CORAL

Use this subagent to diagnose a CORAL run that's misbehaving — agents restarting, every eval failing, the score plateaued, or "is this run healthy?". It reads `coral status` / `coral log` / `coral show` / notes, identifies the pathology, and returns a ranked set of concrete fixes (fix the grader, resume with an instruction, tune heartbeats, fork a regressed line). Read-only on the run — it recommends, it doesn't restart or stop anything.

Use this subagent to turn "optimize / speed up / improve this with CORAL" into a working CORAL task. Give it the code (or just a repo and a rough goal) and it acts immediately — explores the repo to infer the optimization target, scaffolds a .coral_workspace/, writes the grader, and iterates `coral validate` until the grader cleanly scores the seed, then hands back a ready-to-launch task. Delegate here whenever the user wants CORAL pointed at existing code.

The fast path from zero to a running CORAL experiment — what CORAL is and when to reach for it, installing the `coral` CLI, registering a runtime with `coral setup`, and the `.coral_workspace/` convention for pointing CORAL at code you already have and want optimized. Use this whenever the user asks "what is coral", "should I use coral for this", wants to install or get coral set up, hits a "command not found" for coral or doesn't have it installed yet, or says "use coral to optimize / speed up / improve this code" and you need the end-to-end onboarding from install to a launched run. Hands off to `setting-up-coral` (runtime bindings), `creating-a-coral-task` (grader authoring), and `running-coral-experiments` (operating a run) for depth.

Author a new CORAL task — the three pieces that must line up (`task.yaml`, `seed/`, a packaged `grader/`), the `coral init` → `coral validate` → smoke-test loop, and how to pick a grader pattern (stdout float, test pass-rate, ratio-vs-baseline, multi-metric, or an LLM rubric judge). Use whenever the user wants to create a CORAL task, write or wire a grader, port a benchmark into CORAL, score open-ended outputs (reports/memos) with a judge, or debug a grader that crashes on the seed / ranks the leaderboard backwards / leaks the answer key. Deep references for the TaskGrader API, grader patterns, rubric judges, and the full task.yaml schema live alongside this skill.

Run and manage CORAL experiments from the operator side — launch agents with `coral start` (dotlist overrides, model/count, tmux vs local), monitor with `coral status` / `coral log` / `coral show` / the web dashboard, and drive the loop with `coral resume` (inject instructions, fork from an attempt), `coral heartbeat` (tune reflection cadence), and `coral stop`. Use whenever the user wants to start a CORAL run, check on agents, read scores/leaderboard, steer or resume a run, diagnose agents that keep restarting or fail every eval, scale to more agents or islands, or stop a run. Deep references for steering/heartbeat tuning and scaling/troubleshooting live alongside this skill.

One-time machine setup after installing the `coral` CLI — register local agent runtimes as named bindings with `coral setup` / `coral setup agent`, validate them with `coral agents doctor` (incl. a live hello-ping that catches expired auth and model typos), and reference them from a task via `agents.binding`. Use when the user is configuring which agent runtimes/models coral can use, hits a "runtime not found" / auth error when starting a run, or asks how to set up claude/codex/cursor for coral.

1 hook across 1 event