GitHub organization
Agent skills by github
- skills
- 477
- official
- 477
- repositories
- 5
Repositories by github
- awesome-copilotOfficialCommunity-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.40k stars · 417 skills
- gh-awOfficialGitHub Agentic Workflows5.3k stars · 52 skills
- gh-aw-firewallOfficialGitHub Agentic Workflows Firewall148 stars · 6 skills
- copilot-sdkOfficialMulti-platform SDK for integrating GitHub Copilot Agent into apps and services11k stars · 1 skill
- rust-gemsOfficialA collection of rust algorithms and data structures134 stars · 1 skill
Skills by github, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Drives a real browser from the command line with playwright-cli to open pages, interact, mock requests, save state and work with Playwright tests. | github/ | 5.3k | 23 repos | ~2.8k | Automated safety check: Pass | MIT | today |
| 2 | Creates a Java SDK end-to-end test for the Copilot SDK that runs against a recorded YAML snapshot through a replay proxy, so CI needs no real authentication. | github/ | 11k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 3 | Maps an unfamiliar codebase into seven evidence-backed documents in docs/codebase/, using a scan script and templates, for onboarding or architecture write-ups. | github/ | 40k | 1 repo | ~2.3k | Automated safety check: Pass | MIT | today |
| 4 | Designs and verifies a deterministic grader that measures whether a GitHub Agentic Workflow run reached its real-world or repository outcome. | github/ | 5.3k | — | ~6.8k | Automated safety check: Pass | MIT | today |
| 5 | Designs Azure infrastructure from a natural-language description, or diagrams an existing resource group, then refines the design through conversation and deploys it with Bicep. | github/ | 40k | 1 repo | ~1.9k | Automated safety check: Pass | MIT | today |
| 6 | Generates, edits and validates draw.io files with correct mxGraph XML, covering flowcharts, architecture, sequence, ER and UML class diagrams. | github/ | 40k | 1 repo | ~4.9k | Automated safety check: Pass | MIT | today |
| 7 | Scaffolds, edits, reloads and debugs a canvas extension that the GitHub Copilot CLI can open in its side panel. | github/ | 5.3k | — | ~3.7k | Automated safety check: Pass | MIT | today |
| 8 | Cleans raw credit data and screens variables before loan modeling, dropping unstable, noisy or redundant features and writing an Excel report of every step. | github/ | 40k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | today |
| 9 | Builds a warm, browser-based daily focus board the user updates by talking to their agent, with Eisenhower priorities, a brain-dump box and kind not-today carryover. | github/ | 40k | — | ~3k | Automated safety check: Pass | MIT | today |
| 10 | End-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library to PyPI. | github/ | 40k | 1 repo | ~4.6k | Automated safety check: Pass | MIT | today |
| 11 | Practical Python scripts for debugging awf - parse logs, diagnose issues, inspect containers, test domains | github/ | 148 | — | ~2.6k | Automated safety check: Notes | MIT | today |
| 12 | Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. | github/ | 40k | 1 repo | ~547 | Automated safety check: Pass | MIT | today |
| 13 | Drives an open pull request to merge-ready from inside a GitHub Copilot cloud agent, resolving review threads and local checks concurrently, without merging or retriggering CI. | github/ | 5.3k | — | ~3.8k | Automated safety check: Warn | MIT | today |
| 14 | Bumps gh-aw's pinned gh-aw-firewall version, rebuilds generated artifacts, and flags upstream spec or schema changes that need follow-up work. | github/ | 5.3k | — | ~899 | Automated safety check: Pass | MIT | today |
| 15 | Guide to the console struct tag system in gh-aw: headers, titles, number and cost formats, omitempty, and how structs, slices and maps render in the terminal. | github/ | 5.3k | — | ~736 | Automated safety check: Pass | MIT | today |
| 16 | Regenerate and post-process all agentic workflows. An agent skill from github/gh-aw-firewall. | github/ | 148 | — | ~568 | Automated safety check: Pass | MIT | today |
| 17 | Execute git commit with conventional commit message analysis, intelligent staging, and message generation. | github/ | 40k | 11 repos | ~800 | Automated safety check: Notes | MIT | today |
| 18 | Guides an agent through collecting, planning, addressing and answering pull request review feedback, accepting only comments from Copilot, GitHub Actions and team members. | github/ | 5.3k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 19 | Keep dependencies up-to-date. An agent skill from github/rust-gems. | github/ | 134 | — | ~2.7k | Automated safety check: Pass | MIT | today |
| 20 | Generate Excalidraw diagrams from natural language descriptions. | github/ | 40k | 6 repos | ~6.1k | Automated safety check: Pass | MIT | today |
| 21 | Define and validate GitHub custom agent files, prompts, and examples. | github/ | 5.3k | — | ~4.3k | Automated safety check: Pass | MIT | today |
| 22 | Surgical code refactoring to improve maintainability without changing behavior. | github/ | 40k | 7 repos | ~4.2k | Automated safety check: Pass | MIT | today |
| 23 | Finds, vets and assembles the smallest compatible set of agent skills for a multi-step goal, with local index search, safety checks and staged installation. | github/ | 40k | — | ~2.6k | Automated safety check: Pass | MIT | today |
| 24 | Decide and implement how to support a new LLM provider or agent engine in AWF - either as a proxied provider (api-proxy adapter) or a direct-API engine (domain allowlist only), e.g. | github/ | 148 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 25 | Adds and tests declarative, behavior-defined agentic engines in GitHub Agentic Workflows, touching Go infrastructure only when the declarative model falls short. | github/ | 5.3k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 26 | Turns one contested decision into a validated JSON map of supporting, contradicting, qualifying and missing evidence, with exact source locations. | github/ | 40k | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 27 | Debug the AWF firewall by inspecting Docker containers (awf-squid, awf-agent), analyzing Squid access logs, checking iptables rules, and troubleshooting blocked domains or network issues. | github/ | 148 | — | ~1.2k | Automated safety check: Notes | MIT | today |
| 28 | This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. | github/ | 40k | 3 repos | ~2.6k | Automated safety check: Pass | MIT | today |
| 29 | OpenInference semantic conventions and instrumentation for Phoenix AI observability. | github/ | 40k | 3 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 30 | Patterns and techniques for evaluating and improving AI agent outputs. | github/ | 40k | 4 repos | ~1.5k | Automated safety check: Pass | MIT | today |
| 31 | Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. | github/ | 40k | 6 repos | ~1.1k | Automated safety check: Pass | MIT | today |
| 32 | Build agentic applications with GitHub Copilot SDK. An agent skill from github/awesome-copilot. | github/ | 40k | 5 repos | ~6.3k | Automated safety check: Pass | MIT | today |
| 33 | Guides your agent through diagnosing failed GitHub Agentic Workflows by downloading run logs, auditing individual runs and reading the artifacts they leave behind. | github/ | 5.3k | — | ~3.9k | Automated safety check: Pass | MIT | today |
| 34 | Converts .xlsx workbooks to Markdown with a bundled MarkItDown script so an agent can read, summarize or pull data from spreadsheets, single files or whole folders. | github/ | 40k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 35 | Debug GitHub Actions workflows by downloading logs, analyzing summaries, and understanding how agentic workflows and the AWF firewall work together. | github/ | 148 | — | ~2.7k | Automated safety check: Notes | MIT | today |
| 36 | Manage NuGet packages in .NET projects/solutions. An agent skill from github/awesome-copilot. | github/ | 40k | 3 repos | ~855 | Automated safety check: Pass | MIT | today |
| 37 | Diátaxis Documentation Expert. An agent skill from github/awesome-copilot. | github/ | 40k | 7 repos | ~686 | Automated safety check: Pass | MIT | today |
| 38 | Create, update, and manage GitHub issues using MCP tools. An agent skill from github/awesome-copilot. | github/ | 40k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | today |
| 39 | Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using… | github/ | 40k | 3 repos | ~4.1k | Automated safety check: Pass | Apache-2.0 | today |
| 40 | Create a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure. | github/ | 40k | 4 repos | ~2.1k | Automated safety check: Pass | MIT | today |
| 41 | Development rules for changes to GitHub's gh-aw: tiered validation commands, a command matrix by change type, focused test checks and a merge-main playbook. | github/ | 5.3k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 42 | Analyze Azure resource groups and generate detailed Mermaid architecture diagrams showing the relationships between individual resources. | github/ | 40k | 2 repos | ~2.4k | Automated safety check: Pass | MIT | today |
| 43 | Converts PDF files to Markdown with a bundled MarkItDown-based script before the agent reads, summarizes or extracts from them, and pulls embedded images out separately. | github/ | 40k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 44 | A skill your agent uses whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published IP geolocation feed in CSV… | github/ | 40k | 1 repo | ~12k | Automated safety check: Pass | Apache-2.0 | today |
| 45 | Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. | github/ | 40k | 1 repo | ~664 | Automated safety check: Pass | MIT | today |
| 46 | Open a GitHub PR dashboard in the browser. An agent skill from github/awesome-copilot. | github/ | 40k | 1 repo | ~524 | Automated safety check: Pass | MIT | today |
| 47 | Diagnose an AWF (Agentic Workflow Firewall) failure from an error, workflow run URL, or symptom. | github/ | 148 | — | ~829 | Automated safety check: Pass | MIT | today |
| 48 | Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. | github/ | 40k | 2 repos | ~4.6k | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill by github?
playwright-cli Browser Automation (official) from github/gh-aw ranks first of the 477 skills by github listed here, with the highest score: its repository has 5.3k GitHub stars, 23 other GitHub owners carry a copy, its SKILL.md loads about 2.8k tokens and it passes the automated safety check with no findings. Next come Java SDK E2E Test with Replay Snapshot and Acquire Codebase Knowledge.
Are github's skills official?
477 of the 477 skills by github are official, published by the vendor's own GitHub organization: playwright-cli Browser Automation, Java SDK E2E Test with Replay Snapshot, Acquire Codebase Knowledge, Operational Value Designer, Azure Architecture Autopilot and 472 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.