otrebu

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.

Delegate one or more coding tasks to background worker agent-CLI sessions (claude by default; codex, gemini, or any other agent CLI via profiles) and babysit them — spawn each in its own tmux pane or cmux workspace, send a prompt, poll/wait for completion, collect the result, then stop. Use when the user says "spin up a worker / sub-agent to do X", "run these in parallel", "fan this out", "delegate X while I keep working", "drive another claude / codex / gemini", or otherwise wants long-running tasks handled by separate agent instances you supervise. SAFETY: workers run in full-auto mode (e.g. claude --dangerously-skip-permissions — no per-action approval) in whatever directory you point them at — only use on repos/dirs the user trusts you to modify autonomously, and surface NEEDS_INPUT to a human rather than auto-answering.

Shape every reply to the smallest complete answer. Right-size to the ask — trivial asks get one bare sentence; bigger asks get a bottom-line verdict then the tightest fitting structure (table, steps, code, or a small ASCII diagram), with a leading index of headlines only when the answer runs ~4+ sections. Use on every turn to keep replies short and scannable.

Present a list of items one at a time for focused, interactive review — each with enough context to act on, then wait for the user before advancing. Use when the user wants to step through items one at a time, or hands over findings / tasks / suggestions / a file of items to review interactively rather than as a wall of text.

Maintain a persistent visual work tree in an Obsidian Canvas as you (and the agents you're driving) branch into sub-problems, decisions, and dead ends across sessions. Resolves which canvas to use per project, tracks a small active set (1–3 nodes you're working on now — the 👉 primary is the attach anchor), and keeps the layout tidy. Use when the user says "add to the tree/canvas", "branch off X", "focus on Y", "also working on Z", "mark X active", "done with X", "new topic X", "close / finish the X topic", "tidy the tree", "where was I", "what was I doing", "I lost my place", or otherwise wants to capture / navigate the shape of an ongoing investigation.

Publish HTML artifacts (mockups, demos, reports, prototypes) from a local folder tree to a Cloudflare-hosted site at ubuilt.dev, preserving the folder structure as URL paths, with per-folder access control — some folders public, others gated behind email one-time-PIN for named collaborators who need no Cloudflare account. Additive and multi-machine safe: every publish reconciles against live Cloudflare state (R2 objects + Access apps) and never clobbers what another machine pushed. Use when the user says "publish this artifact / mockup / prototype", "share this with <person>", "put this folder behind email auth", "publish to ubuilt.dev", "make this folder public / protected", "unpublish X", or otherwise wants to deploy an HTML tree to their Cloudflare artifacts site and control who can see each part.

Investigate a given topic against the codebase, docs, and (when relevant) the web, then — only if it surfaces a concrete action that can't be resolved right now — draft a lean, assertive GitHub issue and create it for the relevant repo via the gh CLI after the user confirms. Use when the user hands over a topic, idea, or question to look into and may want it captured as an actionable ticket — e.g. "look into X and open an issue if needed", "investigate Y", "should this become a ticket?".

Shape every assistant reply. Simple questions → terse direct answer, freeform. Complex / multi-topic / process answers → open with headlines + one-line summaries, optionally an ASCII visual (diagram, mockup, table, flow) when order or layout matters, then short detail sections that each say what was understood, how it was done, and (when non-obvious) why. Use on every turn to keep replies scannable and aligned.

Audit a plan vs an implementation. Build an interactive HTML checklist of end-user acceptance criteria, then spawn parallel agents to verify each item against the actual code. Use when validating whether a built feature matches its stated plan, stories, tasks, or subtasks — or when you need a copy/paste-friendly feedback artifact tied to the plan.