dyad

Commit any uncommitted changes, run lint checks, fix any issues, and push the current branch.

Root-cause flaky or failing E2E tests from a specific CI run by downloading and analyzing the Playwright HTML report (traces, screenshots, errors). Use this when given a GitHub Actions run URL and asked to investigate failures. Diagnose from report artifacts first, then rebuild and rerun the affected E2E tests locally after making fixes.

Fix failing CI checks and GitHub Actions on a Pull Request.

Read all unresolved GitHub PR comments from trusted authors and address or resolve them appropriately.

Automatically gather flaky E2E tests from recent CI runs on the main branch and from recent PRs by wwwillchen/keppo-bot/dyad-assistant, then deflake them.

Promote the latest pre-release to a stable release by creating a release branch, bumping the version, and pushing.

Map a minified error stack trace from a production Dyad build back to original source locations using source maps.

Add one or more AI models to the language model constants file, researching specs from official docs.

Check GitHub Actions workflow runs from the past day, identify severe or consistent failures, and file an issue if actionable problems are found.

Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are validated using reasoned analysis rather than simple vote counting. Reports merge verdict (YES / NOT SURE / NO). Automatically deduplicates against existing PR comments. Always posts a summary (even if no new issues), with low priority issues in a collapsible section.

Commit any uncommitted changes, run lint checks, fix any issues, and push the current branch. Delegates to a haiku sub-agent for speed.

Create a plan to fix a GitHub issue, then implement it locally.

Address all outstanding issues on a GitHub Pull Request by handling both review comments and failing CI checks.

Swarm planning session with PM, UX, and Engineering agents who debate an idea, ask clarifying questions, and produce a detailed spec written to plans/$plan-name.md.

Debug E2E tests by taking screenshots at key points to visually inspect application state.

Identify and fix flaky E2E tests by running them repeatedly and investigating failures.

Rebase E2E test snapshots based on failed tests from the PR comments.

Turn customer feedback (usually an email) into discrete GitHub issues. Checks for duplicates, proposes new issues for approval, creates them, and drafts a reply email.

Run pre-commit checks including formatting, linting, and type-checking, and fix any errors.

Create a plan collaboratively with the user, then convert the approved plan into a GitHub issue.

Rebase the current branch on the latest upstream changes, resolve conflicts, and push.

Record a visual demonstration of the key feature of this PR using screenshots and add it as a new comment to the PR.

Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

Team-based PR review using Claude Code swarm. Spawns three specialized teammates (correctness expert, code health expert, UX wizard) who review the PR diff, discuss findings with each other, and reach consensus on real issues. Posts a summary with merge verdict and inline comments for HIGH/MEDIUM issues.