489 skills (repositories by github) · sorted by popularity
Create step-by-step code walkthroughs tailored to readers such as new contributors, reviewers, or bug fixers. Produce CodeTour .tour files linked to verified files and line numbers, with explanations of behavior, design choices, and pitfalls.
Find and load Copilot Spaces, shared collections of project documents, code, and instructions, to answer team-specific questions or follow reporting workflows. Also create and update spaces, attached resources, and collaborator settings through the GitHub CLI.
Builds an evidence map for a disputed decision, linking supporting evidence, counterevidence, qualifications, and missing facts to precise source passages. Produces a structured JSON artifact that makes the reasoning and unresolved questions available for review.
Turn a broad product idea into an Epic PRD, a requirements document for a large initiative. Defines users, workflows, business requirements, success metrics, and scope to give engineering teams a basis for technical architecture planning.
Choose an Azure role that grants only the permissions an identity needs. The skill finds suitable built-in roles, creates custom definitions when necessary, and generates CLI commands and Bicep infrastructure code for assigning the role.
Control and inspect a live Chrome browser through Chrome DevTools MCP. Automate page interactions, capture screenshots, inspect errors and network requests, and record performance data to investigate slow loading and unexpected layout changes.
Create an AGENTS.md file that explains how coding agents should work in a project. Examine its structure and existing configuration, then document setup commands, development workflows, tests, coding conventions, builds, and contribution requirements.
Turn incomplete or intermittent bug reports into a minimal reproduction backed by recorded evidence. Capture the environment, expected and actual results, commands, and remaining unknowns in a brief before diagnosis or repair.
Learn GitHub Copilot CLI through guided lessons, multiple-choice quizzes, and practical scenarios. Track progress with experience points, review commands and settings, and check understanding with a final exam.
Convert Excel workbooks into Markdown tables organized by sheet, preparing their contents for reading, summarizing, searching, or extracting data. The bundled script also extracts embedded pictures and processes folders of workbooks, including subfolders when requested.
Turn feature requirements and technical plans into a structured GitHub project plan. Break work into linked issues, define acceptance criteria, dependencies, priorities, and estimates, and outline board settings and automated progress tracking.
Convert PDF text and tables into Markdown for later summarizing, searching, or data extraction. Embedded images are saved separately and grouped by page in an appendix. Process individual files or entire folders, including subfolders.
Assess an Azure resource using logs and performance measurements, investigate failures and their impact, and produce a prioritized remediation plan with concrete steps, validation procedures, rollback options, and monitoring recommendations.
Refine task prompts through questions about scope, deliverables, constraints, and success criteria. Receive an organized Markdown prompt in chat and on your clipboard, with revisions supported through the Joyride extension.
Create and check Git branch names using Conventional Branch rules. Choose a prefix for the task, normalize the description, detect the repository’s base branch, and create and switch to the new branch.
Explore unfamiliar code with Codebase Memory to map architecture, trace function calls and dependencies, and assess change impact. Findings are checked against source files, with index freshness and coverage considered before drawing conclusions.
Review Python and BigQuery pipelines for excessive costs, duplicate writes on reruns, and hard-to-diagnose failures. Receive a structured assessment with specific function and line references, prioritized fixes, and rough estimates of the largest cost risks.
Compare C# Web API source code with its TypeScript or JavaScript clients to find mismatched data fields, required inputs, and response handling. Receive an audit report showing client impact, severity, and confidence in each match.
Turn a screen recording of repetitive work into automation scripts. The skill reconstructs the workflow, proposes options suited to installed tools, and helps build and test the chosen approach while preserving human review steps.
Investigate AWS production incidents using reusable CloudWatch log queries and metric calculations. Narrow affected resources, compare alarms with deployment events, and reconstruct a timeline to identify changes that may explain the symptoms.
Design Azure infrastructure from plain language or visualize existing resources as interactive diagrams. Refine the architecture through conversation, then generate Bicep infrastructure code, review it, and validate changes before deployment.
Assess an AWS resource using CloudWatch logs and metrics, the measurements that describe its behavior. Investigate failures and performance issues, classify their severity, and produce a remediation report with staged actions, CLI commands, and monitoring recommendations.
Improve LLM prompts using Arize production traces, evaluation results, and human feedback. Extract current instructions, identify recurring failures, revise the prompt, and compare experiments to measure changes in output quality and catch regressions.
Turn code files into learning resources by adding comments that explain syntax, programming concepts, and design choices. Adjust explanation depth and repetition to the reader’s knowledge while preserving file structure, encoding, and syntax.