microsoft/GitHub-Copilot-for-Azure
Skill Claude CodeCodex ✓ vendor
Analyzes 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 size.
microsoft/GitHub-Copilot-for-Azure
Skill Claude CodeCodex ✓ vendor
Iteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve skill routing.
microsoft/GitHub-Copilot-for-Azure
Skill Claude CodeCodex ✓ vendor
Guidelines 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-Azure
Skill Claude CodeCodex ✓ vendor
Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions. WHEN: "review skill", "review skill PR", "review skill changes", "check skill quality", "skill PR feedback".
microsoft/GitHub-Copilot-for-Azure
Skill Claude CodeCodex ✓ vendor
Author, 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-Azure
Plugin Claude Code ✓ vendor
Bundles 3 skills, 1 MCP server · 372 tokens together
Kusto graph analysis, IRQL security hunting pipelines, and graph visualization skills for Azure Data Explorer.
microsoft/GitHub-Copilot-for-Azure
Plugin Claude Code ✓ vendor
Bundles 38 skills · 4,347 tokens together
Microsoft Azure MCP and Skills integration for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from Claude Code.
Skill Claude CodeCodex ✓ vendor
Drive, inspect, assert on, record, and watch a real terminal from the command line with the tui-test 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…
Skill Claude CodeCodex ✓ vendor
Inventory 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…
Skill Claude CodeCodex ✓ vendor
--- name: discovery-design-tasks description: "Generate a Microsoft Discovery task design (markdown only) for a user-specified local-app or cloud-service Foundry agent set using one (or all) of the three advanced investigation patterns: Deterministic, Guided Exploration, and Autonomous Research. For cloud-service…
Skill Claude CodeCodex ✓ vendor
Deploy 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…
Skill Claude CodeCodex ✓ vendor
Deploy 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…
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/discovery, covering copilot instructions for python api polling project, project context, code style guidelines, python standards and configuration management.
Agent ✓ vendor
Analyzes crowdsourced subjective test results — runs resultparser.py for data cleaning, quality checks, and per-clip/per-worker MOS aggregation, and writes a re-runnable rerunresultparser.bat that re-runs resultparser.py.
Agent ✓ vendor
Creates subjective speech quality tests using the P.808 toolkit — handles study setup, gold/trapping clip generation, storage upload, project building for crowdsourcing platforms, prompts for study-specific screen-out completion codes (never reused across studies) and for the internal-vs-general master-script assets…
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/P.808, covering copilot instructions, code style and formatting, function documentation, python spacing and syntax and line endings.
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/P.808, covering language and grammar correction rules, goal, do not change, editing rules and code-specific rules.
Instructions file CodexOpenCode ✓ vendor
Instructions for microsoft/P.808, covering agents guide, for ai agents (github copilot, claude, etc.), custom agents and task-specific instructions (future).
Instructions file ✓ vendor
Instructions for microsoft/P.808, covering claude code instructions and custom agents.
Skill Claude CodeCodex ✓ vendor
Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs, and frontends tailored to a user's scenario.
Plugin Claude Code ✓ vendor
Bundles 8 skills · 466 tokens together
Microsoft Dataverse plugin for coding agents, covering record CRUD, bulk data operations, advanced queries, schema and metadata, administration, security, environment management, and solution lifecycle through MCP, CLI, and SDK workflows.
Instructions file ✓ vendor
Instructions for microsoft/Dataverse-skills, covering claude.md — dataverse skills plugin, what this repo is, before committing, skill authoring rules and python only.
Instructions file ✓ vendor
Instructions for microsoft/Agents-for-python, covering claude.md, repository overview, development setup, initial setup and install all libraries in editable mode.
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/mcp-dotnet-samples, covering copilot instructions (concise) – mcp .net samples, architecture & runtime, sample-specific nuance, core conventions and adding / modifying tools.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: