skills/paper-writing-router/SKILL.md
Route ML/AI paper writing tasks to the correct skill — contract planning, prose drafting, section writing, consistency editing, review simulation, rebuttal, submission, or citation work. Use when the task involves writing, revising, reviewing, or submitting a paper instead of guessing between paper-writing-assistant, paper-writing-contract-planner, paper-reviewer-simulator, auto-paper-improvement-loop, or citation skills. Do not draft prose directly.
npx skillsauth add a-green-hand-jack/ml-research-skills paper-writing-routerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a router. Do not draft paper prose directly.
Your job: classify the task → select one child skill → hand off.
git rev-parse --git-common-dir vs --show-toplevel.memory/BRIEFING.md or paper/.agent/writing-contract.md exists, read it to understand current writing phase and contract status.| Bucket | Key signals | Route to |
|---|---|---|
| contract | no writing contract yet, lock section order, archetype, forbidden claims, paragraph roles | paper-writing-contract-planner |
| positioning | what is the paper's contribution, archetype, claim scope, narrative strategy, before venue | paper-positioning-planner |
| venue-adapt | reshape for NeurIPS/ICLR/ICML/CVPR/ACL, venue exemplars, reviewer-friendly structure | conference-writing-adapter |
| prose-write | draft a section, write results, revise paragraphs, fill placeholders, claim-aware prose | paper-writing-assistant |
| writing-state | stale sections, section status, style decisions across sessions, edit impact tracking | paper-writing-memory-manager |
| intro | introduction argument chain, hook, gap, insight, contribution paragraphs | paper-introduction-argument-writer |
| method-section | method notation, module order, overview figure placement, algorithm box | method-section-explainer |
| results-prose | results narrative, turn tables/figures into claim-aware prose, experiment story | experiment-story-writer |
| related-work | related work positioning, novelty boundaries, closest-work grouping, citation wording | related-work-positioning-writer |
| limitations | limitations, scope statements, failure cases, broader impact, conclusion caveats | limitations-scope-writer |
| abstract-title | title options, abstract structure, contribution bullets, top-level claim calibration | abstract-title-contribution-writer |
| consistency | single-pass full-draft audit: terminology, figures, tables, captions, claim alignment | paper-draft-consistency-editor |
| multi-round-edit | 2+ review-fix cycles, fresh reviewer per round, edit-whitelist, crash-resumable | auto-paper-improvement-loop |
| pre-sub-review | simulate venue reviewers, predict scores, reject reasons, meta-review, risk register | paper-reviewer-simulator |
| rebuttal | real reviews arrived, infer reviewer intent, plan experiments, draft responses | rebuttal-strategist |
| appendix | supplementary structure, NeurIPS/ICLR checklist, cross-references, appendix sections | appendix-organizer |
| camera-ready | accepted paper, de-anonymize, rebuttal promises, final claim/evidence check | camera-ready-finalizer |
| submission | pre-submission checklist, source hygiene, anonymity, bibliography, compile | submit-paper |
| citation-keys | BibTeX metadata, unresolved keys, invalid labels, DOI/arXiv data | citation-audit |
| citation-coverage | missing foundational/closest/benchmark/recent papers, insertion points | citation-coverage-audit |
| latex-layout | LaTeX layout issue bundle, PDF page debugging, compile log artifacts | latex-layout-issue-bundler |
paper-writing-assistant, paper-writing-contract-planner, and paper-writing-memory-manager, read references/contrastive-routing.md.paper-reviewer-simulator and rebuttal-strategist, read references/contrastive-routing.md.paper-reviewer-simulator.paper-writing-assistant; if it doesn't, route to paper-writing-contract-planner first.paper-writing-assistant; do not re-plan.testing
Bootstrap project-local ml-research-skills. Use from global installs when creating a new ML research project, enabling this collection in an existing ML research repo, or deciding whether to install the full bundle locally. Route to project-init for new projects; do not handle paper or experiment work directly.
development
Route project operations tasks — git, memory, bootstrap, remote, workspace, code review, timeline, ops — to the correct skill. Use when the task involves commits, pushes, worktrees, project memory, enabling project-local skills, SSH/server coordination, sidecar runners, or audits. Do not solve the ops task directly.
data-ai
Project-local router for ML research skill selection. Use inside an initialized ML research project, or while maintaining this skill repo, when the user describes an ML research/paper/experiment/discovery/ops/release workflow and may not know the skill; route to a domain router or high-signal leaf. Do not use for generic non-ML projects.
development
Route ML experiment planning, execution, debugging, result interpretation, and evidence packaging tasks to the correct skill. Use this when the task involves experiments, compute, results, or evidence — instead of guessing between run-experiment, run-status-monitor, experiment-debugger, result-diagnosis, research-results-auditor, statistical-analysis-planner, or paper packaging skills. Do not solve the task directly.