mikeyobrien/ralph-orchestrator

DirSkills catalogs 20 skills from this repository, across 4 categories: AI Engineering, Automation, DevOps, Quality.

3.1K stars285 forksView on GitHub
๐Ÿงช
2w ago

Code Assist

Code Assist guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. It acts as a technical implementation partner and TDD coach, following existing patterns and avoiding over-engineering.
AI Engineering
3.1K285
๐Ÿ“‹
2w ago

Code Task Generator

Code Task Generator creates structured .code-task.md files from rough descriptions or PDD implementation plans. It auto-detects input type and generates tasks with Given-When-Then acceptance criteria, requiring user approval before writing files.
Automation
3.1K285
๐Ÿงช
2w ago

Complex Test

Complex Test validates directory-based skill discovery (the */SKILL.md pattern) for smoke testing.
Quality
3.1K285
๐Ÿงช
2w ago

Evaluate Presets

Evaluate Presets runs shell scripts to test Ralph's hat collection presets, validating configurations and auditing the preset library for bugs and UX issues.
Quality
3.1K285
๐Ÿ“‹
2w ago

Find Code Tasks

Find Code Tasks lists all code tasks in a repository with their status, dates, and metadata. It helps you get an overview of pending work or find tasks by status.
Automation
3.1K285
๐ŸŽฌ
2w ago

PR Demo

PR Demo creates polished terminal demos for pull requests and documentation by recording with asciinema and converting to GIF or SVG for GitHub embedding.
Automation
3.1K285
๐ŸŽญ
2w ago

Playwriter

Playwriter runs Playwright Page scripts against a local Chrome session, preserving logins, cookies, and extensions. Use it for testing authenticated web dashboards, browser extension flows, and accessibility snapshot discovery.
Automation
3.1K285
๐Ÿ“‹
2w ago

Prompt-Driven Development

Prompt-Driven Development turns a rough idea into a detailed design document and implementation plan. It guides iterative requirements clarification, research, design, and planning, producing spec-driven artifacts without writing code.
AI Engineering
3.1K285
๐Ÿ“š
2w ago

Ralph Docs

Ralph Docs helps agents answer questions about Ralph Orchestrator's internals by consulting its published llms.txt documentation map instead of guessing. Use it to debug failures, explain behavior, and scope code changes from authoritative docs.
AI Engineering
3.1K285
๐ŸŽฉ
2w ago

Ralph Hats

Ralph Hats creates, inspects, validates, and improves Ralph hat collections for multi-hat agent workflows. Use it when making or refining .ralph/hats/*.yml files, debugging hat routing, explaining event topology, or tuning a Ralph run.
AI Engineering
3.1K285
๐Ÿ”„
2w ago

Ralph Loop

Ralph Loop operates Ralph loops from the CLI: start or continue runs with the right configs, inspect state and diffs, resume suspended loops, and merge or discard completed worktree loops. Use it whenever you need to run, monitor, recover, or debug Ralph loops and merge queues.
AI Engineering
3.1K285
๐Ÿค–
2w ago

Ralph Tools

Ralph Tools orchestrates multiple AI coding agents across CLIs like Claude Code, Codex, and Gemini, letting a developer run and manage them from one place.
AI Engineering
3.1K285
๐Ÿš€
2w ago

Release Bump

Release Bump updates version numbers across a Rust workspace Cargo.toml, runs cargo build and cargo test, then commits, pushes, and tags to trigger CI release. Use after fixes are committed and ready to publish.
DevOps
3.1K285
๐Ÿ”
2w ago

Review PR

Review PR runs the ralph.reviewer.yml orchestration loop against a pull request, checking out the PR in an isolated worktree, running tests, reviewing the diff, and producing a structured report. Use it when asked to review a PR or a GitHub pull request URL.
Quality
3.1K285
๐Ÿค–
2w ago

Robot Interaction

Robot Interaction enables an AI agent to send non-blocking progress updates and ask blocking questions to a human via Telegram, with clear rules for when to ask versus proceed. Use it for ambiguous, irreversible, or high-risk decisions that need human input.
AI Engineering
3.1K285
๐Ÿž
2w ago

TUI Debug in Pane

TUI Debug in Pane launches ralph in a tmux split pane to reproduce and debug TUI rendering issues like garbled output, broken streaming, or layout corruption. Use it when you need to capture live output while keeping your main pane free for inspection commands.
Quality
3.1K285
๐Ÿ”
2w ago

TUI Validate

TUI Validate validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual and text-based validation modes.
Quality
3.1K285
๐Ÿงช
2w ago

Test

Test is a minimal skill used to verify the skills discovery and injection pipeline in Ralph Orchestrator. It provides a smoke test for the system, confirming that skills load correctly when triggered.
Quality
3.1K285
๐Ÿงช
2w ago

Test-Driven Development

Test-Driven Development guides test-first development from specs, task files, or descriptions, enforcing red-green-refactor cycles with pattern discovery, proptest guidance, and coverage evidence for Rust codebases.
Quality
3.1K285
๐Ÿ–ฅ๏ธ
2w ago

Tmux Terminal

Tmux Terminal drives interactive terminal sessions using tmux to send keystrokes, capture screen output, and manage long-running CLI or TUI workflows.
Automation
3.1K285