Skills by github

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

This skill documents the GitHub CLI (`gh`) and its commands for repositories, PRs, issues, Actions, codespaces, secrets, and related workflows. It includes shell examples (e.g., `curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | sudo dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg`), instructions that expose/use tokens (`export GH_TOKEN`, `gh auth token`, `gh auth login --with-token < token.txt`), and `gh api` calls to `github.com`.

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

This skill generates Product Requirements Documents (PRDs) and enforces a strict PRD schema plus a required discovery interview. It lists tools `codesearch`, `grep`, and `webfetch`, which implies use of local CLI tooling and a web-fetching capability (shell/network use inferred).

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, or manage issue workflows. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", or any GitHub issue management task.

Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.

This skill performs automated visual reviews of websites and edits project source files in the workspace to apply fixes. It requires network access to `http://localhost:3000` (and remote sites), workspace read/write (e.g., `package.json`, `src/`), and executes CLI commands like `npx` to run `@playwright/mcp@latest`.

Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders.

Provides CLI recipes and examples to manage Azure DevOps using the Azure CLI and `az devops` extension. Contains direct shell commands including `curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash`, network calls to `https://dev.azure.com/{org}`, and guidance to store/use PATs in `AZURE_DEVOPS_EXT_PAT`.

Provides guidance for querying Microsoft documentation across `learn.microsoft.com`, `aspire.dev`, `code.visualstudio.com`, and `docs.github.com`. It instructs invoking retrieval tools like `microsoft_docs_search`, `microsoft_docs_fetch`, `mcp_context7_resolve-library-id` and includes a CLI update command `aspire update --self --channel daily`.

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call MCP tools from command line.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

This skill generates Excalidraw diagrams from natural-language descriptions and includes Python CLI tools and templates to create and modify `.excalidraw` files. It provides explicit instructions to run `python` scripts (e.g. `split-excalidraw-library.py`) and to download icon libraries from `https://libraries.excalidraw.com/`.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

High-risk skill: downloads `https://github.com/plantuml/plantuml/releases/download/v1.2024.0/plantuml-1.2024.0.jar` and instructs executing shell commands such as `java -jar plantuml.jar` and `sudo apt-get install plantuml`. It documents generating ASCII diagrams with `plantuml -txt` and writing files like `./output` and `seq.puml`.

This skill looks up Microsoft API references and fetches official code samples to verify SDK usage. It instructs calling the Microsoft Learn MCP API at `https://learn.microsoft.com/api/mcp`.

This skill documents the GitHub Copilot SDK for embedding agentic workflows into applications. It includes explicit shell commands such as `copilot --server --port 4321` and directs connections to `https://api.githubcopilot.com/mcp/` and `localhost:4321`.

This skill performs preflight validation for Azure Bicep deployments, running CLI checks, what-if analysis, and generating `preflight-report.md`. It instructs executing `bicep build`, `az deployment ... what-if`, and `az login`, which enable local shell execution and network/authentication actions.

This skill provides ImageMagick-based scripts and examples for resizing, converting, and batch-processing images across PowerShell and Bash. It contains explicit shell/PowerShell commands that invoke `magick` (e.g., `magick identify`, `& $magick ...`), which run local CLI commands.

This skill manages NuGet packages in .NET projects and prescribes using the `dotnet` CLI and controlled edits to `Directory.Packages.props`/`.csproj` files. It explicitly instructs running `dotnet add`, `dotnet remove`, `dotnet package search`, and `dotnet restore`, which invoke CLI and network operations.

Guidelines for contributing commands in VS Code extensions. Indicates naming convention, visibility, localization and other relevant attributes, following VS Code extension development guidelines, libraries and good practices

Analyze Azure resource groups and generate detailed Mermaid architecture diagrams showing the relationships between individual resources. Use this skill when the user asks for a diagram of their Azure resources or help in understanding how the resources relate to each other.

When user is asking for guidance for which role to assign to an identity given desired permissions, this agent helps them understand the role that will meet the requirements with least privilege access and how to apply that role.

This skill instruments webapps to send telemetry to Azure Application Insights and provides code edits, Bicep templates, and `az` CLI steps. It instructs running `az` CLI commands and setting the `APPLICATIONINSIGHTS_CONNECTION_STRING` environment variable; these behaviors are purpose-aligned and low risk.

Guidelines for proper localization of VS Code extensions, following VS Code extension development guidelines, libraries and good practices

Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic component placements, draw breadboard diagrams, mockup 6502 builds, generate retro computer schematics, or design vintage electronics projects. Supports 555 timers, W65C02S microprocessors, 28C256 EEPROMs, W65C22 VIA chips, 7400-series logic gates, LEDs, resistors, capacitors, switches, buttons, crystals, and wires.

This skill helps create, configure, and deploy Azure Static Web Apps using the SWA CLI (`npx swa init`, `npx swa start`, `npx swa deploy`). It instructs running local CLI commands and using deployment credentials such as `SWA_CLI_DEPLOYMENT_TOKEN` and GitHub secret `AZURE_STATIC_WEB_APPS_API_TOKEN`.

This skill drafts and validates Snowflake semantic view DDL and guides use of the Snowflake CLI. It instructs running `snow sql` (e.g., `snow sql -q "<...>" --connection <connection_name>`) and configuring connections via `snow connection add`, which executes CLI commands and uses networked Snowflake credentials.

This skill runs the `scoutqa` CLI to perform autonomous exploratory web testing and report execution IDs and live report URLs. It instructs executing shell commands via the Bash tool (`timeout: 5000`), contacting external sites like `https://scoutqa.ai`, and using credentials via `scoutqa send-message`.

This skill guides the Copilot CLI to install and use WorkIQ for querying Microsoft 365 data. It contains explicit local commands and network-installs such as `npm install -g @microsoft/workiq`, `workiq mcp`, and `/plugin install workiq@copilot-plugins`, which invoke shell execution and network access.

Power BI semantic modeling assistant that inspects and modifies models, provides DAX and design guidance, and uses included reference docs. It instructs connecting to `power-bi-modeling MCP` tools and optionally calling `Microsoft Learn MCP` (`microsoft_docs_search` / `microsoft_docs_fetch`), i.e., network operations are required.

This skill converts Markdown to HTML and documents workflows for `marked`, `pandoc`, `gomarkdown`, `jekyll`, and `hugo`. It includes explicit shell commands (e.g., `npm install -g marked`, `pandoc input.md -o output.html`), external URLs (e.g., `https://cdn.jsdelivr.net/npm/marked/lib/marked.umd.js`), and environment usage like `JEKYLL_ENV`.

Provides a Penpot UI/UX design guide that uses local MCP tools (e.g., `mcp__penpot__execute_code`) to inspect and modify Penpot files. It instructs running shell commands (`git clone ...`, `npm run bootstrap`), contacting `http://localhost:4401` endpoints, and editing client config files (`~/Library/Application Support/Claude/claude_desktop_config.json`).

This skill generates concise, actionable meeting minutes for short internal meetings using a strict schema that includes metadata, attendance, decisions, and action items. No security-relevant behaviors detected.

This skill enforces repository contribution workflows and templates, guiding issues, branch creation, commits, and PR content using files like `./assets/issue-template.md`. It instructs VCS operations that imply running `git`/`gh` commands (e.g., `push code`, `create a PR`), so shell execution and network access are required.

This skill is a CLI for initializing, packaging, and signing Windows applications with `winapp`. It includes explicit shell commands (`winapp init`, `winapp pack`, `npm install @microsoft/winappcli`), network installation links (`https://github.com/microsoft/WinAppCli/releases/latest`), and certificate handling (`--cert ./mycert.pfx`, `--cert-password secret`).

Analyzes Terraform plan JSON for AzureRM Set-type attribute false-positive diffs. The documentation and examples instruct executing local shell commands such as `terraform plan` and `python scripts/analyze_plan.py`, which run CLI tools on the host.