paperlisted

# paper — submission-grade research writing for a Rockie lab This skill turns a lab's evidence (experiment logs, result Notes, a corpus of sources) into a paper that survives hostile review. It is **agent-instruction driven**: you, the Rockie agent, follow this procedure and dispatch your own fresh-context subagents for the review gauntlet and the detector gate. There is no heavy runtime here. The single code artifact, `templates/figure-gen.py.tmpl`, is a template a figure agent fills in and runs on Rockie compute — this skill never executes it. The method this skill reproduces is documented in `references/method.md`. It is the same pipeline that produced a real ICML MI-workshop submission: a hard styleguide, a five-stage adversarial gauntlet, and a detector loop that does not stop until two consecutive rounds of fresh judges call the prose "100% human". Do not invent a lighter method. The whole point is that ordinary LLM drafting produces filler; this procedure filters it out. ## Routing Pick the entry point from the user's intent. The three are a pipeline but each runs independently — a user can lit-review without drafting, or publish a draft that was gauntleted in an earlier session. | Entry point | Trigger intent | What it does | Reference | |---|---|---|---| | `/lit-review` | "lit review", "survey the literature on X", "what's the prior work" | Rank a candidate corpus; persist a human reading-list Note + a machine-readable index Note | `references/lit-review.md` | |