opencode

Author runnable TypeScript workflows for OpenCode. Use when creating reusable executable flows under .opencode/workflows or when asked how to write, structure, debug, or invoke a workflow. Triggers on: write a workflow, create workflow, workflow authoring, /workflow, .opencode/workflows.

Run an ultrawork test-fix loop: read the ledger, select the highest-priority unresolved failure, diagnose and fix it, verify it, update the ledger, and continue until all entries are fixed or a blocking escalation stops the run. Use when you need to keep fixing test failures from a ledger. Triggers on: test-fix-round, test-fix-loop, fix test ledger, fix next test, ultrawork test fix.

Review OpenTUI/Solid TUI code for invalid text renderables that can crash TextNodeRenderable handling.

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

Run typecheck and build, extract only errors, and return a concise pass/fail report. Use before tests to catch compile/resolve errors early. Triggers on: build-verify, verify build, check build, typecheck.

Run tests, parse output, and produce a structured failure report with dual verification. Use when you need to analyze test failures, diagnose broken tests, or generate a failure report. Triggers on: test-analyze, analyze tests, test failures, test report, diagnose tests.

Compare and sync oh-my-opencode (OMO) changes into the codebase. Fetches latest OMO from npm, runs diff against baseline, generates a backport plan, and applies changes incrementally. Triggers on: omo-sync, sync omo, oh-my-opencode sync, omo update, backport omo.

Sync local master branch with upstream/dev: fetch, analyze, integrate upstream changes, and re-apply custom features. Phased workflow with ledger tracking to survive context limits. Triggers on: upstream-sync, sync upstream, update from upstream, rebase on upstream.

Atomic commit generation with conventional commit enforcement, interactive staging, and smart commit message drafting

Browser automation for testing with Playwright - navigate pages, interact with elements, take screenshots, and verify UI behavior

Run tests, parse output, and produce a structured failure report with dual verification. Use when you need to analyze test failures, diagnose broken tests, or generate a failure report. Triggers on: test-analyze, analyze tests, test failures, test report, diagnose tests.

Execute a single test-fix cycle: read ledger, select highest-priority discovered failure, diagnose and fix it, verify, and update ledger. Use when you need to fix one test failure at a time. Triggers on: test-fix-round, fix one test, fix next test, single fix round.

Generate a final Markdown fix report from the test-fix ledger. Reads the ledger JSON, summarizes fixes and escalations, verifies ledger integrity, and saves the report. Triggers on: test-fix-report, fix report, generate report, test report from ledger.