
Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, hats, memories, tasks, backends, presets), debug an unfamiliar failure mode, or propose a code change to the ralph-orchestrator repo. The skill teaches the agent to discover authoritative answers from the live docs via llms.txt before guessing, and to scope improvements through the published architecture rather than the local checkout alone.
Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows.
Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly formatted tasks with Given-When-Then acceptance criteria.
Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.
Transforms a rough idea into a detailed design document with implementation plan. Follows Prompt-Driven Development — iterative requirements clarification, research, design, and planning.
Shared tool commands for interact, skill, and output format reference during Ralph orchestration
Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL
Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.
Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a `.ralph/hats/*.yml` workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph run.
Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.
Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.
Use when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publish
Use 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 capturing live output.
A directory-style test skill for smoke testing
Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptest guidance and backpressure integration.
Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
Run, 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 suspended loops, analyze diagnostics, or unblock merge queue issues.
Install and configure Rho from scratch (Doom-style init.toml + sync). Only prereq: a coding agent that can run shell commands.
Search across pi session JSONL logs (user prompts, tool calls, results). Uses the session-digest tool and ripgrep for fast triage.
Analyze a repository and generate comprehensive architecture and workflow documentation.
Execute a completed PDD implementation plan step-by-step with validation gates.
Transform a rough idea into a detailed design document and implementation plan.
Open URLs, files, and applications on macOS. Use for launching browsers, opening documents, or starting apps.
Implement coding tasks with an explore-plan-code workflow and explicit verification gates.
Text-to-speech on Linux -- make the device speak text aloud. Use for voice announcements, reading content aloud, or accessibility.
Read and send SMS messages. Use for checking texts, 2FA codes, or sending SMS alerts.
Get device location via GPS or network. Use for location-aware actions, finding nearby places, or logging position.
Open URLs and launch apps on Android. Use for opening links in a browser, launching specific apps, or viewing files.
Access phone contacts and call log. Use for looking up contact info or checking recent calls.
Run a curiosity-driven explore-and-build loop to ship one useful improvement.
Show system notifications with optional buttons, sounds, and actions. Use for alerts, reminders, or persistent status messages.
Generate structured .code-task.md files from rough descriptions or PDD plans.
Manage agent email at [email protected] via the Rhobot Mail API. Use when checking inbox, reading messages, sending email, or managing allowed senders. Requires credentials from rho-cloud-onboard.
Create Tasker profiles and tasks via XML for Android automation. Use when adding new Tasker functionality, creating Intent Received handlers, or building automation that integrates with the rho.tasker extension.
Read or write the macOS clipboard. Use when copying/pasting text, transferring data between apps, or accessing clipboard contents.
Show macOS system notifications with title, body, and optional sound. Use for alerts, reminders, or status updates.
Device controls — vibration, torch, volume, battery status, toast messages. Use for haptic feedback, flashlight, or quick status checks.
Text-to-speech on macOS -- make the device speak text aloud. Use for voice announcements, reading content aloud, or accessibility.
Extract durable learnings and preferences from conversations for automatic memory capture.
Read or write the system clipboard. Use when copying/pasting text, transferring data between apps, or accessing clipboard contents.
Read or write the Linux clipboard. Use when copying/pasting text, transferring data between apps, or accessing clipboard contents.
Create a new SOP-style skill as skills/<name>/SKILL.md with kind: sop frontmatter and structured Parameters/Steps sections.
Show interactive dialogs for user input — text, confirmations, choices, date/time pickers. Use when you need user input beyond chat.
Plan and run conversational AI agent evaluations with test generation and analysis.
Play audio files, record from microphone, take photos. Use for media playback, voice recording, or camera capture.
Consolidate brain memory and mine user sessions since the last consolidation checkpoint (sleep-cycle style). Use to reduce noisy prompt injection while preserving durable high-value memories.
Show Linux desktop notifications with title, body, urgency, and icons. Use for alerts, reminders, or status updates.
Open URLs, files, and directories on Linux using default applications. Use for launching browsers, opening documents, or viewing files.
Register an agent email address on Rhobot Mail ([email protected]). Use when the user wants to set up agent email, register a Rhobot Mail account, claim an email handle, or onboard to rhobot.dev.
Speech-to-text — transcribe voice to text using device microphone. Use for voice commands, dictation, or hands-free input.
Text-to-speech — make the device speak text aloud. Use for voice announcements, reading content aloud, or accessibility.
Update the pi-coding-agent npm package to the latest version. Use when the user wants to update pi, upgrade pi, or get the latest version of the coding agent.
Detect and resolve orphaned notes in the vault. Use during heartbeat maintenance or when vault status shows orphans. Finds notes with no inbound wikilinks and either connects them to the graph or flags them for cleanup.
Keep CHANGELOG.md idiomatic (Keep a Changelog) and cut a tag-based GitHub release that triggers npm publish CI.