Tools tagged with "Official"

Find and close stale bug issues in microsoft/AzureStorageExplorer. Use this when asked to clean up stale issues, close inactive bugs, or perform issue hygiene.

Write, update, run, or debug vscode-java-pack UI/E2E tests using AutoTest YAML plans. Use when the user asks for a UI test, E2E test, VS Code UI validation, web

Add new T-SQL features to ScriptDOM parser. Asks questions about SQL Server version and feature type, then guides through grammar changes, AST updates, script g

Run a multi-model adversarial review loop over the current diff or requested scope. Use one Claude-family reviewer and one GPT-family reviewer in parallel, fix

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. TRI

Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation

Architecture map, layer responsibilities, key files, auth types, and debug runbook by symptom.

Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatibl

Generate an interactive, scrollable HTML calendar view from a markdown schedule file. The calendar uses the Canvas skill to display as a borderless app window.

Show things visually using Canvas. Use when the human says "put this on the canvas," "show me a visual," "make a slide," or "visualize this." Canvas creates an

Development workflow for building, syncing, packaging, and shipping Copilot Studio agents. Use this skill when working with Copilot Studio YAML files (agent.mcs

Stage, commit, push, and create GitHub PRs for the current branch — always main, then automatically cherry-picks to release/stable.

Diagnose a pipeline failure or customer issue end-to-end. Accepts a log path, error text, ADO work item ID, or GitHub issue URL.

Serialize AI-detected security findings as SARIF v2.1.0 conforming to the AI-generated-findings profile, using the Sarif.Multitool emit verbs.

File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failur

Fix Dependabot security alerts by updating vulnerable npm dependencies. Use when the user mentions "dependabot", "security alerts", "vulnerability", "CVE", or w

Fix all vulnerabilities on the current branch using npm audit. Local branch only — no ADO/GitHub queries.

Run a Godot/GDExtension finish pass over the current diff: enforce headless GDScript validation, public API docclasses coverage, docs/spec/sample/test synchroni

Investigate a failing integration test from a GitHub issue. Downloads logs/artifacts, analyzes the failure, examines relevant skills, and suggests fixes. TRIGGE

Sync ADO work items and ICM incidents to the persistent knowledge log. Invoked automatically by /review, /workitem, and /pac-cli-update when knowledge is stale.

Analyzes markdown files for token efficiency. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file,

Your companion for Microsoft Build 2026. Helps you find sessions relevant to your project, discover what's new for your tech stack, scaffold projects from sessi

Upgrade, add, remove, or review NuGet package references and dependencies in this repo. Use when changing version.json, Directory.Packages.props, <PackageRefere

Bump PAC CLI binary version and/or cli-wrapper npm package. Always produces two PRs — main and release/stable.

Turn GitHub PR feedback into a disciplined remediation loop: gather review threads, comments, and check runs; classify actionable items; fix the concrete must-f

Verify that a pull request into microsoft/vscode-makefile-tools meets contribution requirements. Use when preparing, reviewing, or finalizing a PR to check for

Review a pull request for correctness, approach, completeness, and consistency with instructions in this repo. Use for initial PR reviews, follow-up reviews aft

Prepare and publish SwiftStreamingMarkdown pull requests end-to-end: generate PR description, commit changes, create/push branch, and open a PR when needed.

Uploads a finalized SARIF file to GitHub Advanced Security (GHAS) code scanning using the Sarif.Multitool publish-to-ghas verb, deriving the GitHub target, comm

Uploads a finalized SARIF file to GitHub Advanced Security for Azure DevOps (GHAzDO) using the Sarif.Multitool publish-to-ghazdo verb.

Review code for correctness, approach, completeness, and consistency with instructions in this repo. Use for initial review, and verifying addressed feedback.

Autonomous PR review — reads diff, cross-references knowledge base, posts inline comments, and leaves an overall verdict.

Fetch all open security alerts from S360/ADO, Dependabot, and npm audit, apply all fixes, verify, commit, and create a PR.

Iteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve skill routing

Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skill", "write a skill", "skill template", "

Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions. WHEN: "review skill