP tools) as the full agent provider in place of the Claude Agent SDK. Routes through OneCLI's Authorization-header rewrite path so the host never holds raw API keys. Per-group via agent_provider.
- 80/100
add-atomic-chat-tool
Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.
- 100/100
add-codex
Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
- 90/100
add-dashboard
Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.
- 70/100
add-deltachat
Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.
- 100/100
add-discord
Add Discord bot channel integration via Chat SDK.
- 90/100
add-emacs
Add Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Local HTTP bridge — no bot token or external service needed.
- 95/100
add-gcal-tool
Add Google Calendar as an MCP tool (list calendars, list/search/create events, free/busy queries) using OneCLI-managed OAuth. Multi-calendar and multi-account supported. Mirrors /add-gmail-tool's stub pattern — no raw credentials ever reach the container; OneCLI injects real tokens at request time.
- 100/100
add-gchat
Add Google Chat channel integration via Chat SDK.
- 100/100
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
- 95/100
add-gmail-tool
Add Gmail as an MCP tool (read, search, send, label, draft) using OneCLI-managed OAuth. The agent gets Gmail tools in every enabled group; OneCLI injects real tokens at request time so no raw credentials are ever in the container or on disk in usable form.
- 100/100
add-imessage
Add iMessage channel integration via Chat SDK. Local (macOS) or remote (Photon API) mode.
- 100/100
add-karpathy-llm-wiki
Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".
- 100/100
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
- 100/100
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.
- 85/100
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
- 100/100
add-mnemon
Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.
- 80/100
add-ollama-provider
Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background.
- 95/100
add-ollama-tool
Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.
- 100/100
add-opencode
Use OpenCode as an agent provider (AGENT_PROVIDER=opencode). OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per-session and per-group via agent_provider; host passes OPENCODE_* and XDG mount when spawning containers.
- 100/100
add-resend
Add Resend (email) channel integration via Chat SDK.
- 100/100
add-rtk
Install rtk token-compression proxy into agent containers. Routes Bash tool calls through rtk for 60–90% token savings on dev commands (git, cargo, pytest, docker, kubectl, etc.).
- 100/100
add-signal
Add Signal channel integration via signal-cli TCP daemon. Native adapter — no Chat SDK bridge.
- 100/100
add-slack
Add Slack channel integration via Chat SDK.
- 100/100
add-telegram
Add Telegram channel integration via Chat SDK.
- 100/100
add-vercel
Add Vercel deployment capability to NanoClaw agents. Installs the Vercel CLI in agent containers and sets up OneCLI credential injection for api.vercel.com. Use when the user wants agents to deploy web applications to Vercel.
- 100/100
add-webex
Add Webex channel integration via Chat SDK.
- 100/100
add-wechat
Add WeChat (personal) channel integration via Tencent's official iLink Bot API. Uses long-polling and QR scan — no webhook, no ToS risk, no paid token.
- 100/100
add-whatsapp
Add WhatsApp channel via native Baileys adapter. Direct connection — no Chat SDK bridge. Uses QR code or pairing code for authentication.
- 100/100
add-whatsapp-cloud
Add WhatsApp Business Cloud API channel via Chat SDK. Official Meta API.
- 100/100
agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.
- 100/100
amplifier-opencode-bugfix
Triage and fix an amplifier-app-opencode bug, from report to verified fix, using E2E-test-driven development. Covers intake, ruling out non-code causes (stale server, stale install, mismatched floor), root-cause pinning, the coverage-gap gate that classifies why e2e missed it, red/green regression TDD, and scoped verification. Stops before release.
- 100/100
amplifier-opencode-new-feature
Develop a new amplifier-app-opencode feature from ideation to working end-to-end in a DTU, using E2E-test-driven development with the spec landing in the same commit as the contract change. Covers orientation, planning, spec-first review, red/green E2E TDD, and the loop-until-green discipline. Stops before release.
- 100/100
amplifier-opencode-release
Release amplifier-app-opencode: bound the commit range, sweep the diff for anything that should not ship, bump both version declarations in agreement, write the changelog, confirm the agent-version floor decision, run the local gate, and open the release PR. Merging to main IS the release; there is no tag or publish step.
- 100/100
adversarial-review
Adversarial review of a system design from 6 critical perspectives -- SRE, security, staff engineer, finance, operator, and developer advocate. Produces a unified risk assessment. Use for INTERACTIVE on-demand reviews during a design conversation (/adversarial-review). For RECIPE-DRIVEN reviews (where prior step context is needed), use the systems-design-critic agent instead.
- 100/100
architecture-primitives
Catalog of reusable architectural primitives — boundaries, contracts, state machines, queues, caches, consistency models, and more. For each: what it is, when it's right, when it's WRONG. Use when selecting patterns for a design or evaluating whether a pattern fits.
- 100/100
artifact-template-analytics-dashboard
Use the analytics dashboard spreadsheet template.
- 100/100
artifact-template-business-review
Use the business review presentation template.
- 100/100
artifact-template-design-report
Use the design report document template.
- 100/100
artifact-template-experiment-analysis
Use the experiment analysis document template.
- 100/100
artifact-template-financial-budget
Use the financial budget spreadsheet template.
- 100/100
artifact-template-investment-committee-memo
Use the investment committee memo document template.
- 100/100
artifact-template-legal-memorandum
Use the legal memorandum document template.
- 100/100
artifact-template-market-trends-report
Use the market trends report presentation template.
- 100/100
artifact-template-minimal-letterhead
Use the minimal letterhead document template.
- 100/100
artifact-template-operating-calendar
Use the operating calendar spreadsheet template.
- 100/100
artifact-template-operating-review
Use the operating review presentation template.
- 100/100
artifact-template-project-kickoff
Use the project kickoff presentation template.
- 100/100
artifact-template-project-tracker
Use the project tracker spreadsheet template.
- 100/100
artifact-template-sales-pipeline
Use the sales pipeline spreadsheet template.
- 100/100
artifact-template-simple-dark-mode
Use the simple dark mode presentation template.
- 100/100
artifact-template-simple-light-mode
Use the simple light mode presentation template.
- 100/100
artifact-template-strategy-memorandum
Use the strategy memorandum document template.
- 100/100
artifact-template-system-design
Use the system design document template.
- 100/100
artifact-template-team-alignment
Use the team alignment presentation template.
- 100/100
artifact-template-three-statement-forecast
Use the three statement forecast spreadsheet template.
- 80/100
apm-spec-guardian
>-
- 100/100
apm-strategy
>-
- 100/100
apm-usage
>
- 100/100
auth
>
- 100/100
autopilot-comment
>-
- 100/100
autopilot-issue-delivery-scheduler
>-
- 100/100
autopilot-issue-delivery-worker
>-
- 80/100
autopilot-issue-triage-scheduler
>-
- 100/100
autopilot-issue-triage-worker
>-
- 100/100
autopilot-pr-merge-worker
>-
- 100/100
autopilot-pr-review-scheduler
>-
- 100/100
autopilot-pr-review-worker
>-
- 100/100
autopilot-pr-triage-scheduler
>-
- 80/100
autopilot-pr-triage-worker
>-
- 100/100
argus-run
Use when work needs persistent multi-step execution, independent review, resumable project state, or long-running research and engineering coordination through Argus.
- 100/100
argus-runtime-orchestration
Portable outer-operator procedure for durable Argus missions across five hosts.
- 100/100
argus-status
Use when checking an Argus project's progress, pending questions, active role, diagnostics, selected artifacts, intervention state, recovery options, or graceful stop status.
- 100/100
api-review
Reviews .NET API surface area PRs for design guideline violations. Analyzes api/*.cs file diffs, applies review rules from .NET Framework Design Guidelines and Aspire conventions, and attributes findings to the developer who introduced each API (via git blame). Use this when asked to review API surface area changes.
- 100/100
azdo-internal
Expert knowledge for triggering, monitoring, and validating changes to the Aspire internal Azure DevOps pipeline (microsoft-aspire, definition 1602) on dnceng/internal. Use when asked to trigger an internal/AzDO build, check pipeline/build status, push to the internal mirror, or validate eng/ pipeline (eng/pipelines/azure-pipelines.yml / release pipeline) changes for the microsoft/aspire repository.
- 100/100
aspire-deployment
**WORKFLOW SKILL** — Deploy Aspire apps from AppHost models to Docker Compose, Kubernetes, Azure, AWS, or preview Radius. WHEN: \"deploy Aspire app\", \"publish Aspire artifacts\", \"deploy to Azure Container Apps\", \"generate Kubernetes artifacts\", \"deploy to Radius\", \"tear down Aspire deployment\". INVOKES: aspire CLI, Aspire docs, target cloud/container CLIs. FOR SINGLE OPERATIONS: use generic Azure, Kubernetes, Docker, AWS, or Radius tools only when no Aspire AppHost exists.
- 85/100
aspire-init
>-
- 100/100
aspire-monitoring
>-
- 90/100
aspire-orchestration
>-
- 100/100
aspire-project-v2-migration
>-
- 95/100
aspireify
>-
- 100/100
autoGenesis-run
Execute Appium BDD test scenarios via appium-mcp-server with auto code generation. Use when user provides a scenario name and asks to run, execute, or generate test code for it. Triggers on phrases like "execute scenario X", "run appium test for scenario", "generate test code for scenario", "use autoGenesis-run skill", or when a scenario name is provided alongside a request to automate or test it. Reads scenario steps from .feature files in behave-demo/features/, drives each step through MCP tool calls with persistent retry, then saves generated code via preview_code_changes + confirm_code_changes.
- 100/100
autoGenesis-win
Execute Windows application BDD test scenarios via pywinauto-mcp-server with auto code generation. Use when user provides a scenario name and asks to run, execute, or generate test code for Windows applications. Triggers on phrases like "execute Windows scenario X", "run pywinauto test for scenario", "generate test code for Windows scenario", "use autoGenesis-win skill", or when a scenario name is provided alongside a request to automate or test Windows apps. Reads scenario steps from .feature files, drives each step through MCP tool calls with persistent retry, then saves generated code via preview_code_changes + confirm_code_changes.
- 100/100
analyze-skill-issues
Query the integration-test storage account to find why a specific skill's tests are failing. Reads blob-stored test result files and surfaces error details. TRIGGERS: why is skill failing, skill test failures, debug skill tests, skill failing tests, analyze skill failures, why are tests failing for skill, skill test errors, investigate skill issues. DO NOT USE FOR: analyzing a GitHub Actions run report or comparing test runs across runs (use analyze-test-run).
- 100/100
analyze-test-run
Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report
- 100/100
activate-site
>-
- 100/100
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.
- 100/100
add-cloud-flow
>-
- 100/100
add-connector
Adds any Power Platform connector to a Power Apps code app. Generic fallback for connectors not covered by a specific skill.
- 100/100
add-data-source
Guide the user to add a data source, connection, or API connector to a Canvas App via Power Apps Studio, then verify and continue. USE WHEN the user asks to add a data source, add a connection, add an API, add a connector, connect to SharePoint / Dataverse / SQL / Excel / OneDrive / Teams / Office 365, or any similar request to make new data available to the app. DO NOT USE WHEN the user is asking to list or describe existing data sources — call list_data_sources or list_apis directly instead.
- 100/100
add-datasource
Adds a data source or connector to a Power Apps code app. Asks what the user wants to accomplish and routes to the appropriate specialized skill.
- 100/100
add-dataverse
Adds Dataverse tables to a Power Apps code app with generated TypeScript models and services. Can also create new Dataverse tables. Use when connecting to Dataverse, adding tables, creating schema, or querying Dataverse data.
- 100/100
add-excel
Adds Excel Online (Business) connector to a Power Apps code app. Use when reading or writing Excel workbook data from OneDrive or SharePoint.
- 100/100
add-mcscopilot
Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.
- 100/100
add-office365
Adds Office 365 Outlook connector to a Power Apps code app. Use when accessing calendars, sending emails, reading inbox, or managing Outlook events.
- 100/100
add-onedrive
Adds OneDrive for Business connector to a Power Apps code app. Use when uploading, downloading, listing, or managing files in OneDrive.
- 100/100
add-sample-data
>-
- 100/100
add-seo
>-
- 100/100
add-server-logic
>-
- 75/100
add-sharepoint
Adds SharePoint Online connector to a Power Apps code app. Use when reading lists, managing documents, or integrating with SharePoint sites. Can also create new SharePoint lists.
- 100/100
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
- 100/100
audit-permissions
>-
- 100/100
agent-framework-azure-ai-py
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.
- 100/100
airunway-aks-setup
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: \"setup AI Runway\", \"onboard AKS cluster\", \"install AI Runway\", \"airunway setup\", \"deploy model to AKS\", \"GPU inference on AKS\", \"KAITO setup on AKS\", \"run LLM on AKS\", \"vLLM on AKS\", \"set up model serving on AKS\", \"AI Runway controller\".
- 100/100
appinsights-instrumentation
Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. WHEN: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices.
- 100/100
applicationinsights-web-ts
Instrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web). Use for Real User Monitoring (RUM) — page views, clicks, AJAX/fetch dependencies, exceptions, custom events, and browser-side GenAI agent traces correlated to backend OpenTelemetry traces. Covers SDK Loader Script and npm setup, framework extensions (React, React Native, Angular), Click Analytics, telemetry initializers, and OTel GenAI semantic conventions for agent/tool/model spans emitted from the browser.
- 100/100
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
- 100/100
azure-ai-agents-persistent-dotnet
|
- 100/100
azure-ai-agents-persistent-java
|
- 100/100
azure-ai-anomalydetector-java
Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate/multivariate anomaly detection, time-series analysis, or AI-powered monitoring.
- 100/100
azure-ai-contentsafety-java
Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.
- 100/100
azure-ai-contentsafety-py
|
- 100/100
azure-ai-contentsafety-ts
Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.
- 100/100
azure-ai-contentunderstanding-py
|
- 100/100
accessibility
Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.
- 100/100
act-on-feedback
Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.
- 100/100
agent-customization
**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax. DO NOT USE FOR: general coding questions (use default agent); runtime debugging or error diagnosis; MCP server configuration (use MCP docs directly); VS Code extension development. INVOKES: file system tools (read/write customization files), ask-questions tool (interview user for requirements), subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML frontmatter fixes or creating a single file from a known pattern, edit the file directly — no skill needed.
- 100/100
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
- 100/100
agent-host-e2e-tests
Use when writing, recording, updating, validating, or troubleshooting Agent Host end-to-end and real-provider integration tests under src/vs/platform/agentHost/test/node/e2e and providerIntegration. Covers adding a cross-provider test, re-recording fixtures after an SDK bump, required cross-platform Azure validation, gating non-deterministic or platform-specific tests, and diagnosing replay cache misses.
- 100/100
agent-host-logs
Analyze Agent Host debug log exports. Use when given an ah-logs or ahp-logs zip/folder, an Export Agent Host Debug Logs bundle, events.jsonl, AHP JSONL transport logs, Agent Host.log, remote-agenthost.log, or copilot-logs.
- 100/100
author-contributions
Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.
- 100/100
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.