Claude Skills by wanshuiyin

DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says \"做海报\", \"poster\", \"conference poster\", \"paper poster\", or asks to design/redo a research poster.

DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.

Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says \"做PPT\", \"做幻灯片\", \"make slides\", \"conference talk\", \"presentation slides\", \"生成slides\", \"写演讲稿\", or wants beamer slides for a conference talk.

End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: \"做 talk\", \"做 PPT 全流程\", \"talk pipeline\", \"end-to-end slides\", \"做演讲\", \"conference talk full workflow\". Use when the user wants the complete talk artifact, not just a slide deck.

Draft LaTeX paper section by section from an outline. Use when user says \\\"\u5199\u8bba\u6587\\\", \\\"write paper\\\", \\\"draft LaTeX\\\", \\\"\u5f00\u59cb\u5199\\\", or wants to generate LaTeX content from a paper plan.

Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says \"写论文全流程\", \"write paper pipeline\", \"从报告到PDF\", \"paper writing\", or wants the complete paper generation workflow.

Assess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"可专利性评估\", \"patentability check\", or wants to evaluate if an invention is patentable.

Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says \"写专利\", \"patent pipeline\", \"专利申请\", \"draft patent\", \"写权利要求书\", or wants to draft a complete patent application.

Get an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \"审查意见\", \"examiner review\", or wants critical feedback on patent claims and specification.

Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says \"\u753b\u50cf\u7d20\u56fe\", \"pixel art\", \"make an SVG illustration\", \"README hero image\", or wants a cute visual.

Search patent databases and academic literature for prior art relevant to an invention. Use when user says \"现有技术检索\", \"prior art search\", \"专利检索\", \"check patents\", or wants to find relevant prior art.

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via fresh-agent Codex GPT-5.6-Sol ultra review, fixes each gap with full derivations, re-reviews, and generates an audit report. Base review is same-family provisional. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.

Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, \u8865\u5168\u8bc1\u660e, \u5199\u8bc1\u660e, \u8bc1\u660e\u67d0\u4e2a\u547d\u9898, or determine whether a claimed proof can actually be completed under the stated assumptions.

Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed training jobs on a Qizhi instance.

Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says \"rebuttal\", \"reply to reviewers\", \"ICML rebuttal\", \"OpenReview response\", or wants to answer external reviews safely.

Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says \"渲染 HTML\", \"出一份 HTML 报告\", \"render html\", \"make this readable\", \"export to html\", or wants a polished web-rendered view of a Markdown artifact.

Search and analyze research papers, find related work, summarize key ideas. Use when user says \"find papers\", \"related work\", \"literature review\", \"what does this paper say\", or needs to understand academic papers.

Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says \"全流程\", \"full pipeline\", \"从找idea到投稿\", \"end-to-end research\", or wants the complete autonomous research lifecycle.

Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to \"\u4e32\u8d77\u6765\", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.6-Sol review. Use when the user says \"refine my approach\", \"\u5e2e\u6211\u7ec6\u5316\u65b9\u6848\", \"decompose this problem\", \"\u6253\u78e8idea\", \"refine research plan\", \"\u7ec6\u5316\u7814\u7a76\u65b9\u6848\", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

Get a deep critical review of research from GPT using a secondary Codex agent. Use when user says \"review my research\", \"help me review\", \"get external review\", or wants critical feedback on research ideas, papers, or experimental results.

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says \"知识库\", \"research wiki\", \"add paper\", \"wiki query\", \"查知识库\", or wants to build/query a persistent field map.

Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says \"resubmit pipeline\", \"重投流程\", \"port paper to <new venue>\", \"resubmit to <venue>\", \"tighten paper for resubmission\", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.

Deploy and run ML experiments on local or remote GPU servers. Use when user says \"run experiment\", \"deploy to server\", \"\u8dd1\u5b9e\u9a8c\", or needs to launch training jobs.

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.

Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says \"modal run\", \"modal training\", \"modal inference\", \"deploy to modal\", \"need a GPU\", \"run on modal\", \"serverless GPU\", or needs remote GPU compute.

Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.

Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic style leaks, fixes text-frame overflow, and catches per-slide layout drift. Trigger phrases: \"polish slides\", \"slides 排版不对\", \"PPTX 字体太小\", \"和 Beamer 比一下\", \"per-page review...

Write the full patent specification from claims and invention disclosure. Use when user says \"撰写说明书\", \"write specification\", \"写说明书\", \"patent description\", or wants to draft the complete patent specification.

Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says \"profile\", \"benchmark\", \"bottleneck\", or wants performance analysis.

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.

Rent, manage, and destroy GPU instances on vast.ai. Use when user says \"rent gpu\", \"vast.ai\", \"rent a server\", \"cloud gpu\", or needs on-demand GPU without owning hardware.

Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.

Fill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers/ as TODO scaffolds.

Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.

Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory. Produces editable structured source files (profile.yml + publications.bib + bio.md + news.md) and a single-file HTML page. Uses Codex MCP for independent factual review against DBLP / arXiv. Optionally uses Gemini multimodal for screenshot critique when available. Use when the user says '做个学术主页', '从CV生成主页', 'aris-homepage', 'generate academic homepage from...

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Cross-model codex review checks math, code, historical citations, and style discipline; then /render-html produces a single-file HTML with academic-newspaper template. Output: docs/tutorials/<slug>_tutorial.{md,html,review.json}. Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题',...

Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Academic template outputs are gated by a fresh cross-model Codex review for render fidelity + safety (the ARIS invariant). Use when the user says \"渲染 HTML\", \"出一份 HTML 报告\", \"render html\", \"make this readable\", \"export to html\", or wants a polished web-rendered view of a Markdown artifact. Markdown/JSON stays ...

Phase-1 (S4) of a comic movie — PRODUCE the canonical reusable references the whole spiral conditions on. Per asset it bakes ONE canonical 1:1 white-bg identity ref via the agent mcp__codex__codex sidecar bake (Codex native image_gen — conditioned, never hand-pasted) OR, for a deterministic motif (clock/chart/stamp/star-map), emits a single-source parametric SVG from a python generator (asset_lib.py). Hashes + base64-encodes the bake into the asset node's output_ref (all 6 fields or it's a sc...

Phase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panel_gate (composed-output) or the assembly_gate (cross-panel) — it gates the refs that FEED both, so identity drift is caught at the source, not downstream. Two layers: (1) a MANDATORY static single-source collision check (check...

Phase 1 ORCHESTRATOR of a movie/comic — turn a fuzzy story idea into the Authored Source of Truth (a schema-valid comic.json + its locked asset library) by driving the detailed author skills in order (intent → style → outline → storyboard → assets → blueprints → prompts → comic.json), each gated by comic-cross-layer-gate, so comic-director (Phase 2/3) can bake + cross-model-verify it. You don't hand-write comic.json; this is the workflow your agent runs to author it. Use when the user says "做...

Phase-1 comic-author step (post-final eval) — a DOUBLE-BLIND A/B of two FINAL whole comics: our cross-model-audited progressive render (the comic-author + comic-director output) vs a naive single-shot baseline. A single sealed coin-flip hides which is which; two cross-model reviewers (Codex + Gemini) score both on a fixed rubric reading only a SHARED blind spec (intent + ART_BIBLE); only AFTER both reviews land do we unseal, re-label, and write a Chinese comparison.md + the A/B verdict nodes....

Phase-1 (S7 of the comic-author suite) — turn ONE locked panel_spec into a deterministic content-SVG blueprint that becomes the bake condition (reference #1 of the agent mcp__codex__codex sidecar bake), by WRITING A PYTHON GENERATOR (never raw SVG in chat — LLMs botch coordinates). The HEADLINE comic-pivot rule: the image bakes NO bubbles at all — draw only characters + scene + leave negative-space SAFE ZONES; HTML/CSS owns the entire bubble. Every panel gets a content_svg (a figure OR a layo...

The authoring-side DIEGETIC continuity AUDIT — it produces the world-state evidence that comic-cross-layer-gate `--gate continuity` adjudicates against the storyboard's MOTIF STATE TABLE (motif_ledger). It checks each baked panel STRICTLY against the pre-committed table row, then emits a continuity review-node the gate fuses (it does NOT own a bake-time KEEP). Gemini auto-gemini-3 is the per-panel FACT extractor (one analyzeFile per panel image, fact-only); Claude is the deterministic JUDGE a...

The ONE parameterized score-fuser for EVERY comic-author authoring gate — `--gate intent|outline|asset|storyboard|blueprint|continuity|p0_proof|compile`. A single fuser (not a per-layer split) prevents drift. It NEVER re-runs a reviewer; it collects the reviewer score-nodes already on the wiki (via `reviews` edges), fuses them deterministically (min-fuse per dim, max for inverted dims, SKIP missing dims — never substitute 0), then a Codex xhigh adjudicator (NO model pin — follows the local co...

Phase 2/3 of a movie — bake + cross-model-verify a movie from an authored comic.json. Per frame: render the content-SVG blueprint, bake via the agent mcp__codex__codex sidecar, gate with a 3-reviewer cross-model panel (narrative [currently the codex CLI] ‖ Gemini visual ‖ Codex visual, deterministic fuse), keep/retry/assemble, write the wiki trace, project to the viewer. The movie-side twin of method-figure's render half. (Author the comic.json first with the comic-author skill.)

Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intent_spec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes against. Codex-as-parser (raw bytes + schema, never Claude's gloss) + reviewer-independence + banned-vocab lint + confidence-gated under_review routing + a HARD user-approval gate. It NEVER invents panels, assets, or sto...

Phase-1 (S9, the FINAL comic-author step) — assemble the LOCKED storyboard + locked per-panel blueprints into ONE schema-valid `comic.json` (the comic-ir/1.0 contract boundary handed to comic-director / run_comic.py). Project the page_order + each panel's condition{} + render fields into `pages[]` + keyed `panels{}` per schemas/comic.schema.json; author ONLY authored fields and leave image_path/active_attempt_id/wiki_node_id EMPTY for the engine. THE step where page-count integrity is reconci...