PreToolUse
01Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing gh-permission-hook.py and python-permission-hook.py (2 commands). From dyad-sh/dyad.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing gh-permission-hook.py and python-permission-hook.py (2 commands). From dyad-sh/dyad.
Hook Claude Code
Runs when a session starts, running npm install. From dyad-sh/dyad.
Settings file Claude Code
Agent settings declaring 2 hook events (PreToolUse, SessionStart) and 127 allowed tools.
Skill Claude CodeCodex
Add one or more AI models to the language model constants file, researching specs from official docs.
Skill Claude CodeCodex
Check GitHub Actions workflow runs from the past day, identify severe or consistent failures, and file an issue if actionable problems are found.
Skill Claude CodeCodex
Map a minified error stack trace from a production Dyad build back to original source locations using source maps.
Skill Claude CodeCodex
Debug E2E tests by taking screenshots at key points to visually inspect application state.
Skill Claude CodeCodex
Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported. Local equivalent of /code-review ultra. Use when the user asks for a deep, thorough, or multi-agent review of their…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Identify and fix flaky E2E tests by running them repeatedly and investigating failures.
Skill Claude CodeCodex
Rebase E2E test snapshots based on failed tests from the PR comments.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Create a plan to fix a GitHub issue, then implement it locally.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Create a plan collaboratively with the user, then convert the approved plan into a GitHub issue.
Skill Claude CodeCodex
Diagnose and fix failing CI checks on a pull request from its latest GitHub Actions CI run. Use when PR CI has E2E/Playwright failures, macOS or Windows unit-test failures, or presubmit/type/build failures; analyzes the exact run logs and artifacts, invokes dyad:deflake-e2e-from-run for E2E failures, reproduces…
Skill Claude CodeCodex
Read all unresolved GitHub PR comments from trusted authors and address or resolve them appropriately.
Skill Claude CodeCodex
Address all outstanding issues on a GitHub Pull Request by handling both review comments and failing CI checks.
Skill Claude CodeCodex
Publish local work by committing changes, running checks, pushing the branch, and creating or refreshing a GitHub PR with a reviewer-useful description.
Skill Claude CodeCodex
Rebase the current branch on the latest upstream changes, resolve conflicts, and push.
Skill Claude CodeCodex
Record a visual demonstration of the key feature of this PR using screenshots and add it as a new comment to the PR.
Skill Claude CodeCodex
Promote the latest pre-release to a stable release by creating a release branch, bumping the version, and pushing.
Skill Claude CodeCodex
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.