mikeyobrien/ralph-orchestrator
18 skills
$npx skills add mikeyobrien/ralph-orchestratorSkillInstalls
code-assistGuides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow.code-task-generatorGenerates structured .code-task.md files from descriptions or PDD implementation plans.complex-test-skillA directory-style test skill for smoke testingevaluate-presetsUse when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.find-code-tasksLists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.pddTransforms a rough idea into a detailed design document with implementation plan.playwriterBrowser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.pr-demoUse when creating animated demos (GIFs) for pull requests or documentation.ralph-docsIntrospect, explain, and improve Ralph Orchestrator using its published llms.txt doc map.ralph-hatsCreate, inspect, validate, explain, and improve Ralph hat collections.ralph-loopRun, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover…ralph-tools../../../crates/ralph-core/data/ralph-tools.mdrelease-bumpUse when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publishreview-prUse when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URLtest-driven-developmentUnified TDD skill with three input modes — from spec, from task, or from description.tmux-terminalInteractive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows.tui-debug-in-paneUse when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and…tui-validateValidates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation.