goal

Set, inspect, or control a durable goal — the agent keeps iterating across turns until the stop condition is met.

npx skills add https://github.com/microsoft/vscode-team-kit --skill goal

Download ZIP GitHub

Try this skillSponsored

You are handling the /goal command. Invoke the follow-goal skill to do the actual work.

Persist goal state into session storage as goal.md. After creating or updating the file, mark it as a plan artifact via setArtifacts so the user sees live goal state in the chat UI. Do not write the goal to the workspace.

Dispatch based on what the user typed after /goal:

/goal <objective text> → Set a new goal. Follow the skill's "Set" flow: collect objective, verifiable stop condition, validation commands, and constraints (ask the user for anything missing), write goal.md with status: active, and start the loop.
/goal (no extra args) → Status only. Read goal.md and report objective, stop condition, status, checkpoint count, and the last few progress-log lines. Do nothing else.
/goal pause → Mark the goal paused. Stop iterating.
/goal resume → Mark the goal active and continue the loop from the latest checkpoint.
/goal clear → Mark the goal cleared. Leave the file in place for history.

Rules:

If goal.md does not exist in session storage and the user typed something other than a new objective, tell them there is no active goal and show them the /goal <objective> syntax.
After every write to goal.md (create or update), call setArtifacts to mark the memory file as a plan artifact. This keeps the UI widget in sync with the persisted state.
If a goal is already active and the user sets a new one, ask whether to replace, pause, or clear the existing goal first.
Never invent a stop condition the user didn't give you. If they can't articulate one, push back — a goal without a verifiable end state is not ready.

More skills from microsoft

OSS growth hacker persona

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.

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".

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.

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.

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.

azure-ai-language-conversations-py

Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.

Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines. Triggers: "azure-ai-ml", "MLClient", "workspace", "model registry", "training jobs", "datasets".