Create and manage coding tasks for GitHub Copilot from the command line. The skill covers writing clear implementation requests, listing and updating sessions, and connecting task creation to automated GitHub workflows that produce pull requests for review.
Find and review pull requests created with GitHub Copilot using author searches, branch names, and Git history. Follow practical checks for changes and tests, and export request lists to CSV to track contributions.
Turn a code pattern fixed in a pull request into a custom Go linter, a tool that checks code without running it. Covers a focused detection rule, tests, and registration in the linter runner.
Helps agents work within gh-aw tool restrictions by checking the allowlist, diagnosing denied calls, and choosing permitted alternatives. It guides agents to complete available work and report specific limitations before repeated denials end the session.
Automate browser tasks such as clicking, filling forms, and navigating tabs. Inspect page structure, console messages, and network requests, and capture screenshots or recordings to support web testing, debugging, and UI feedback.
Handle pull request review feedback by collecting comments, grouping requests, planning fixes, and validating changes before replying. The workflow covers team members and trusted GitHub automation, with individual replies and resolution of addressed discussion threads.
Prepare an open pull request for human merging from a GitHub Copilot cloud agent. Address review threads, validate changes locally, resolve branch conflicts, and report remaining blockers, including the need for a human to rerun CI.
Build and troubleshoot canvas extensions displayed in the GitHub Copilot app's side panel. Follow guidance for scaffolding, implementing actions and inputs, preserving state, matching app themes, and checking behavior through canvas tools and extension logs.
Guide gh-aw release preparation and assess whether command-line changes break existing usage. The reference covers changesets, which record release changes, version previews, release steps, firewall log classification, and summaries of Go module usage.
Add custom Go code checkers to gh-aw, with guidance on tests, registration, and running all checks. Handle equivalent syntax consistently and optionally limit performance rules using test coverage, which records which code tests execute.
Query GitHub pull requests by author, status, or review needs, and extract selected fields as JSON. Inspect the data structure and size first, then use jq, a JSON filtering tool, to refine results.
Query GitHub Discussions and extract titles, authors, categories, or answer status. First inspect the data structure and size, then use jq, a JSON filtering tool, to select relevant discussions, sort updates, or count entries by category.
Retrieve labels from a GitHub repository, filter their names by partial matches, and choose page sizes and page numbers. Results arrive as JSON, including label names, colors, descriptions, and pagination details.
Review GitHub agentic workflows, automated workflows guided by AI agents, for security and correctness. Compile changes, inspect permissions and safeguards, and use available run logs to identify supported improvements to cost and execution time.
Analyze gh-aw execution traces, which record individual processing steps, to investigate slow or failing workflows. Using local JSONL files or telemetry backends, the skill checks timing, errors, missing attributes, and trace connections to support focused improvements.
Implement HTTP headers that pass GitHub Actions secrets through environment variables in gh-aw’s copilot engine. This reference explains secret extraction, generated MCP configuration, execution-step settings, and tests for keeping secret values out of configuration files.
Review regular expressions used to detect errors in agent engines. Check for empty matches, test patterns against real logs, and add safeguards against repeated matches that can cause JavaScript loops to hang.
Analyze token usage and AI costs in GitHub Agentic Workflows, identify expensive steps and budget or timeout failures, and develop prioritized improvements checked against the original workflow’s output quality.
Implement and test Go codemods, automated migration routines used by gh aw fix. The guide covers targeted configuration changes, preserving comments and document content, safe repeated execution, and checks for registration and execution order.
Inspect JSON files or API responses with jq and produce a compact map of keys and value types. Use the result to understand nested data before writing queries or processing the full dataset.
Use concrete JSON and Markdown examples to structure Sergo tool caches, strategy histories, improvement tasks, and reports. The templates show which fields to record and how to organize findings for review.
Design error recovery for gh-aw workflows, including failed installations and API calls. Define retry limits, increasing wait times, error categories, and debug logs to handle temporary failures and prevent endless retries.
Write and edit gh-aw documentation using Diátaxis, a framework that separates learning, task instructions, reference, and explanations. Apply Astro Starlight Markdown conventions while keeping examples focused and removing repeated or unnecessary content.
Use this reference to configure GitHub access for AI agents through MCP, a protocol for connecting agents to tools. Covers tool selection, authentication, read-only access, and migration of existing workflow settings.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)