Skill Claude CodeCodex
One-time onboarding flow for users who set ROCKIEGPUMODE=custom (i.e., they have their own GPU setup — own AWS account, on-prem cluster, SSH tunnel to a workstation, university HPC, custom orchestration — instead of using Rockie's deidentified GPU router). Trigger this when (1) the user mentions…
Skill Claude CodeCodex
Runtime skill for users in ROCKIEGPUMODE=custom — invoked when the user (or agent) needs to do anything GPU-related (provision, connect, check status, check cost, terminate) in a project where Rockie's GPU router is bypassed in favor of the user's own setup. Reads .codex/gpu-custom.md (populated by /gpu-custom-setup)…
Skill Claude CodeCodex
Skill "gpu-spend" from Rockielab/rockie-codex, covering /gpu-spend — rockie-gpu spend snapshot, when to invoke, what the skill does, composition and agent invocation template.
Skill Claude CodeCodex
Productize an open-source model into a hosted inference endpoint the researcher (or their agent) can call. Picks the right hardware, the right serving stack (vLLM / Triton / TEI / BentoML), wraps it in an OpenAI-compatible gateway (LiteLLM) with per-tenant auth, exposes it as an MCP tool in chat, and runs a quality +…
Skill Claude CodeCodex
Manage swappable operational overlays on top of the central taste corpus. A mode is a small TOML file capturing how this session's policy differs from the researcher's stable identity — hardware preferences, budget ceilings, reading focus, scope-lock, subagent model policy, output register, deadlines. The active mode…
Skill Claude CodeCodex
One-time researcher onboarding interview that compiles a taste/ corpus (SOUL.md, STYLE.md, METHODOLOGY.md, DISMISSALS.md, MEMORY.md, INDEX.md) capturing the researcher's intellectual taste, beliefs, and values. Auto-injects INDEX.md into every future session via SessionStart. Triggers on first install ("no taste…
Skill Claude CodeCodex
Write submission-grade research papers end to end inside a Rockie lab, the way a careful human researcher does — not generic LLM filler. Three entry points. /lit-review pulls and ranks a corpus and persists a human reading list Note plus a machine-readable index Note. /paper-draft produces a brief, a page-budgeted…
Skill Claude CodeCodex
Route physics simulation, modeling, validation, and research-compute requests across force fields, molecular dynamics, electronic structure, particle transport/collision, continuum multiphysics, plasma/PIC, nuclear/radiation, and astro/cosmology. Use open-source-first engines, refuse local heavyweight execution on the…
Skill Claude CodeCodex
After an experiment finishes, structured review emits {isbug, failureclass, summary, metric, lowerisbetter}, auto-closes the journal node, emits a [LEARN] block when isbug=true, and files a [DEAD-END] when the failureclass is "bad-hypothesis". Use immediately after any training/eval run — the agent invokes this…
Skill Claude CodeCodex
Create validated PowerPoint .pptx deck artifacts through the lean Rockie PPTAgent wrapper and emit them to the lab.
Skill Claude CodeCodex
Package a harness-level improvement (a new hook, a fixed script, an improved skill) as a reviewed, verified patch — optionally openable as a PR against the rockie upstream repo. Uses Generator/Verifier/Updater role separation so the proposing agent never auto-commits; a fresh-context verifier plus the smoke test must…
Skill Claude CodeCodex
Refill the experiment queue when it drops below target (default 5 pending items). Brainstorms 3–5 new high-quality experiments informed by recent [LEARN] rules, killed dead-ends, best-so-far results, and hypothesis-calibration drift. Use when queue.py refill-needed returns non-zero, when the user asks "what should we…
Skill Claude CodeCodex
Persistent notes a scheduled/recurring agent reads as its FIRST action and writes as its LAST action, so a weekly/nightly autonomous run "knows where it left off." Use inside /loop or /schedule tasks that span multiple wake-ups. Pairs with hypothesis calibration and the experiment queue.
Skill Claude CodeCodex
Track 3 quickstart wrapper that reproduces a paper or repository baseline on Rockie GPU, then extends it with a user-specified delta and compares baseline versus delta.
Skill Claude CodeCodex
Scan the current Codex session for harness-level patterns that would be useful to other rockie-codex users — pruning fixes, small skill improvements, new hooks, cross-discipline-useful capabilities, memory-schema upgrades — strip the project-specific specificity, and dispatch a writer sub-agent that forks…
Skill Claude CodeCodex
Dashboard-backed multi-agent team orchestration for hard, multi-dimensional problems. Each agent runs in its own git worktree, coordinates through a shared thread, and stays observable through a live local dashboard the developer can intervene in. Use this when the problem benefits from cross-pollination and live…
Hook
Runs when a session starts, executing session-start.sh via bash. From Rockielab/rockie-nugget.
Hook
Runs when the agent finishes a response, executing capture.sh via bash. From Rockielab/rockie-nugget.