oh-my-copilot

Use when a user wants to compare an arbitrary skill or path across models, quality, cost, latency, or routing.

Analyze actual local Copilot skill activations without reading conversation content.

Plan work too big for one agent session as a shared map of decision tickets on GitHub Issues or Jira, then resolve them one at a time until the route is clear. Use with /wayfinder when the user says "plan something too big for one session", "chart a map", "wayfind", "work the map", or "decision tickets". Always confirm tracker (GitHub vs Jira) and destination before writing. Adapted from mattpocock/skills wayfinder (MIT).

Create or resume a task handoff so a fresh agent can continue unfinished work. Persist via omp handoff CLI (never write handoff files yourself). Use when the user says /handoff, wants to pause mid-task, or resume prior work.

Single-owner execute-fix-verify loop for one clear task. Use with /ralph when one agent should keep going until evidence or blocker.

Adversarial QA pass that tests behavior, failures, and regressions. Use with /ultraqa after implementation when shallow checks are not enough.

Capture user-correction patterns from this session and, when a pattern recurs, draft a new project skill. Use at end of session, when the user signals wrap-up, or when invoked directly.

Multi-model council — fan a question out to several models in parallel, then synthesize one weighted verdict with a minority report. Use with /weighted-consensus to decide, review, or compare options across diverse models.

Stateful multi-session teaching loop. Builds knowledge, skills, and wisdom from trusted sources via short interactive lessons grounded in a mission. Use with /teach when the user wants to learn a topic over time.

Reproduce, minimize, diagnose, fix, and regression-test a bug. Use with /debug for broken, failing, slow, or confusing behavior.

Drive a real browser from the CLI to QA a flow — navigate, click, fill, verify. Uses @playwright/cli (token-efficient, not MCP). Use with /qa-browse when the user wants to manually check a web flow works, not write a test suite.

Prove completion claims with fresh evidence. Use with /verify before saying done.

Review completed changes for blockers, regressions, security, and scope drift. Use with /code-review before merge or final handoff.

Produce an implementation-ready plan with risks, acceptance criteria, and test shape. Use with /ralplan when edits need planning first.

Red-green-refactor loop for behavior changes where tests are practical. Use with /tdd when a change can be specified by tests.

Lazy senior dev mode. Forces the simplest, shortest solution that actually works — YAGNI, stdlib first, native platform features before dependencies, one line before fifty, no unrequested abstractions. Use with /ponytail when the user complains about over-engineering, bloat, boilerplate, or unnecessary dependencies, or says "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path". Adapted from DietrichGebert/ponytail (MIT).

Register a durable local cron job that re-runs a prompt on a schedule (e.g. "check the PR every 15 min"). Use with /schedule when you want a fresh agent session to fire unattended on an interval and survive reboot.

Split an approved plan into parallel tmux panes in the current window so the user can watch agents work. Prefer this visual flow by default; use `omp team` only when the user explicitly wants background execution or runtime messaging/status APIs.

High-throughput execution for many independent small tasks. Use with /ultrawork when work can be batched safely.

Verify an omp change end-to-end — static gate (build/tsc/tests/lint/catalog) plus a live BYOK run that drives Copilot/teams on a real model and captures evidence. Use before merging any PR that touches hooks, comms, team, launch, or skills.

Prepare Jira create, comment, and safe-update payloads with safe dry-run fallback. Use with /jira-ticket when work tracking is requested.

Full lightweight flow from research to plan, execution, review, and verification. Use with /omp-autopilot only for clear autonomous work. (Renamed from /autopilot to avoid collision with the Copilot CLI built-in.)

Comprehensive codebase research that scales effort to task complexity, synthesises findings, and writes a timestamped document to docs/research/. Use when user says /research-codebase, asks to research or document a codebase area, or wants a deep-dive into how something works.

Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.

Keep a simple per-project daily memory log under the project's daily-memory directory. Review it at session start when relevant, set today's goal, append milestones, and summarize before wrapping up. Use when the user says /daily-log, asks to record/recall what was done, or at end of session.

Post an outbound Slack notification — ONLY when the user types the explicit `/slack` slash command. Never auto-trigger from natural-language phrases like "tell Slack" or "notify me on Slack"; those go to the regular chat. One-way (publish only); the v0.8.0 gateway bridge still handles bidirectional DM chat.

Set or show the repo's durable objective — what we want to achieve in this repo — stored per project at .omp/goal.md. Use when the user says /goal, states the repo's north-star, or asks "what are we trying to achieve here".

Ultra-compact response mode with no filler. Use with /caveman when the user wants fewer tokens.

Ask one sharp clarification question after codebase research when ambiguity still matters. Use with /grill-me before planning or implementation.

Build a disposable experiment to answer one design, UI, state, or data-model question. Use with /prototype when a cheap experiment beats guessing.

Guides worktree-based workflow for parallel branch work. Use when user wants to start a new ticket, review a PR, or work on a branch without switching. Also use when user mentions worktree, branch switching, or parallel branch work.