gh-workflow

Use after receiving PR review feedback to systematically address comments, verify fixes, and re-request review

Use after making changes to commit with context-aware classification that flags out-of-context modifications before committing

Explore what AI built — loads decision journal, diff, and issue context for interactive Q&A

Use when needing to create a new GitHub issue to gather requirements, check for duplicates, and create solution-agnostic issues

Use after PR is approved to merge with safe defaults, verification checks, and optional branch cleanup

Use when ready to create a PR to run full code review, convention checks, and get reviewer suggestions before PR creation

Use when ready to release to create a git tag, generate changelog from merged PRs, and create GitHub release

Use to resolve merge conflicts on the current branch or for a pull request — detects conflict types, analyzes both sides, applies per-file resolution strategies, and verifies the result

Use when assigned as reviewer or proactively reviewing PRs to perform multi-faceted code review with prioritized findings

Use to perform a dedicated security review of current branch changes before pushing

Use to set up or update gh-workflow in a repository - analyzes tech stack, detects conventions, generates workflow configuration, and upgrades existing installations to latest version

Autonomous issue-to-PR pipeline with iterative review-fix loops until zero findings — assigns issue, implements, reviews, addresses all findings, and creates PR

Use to start work on a GitHub issue - assigns issue, creates branch, guides implementation with task tracking, and prepares for PR

Use to get a quick overview of assigned issues, open PRs, and pending review requests

Use proactively after code changes to review for quality, security, edge cases, and error handling. Use when performing self-review before PR creation or during PR review.

Use when validating Git conventions including commit messages, branch naming, PR format, and issue linkage. Use during PR review or before creating a PR.

Use when starting work on a GitHub issue to parse acceptance criteria and create a task breakdown. Use to establish implementation order and track progress.

Use to discover and run project-specific lint, test, and type-check commands. Use after code changes to verify quality gates pass before PR creation or merge.

Discovers available agents, skills, quality commands (lint, test, typecheck), and tech stack in the project environment. Use when starting implementation, creating PRs, reviewing PRs, or addressing feedback to determine which agents to dispatch and which quality commands to run. Use before workflow execution to adapt gh-workflow commands to project-specific tooling.

Generates architecture narratives and requirements adherence reports from diffs, decision journals, and issue context. Use when creating PR bodies that need comprehension reports. Use when validating that implementation meets acceptance criteria or when humans need to understand what AI built and why.

Extracts and structures development decisions from diffs, manages decision journal entries, and detects human gate triggers. Use when logging decisions during gh-start, gh-commit, or gh-address. Use when summarizing decisions for PR bodies or when checking for gate-triggering changes like new dependencies, security modifications, or scope deviations.

Detect, classify, and resolve git merge conflicts through structured analysis of conflict markers, per-file strategy selection, and post-resolution verification. Use when a branch has conflicts with its merge target, when rebasing onto an updated base, or when gh-merge detects an unmergeable PR.

Provides dynamic repository configuration patterns for gh-workflow agents. Use when an agent needs the default branch name for diffs, the repository owner/name for API calls, or branch naming and commit conventions for validation.

Verifies implementation works at runtime by discovering and executing dev server startup, API smoke tests, E2E tests, and browser checks. Use after quality checks pass (lint, test, typecheck) to confirm the code actually runs. Use when validating acceptance criteria, running Playwright or Cypress suites, or smoke-testing endpoints before PR creation.

Suggests reviewers for PRs and assignees for issues by ranking users based on CODEOWNERS match, file expertise, recent activity, and workload balancing. Use when creating PRs to suggest reviewers, creating issues to suggest assignees, or re-requesting review after addressing comments.