Menu
SkillsMP a collecté 35 skills depuis damian87x/oh-my-copilot. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 35 skills collectés sur 35.
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.
Langue du texte source : anglais
Gate-driven retry loop — re-run an agent until a shell gate command passes (e.g. PR checks green, tests passing). Use with /loop when a machine-checked condition decides done-ness, not the model's say-so.
Langue du texte source : anglais
Use when the user invokes /goal, wants a durable objective for the current Copilot session, asks to resume an unfinished objective, or needs turn-based continuation with completion and blocker decisions.
Langue du texte source : anglais
Use when the user invokes /project-goal, wants to set or inspect the repository's durable north-star, or asks what the project is trying to achieve across sessions.
Langue du texte source : anglais
Single-owner execute-fix-verify loop for one clear task. Use with /ralph when one agent should keep going until evidence or blocker.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Use when the user invokes /ultragoal, wants a durable multi-story objective, provides a Ralplan artifact for sequential execution, or requires criterion evidence and independent completion gates.
Langue du texte source : anglais
Adversarial QA pass that tests behavior, failures, and regressions. Use with /ultraqa after implementation when shallow checks are not enough.
Langue du texte source : anglais
High-throughput execution for many independent small tasks. Use with /ultrawork when work can be batched safely.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Produce an implementation-ready plan with risks, acceptance criteria, and test shape, reviewed by architect and critic subagents until consensus. Use with /ralplan when edits need planning first.
Langue du texte source : anglais
Bulletproof skill-usage retrospective from local Copilot history. Prefer omp skill-retro (not history analyze). Simple or advanced tables, optional HTML. Use for skill usage retros, times used, tokens, spend.
Langue du texte source : anglais
Use when a user wants to compare an arbitrary skill or path across models, quality, cost, latency, or routing.
Langue du texte source : anglais
Analyze actual local Copilot skill activations without reading conversation content.
Langue du texte source : anglais
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",…
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Reproduce, minimize, diagnose, fix, and regression-test a bug. Use with /debug for broken, failing, slow, or confusing behavior.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Prove completion claims with fresh evidence. Use with /verify before saying done.
Langue du texte source : anglais
Review completed changes for blockers, regressions, security, and scope drift. Use with /code-review before merge or final handoff.
Langue du texte source : anglais
Red-green-refactor loop for behavior changes where tests are practical. Use with /tdd when a change can be specified by tests.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Prepare Jira create, comment, and safe-update payloads with safe dry-run fallback. Use with /jira-ticket when work tracking is requested.
Langue du texte source : anglais
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.)
Langue du texte source : anglais
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…
Langue du texte source : anglais
Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Ultra-compact response mode with no filler. Use with /caveman when the user wants fewer tokens.
Langue du texte source : anglais
Ask one sharp clarification question after codebase research when ambiguity still matters. Use with /grill-me before planning or implementation.
Langue du texte source : anglais
Build a disposable experiment to answer one design, UI, state, or data-model question. Use with /prototype when a cheap experiment beats guessing.
Langue du texte source : anglais
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.
Langue du texte source : anglais