zhiming33416
UserEvidence-grounded agent skills for Codex & Claude Code: writing, citation evidence, figures, polishing, pre-submission review, and reviewer response for top CS conferences (WWW/ICLR/ICML/NeurIPS/CVPR/ACL) - without inventing experiments, citations, or venue rules.
Categories
Indexed Skills (7)
top-cs-evidence
Build and audit author-controlled claim-to-source evidence for top computer-science conference papers. Use for literature-positioning plans, BibTeX or DOI metadata checks, citation ledgers, claim-to-source maps, supplied source excerpts, and evidence handoffs to writing, review, or response work. Use only author-provided sources and explicit optional metadata lookup; never download full text, invent citations, or claim that a source supports a proposition without supplied source text or author notes.
top-cs-figure
Create, revise, audit, render, and export publication-ready computer-science paper figures using a Python-first, corpus-calibrated workflow. Use for manuscript figures, multi-panel experimental charts, comparison plots, scaling curves, heatmaps, embeddings, network diagrams, method schematics, executable YAML/CSV figure render specs, figure-brief handoffs, caption/callout alignment, SVG/PDF/PNG/TIFF export bundles, and visual QA for WWW, ICLR, ICML, NeurIPS, CVPR, ACL, or generic top-CS submissions. Do not use for interactive dashboards, Plotly/Altair/web apps, Illustrator/Figma-first layout, AI-generated graphical abstracts, or result-table writing.
top-cs-paper-workflow
Coordinate a complete evidence-grounded CS paper project across the six Top CS skills. Use when work spans contribution planning, literature evidence and figure handoff, manuscript revision, pre-submission review, or reviewer response and needs resumable project status. Do not use for a single specialist task.
top-cs-polishing
Polish, translate, tighten, structurally revise, or diagnose existing computer-science manuscript prose and LaTeX for WWW, ICLR, ICML, NeurIPS, CVPR, ACL, or a generic venue while preserving evidence. Use for Chinese-to-English academic rewriting, paragraph flow, section-level revision, claim calibration, concision, terminology consistency, reducing generic AI prose, revision ledgers, and LaTeX layout or float-placement problems. Do not use to invent a paper from sparse notes, simulate peer review, or write a reviewer response.
top-cs-response
Prepare, audit, or revise evidence-grounded author responses, rebuttals, discussion replies, decision-email triage, cover letters, revision packages, and LaTeX response templates for WWW, ICLR, ICML, NeurIPS, CVPR, ACL, or a generic computer-science venue. Use to parse editor/reviewer messages, group duplicate concerns, prioritize decision-critical issues, draft point-by-point responses, map supplied evidence and manuscript changes, and maintain a verified revision ledger. Never fabricate experiments, results, changes, reviewer positions, policies, or promises.
top-cs-reviewer
Perform a confidential pre-submission audit of a computer-science manuscript against WWW, ICLR, ICML, NeurIPS, CVPR, ACL, or generic top-conference expectations. Use for reviewer-style assessment, rejection-risk analysis, claim verification, experimental and reproducibility audits, venue or track fit, anonymity checks, paper readiness, and actionable revision priorities. This is an author-side simulation, not an official review and not a substitute for domain experts.
top-cs-writing
Draft, restructure, or plan evidence-grounded computer-science conference papers for WWW, ICLR, ICML, NeurIPS, CVPR, ACL, or a generic venue. Use for paper outlines, titles, abstracts, introductions, related work, methods, experiments, discussions, limitations, conclusions, full manuscript arguments, Chinese research notes to English drafting, and LaTeX or Markdown section writing. Do not use for sentence-only polishing of a finished draft, reviewer-style auditing, or rebuttal writing.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.