all-agents

Walk through a milestone GUIDE.md with agent-browser, testing every step. Fixes code bugs and guide inaccuracies as they're found. Use when user asks to "test the guide", "run guide and fix", "validate guide", or "run-guide-and-fix".

Generate a comprehensive GUIDE.md for a project milestone. Use when user asks to "write guide", "generate guide", "create demo guide", or "write-guide". Analyzes milestone stories, git changes, and project setup to produce a step-by-step demo guide.

Complete reference for using the All Agents CLI (`aaa`). Use this skill whenever the user asks to run an aaa command, wants to plan/build/review with Ralph, needs to know the right CLI invocation, asks about available commands or flags, mentions 'aaa', 'ralph', 'subtasks', 'milestones', 'cascade', or needs help constructing any `aaa` CLI command. Also trigger when user says things like 'plan stories', 'build the queue', 'check status', 'review subtasks', 'run calibration', or any development workflow task that maps to an aaa command.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Create Obsidian .canvas files programmatically with correct format. Use when user asks to "create canvas", "make canvas", "canvas file", "obsidian canvas", or needs to generate a .canvas for Obsidian.

Run Ralph calibration checks to analyze intention drift, technical quality, and self-improvement opportunities. Use when user asks to "ralph calibrate", "check drift", "analyze sessions", or needs to verify work alignment.

Audit and repair aaa ralph command examples in this repo's prompts using LLM-as-judge backed by the live CLI command table. Use when user asks to find prompt drift, stale Ralph commands, or sync prompt examples with current CLI syntax.

Set up lint-staged for optimized pre-commit validation in a target repository. Use when user asks to setup lint-staged or optimize pre-commit.

Interactive vision planning using Socratic method. Use when user asks to "ralph plan vision", "plan a vision", "ralph plan roadmap", "ralph plan stories", "ralph plan tasks", or needs to define product vision/roadmap/stories/tasks through guided dialogue.

Run Ralph autonomous build loop. Use when user asks to "ralph build", "run build loop", or needs to process subtasks autonomously. Executes iterations against a subtasks.json queue.

Display Ralph build status and progress. Use when user asks for "ralph status", "build status", "queue status", or wants to see subtask progress and iteration statistics.

Interrogate code changes to surface decisions, alternatives, and confidence levels. Use when user asks to "interrogate", "what decisions", "hardest part", "alternatives", or wants to understand the reasoning behind code changes.

Interactive review of auto-generated Ralph artifacts. Use when user asks to "ralph review stories", "ralph review tasks", "ralph review roadmap", or needs to validate planning artifacts against their intent.

CLI Feature Creator wizard for adding new aaa CLI commands. Use when user asks to "add aaa command", "create CLI feature", "add CLI command", or needs to extend the aaa CLI with new functionality.

Orchestrate parallel code review using specialized reviewer agents. Spawns 11 reviewers in parallel, synthesizes findings, and presents for triage. Use when user wants comprehensive multi-agent code review.

Create/update atomic documentation (blocks, foundations, stacks). Use when user asks to "create atomic doc", "add a block", "add a foundation", "setup a stack", or needs to document reusable knowledge. Creates files in context/ following SWEBOK-aligned structure.

Analyze documentation needs with tiered approach. Use when user asks to "analyze docs", "find missing docs", "plan documentation", "what docs do I need", or needs to understand documentation coverage for a domain or feature.

Search GitHub for code examples and patterns. Use when user asks to "search GitHub", "find examples on GitHub", "how do people implement X", or needs real-world code patterns.

Present items one at a time for focused review. Use when user asks to "walk through", "step through", "present one by one", or needs to review a list interactively.

Facilitate structured brainstorming using parallel sub-agents to explore idea spaces. Use for IDEATION/CONCEPTUAL WORK ONLY, NOT for implementation planning or task breakdown. Use when user wants to brainstorm, explore ideas, generate concepts, develop vision, or discover creative directions. Transforms vague ideas into practical, tangible expressions through 5 rounds of parallel agent analysis and refinement.

Scan ~/dev recursively for git repos and report today's work with commits, branches, stats, and detailed change analysis. Use when user asks "what did I work on", "show my work", "daily summary", "what repos did I touch".