otrebu
- 27 skills
- 0 followers
- 6 hours ago last updated
- ▌ Orchestrate · otrebu bundleSupervise detached agent-CLI workers through a run-scoped tmux or cmux control loop.
- ▌ Walkthrough · otrebu bundlePresent 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.
- ▌ Tmp Snapshot · otrebu bundleSave content from the current conversation to /tmp/<descriptive-kebab-name>.md, then return the absolute path and an outline (every header with a one-line summary). Use when the user says "save this to /tmp", "snapshot this", "dump the X part", "stash this", "save the discussion about Y", or otherwise asks to drop content from the chat into a quick scratch markdown file.
- ▌ Concise Replies · otrebu bundleShape replies 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 only when the user names this skill or asks for this reply style.
- ▌ Favorite Harness · otrebu bundleLook up the user's preferred coding-agent harness, model, effort, and autonomous launch command. Use when choosing or launching a coding agent or when another routing skill needs defaults; do not use as an orchestration workflow.
- ▌ Work Tree Canvas · otrebu bundleMaintain 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.
- ▌ Maintain LLM Wiki · otrebu bundleMaintain a compounding LLM wiki that integrates immutable sources into an interlinked, agent-owned knowledge base. Use when setting up a persistent markdown wiki, ingesting sources into it, answering or filing cited wiki queries, or linting the wiki for contradictions, staleness, gaps, and broken links.
- ▌ Publish Artifacts · otrebu bundlePublish 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.
- ▌ Theory Vs Reality · otrebu bundleAudit 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.
- ▌ Native Tools First · otrebu bundleRight-size non-trivial technical plans and implementations around existing libraries, CLIs, platform features, standards, workflows, and repository utilities before adding custom code. Use when a solution could duplicate native capabilities or drift into an oversized framework; skip trivial edits and tightly specified implementations.
- ▌ Structured Replies · otrebu bundleShape assistant replies. 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 only when the user names this skill or asks for this reply style.
- ▌ Fable Orchestration · otrebu bundleLet Fable 5.1, xhigh choose how to orchestrate work with ultracode and appropriately capable subagents.
- ▌ Herdr Orchestration · otrebu bundleOrchestrate agent workers through Herdr from any host agent, with capability-based routing, supervised integration, and scoped cleanup.
- ▌ Fable Herdr Orchestration · otrebu bundleOrchestrate Fable and Codex workers through Herdr with explicit model and effort routing.
- ▌ Handoff That To Agent Pane · otrebu bundleHand off a bounded task to a chosen coding agent in a right-hand Herdr pane using a conversation snapshot.
- ▌ Ralph Plan · otrebuInteractive 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.
- ▌ Code Review · otrebuOrchestrate 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.
- ▌ Ralph Build · otrebuRun 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.
- ▌ Write Guide · otrebuGenerate 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.
- ▌ Ralph Status · otrebuDisplay 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.
- ▌ Obsidian Canvas · otrebuCreate 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.
- ▌ Ralph Calibrate · otrebuRun 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.
- ▌ Run Guide And Fix · otrebuWalk 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".
- ▌ Setup Lint Staged · otrebuSet up lint-staged for optimized pre-commit validation in a target repository. Use when user asks to setup lint-staged or optimize pre-commit.
- ▌ Ralph Prompt Audit · otrebu bundleAudit 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.
- ▌ Dev Interrogate · otrebuInterrogate 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.
- ▌ Aaa CLI · otrebuComplete 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.