wanshuiyin
Showing 1–60 of 82 skills · Page 1 of 2
wanshuiyin / citation-audit
18.5kZero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations
wanshuiyin / experiment-audit
18.5kAudit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope
wanshuiyin / experiment-bridge
18.5kWorkflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results
wanshuiyin / experiment-queue
18.5kSSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention
wanshuiyin / grant-proposal
18.5kDraft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats
wanshuiyin / idea-discovery-robot
18.5kWorkflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas
wanshuiyin / interview-cheatsheet
18.5kGenerate 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)
wanshuiyin / kill-argument
18.5kTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues
wanshuiyin / mermaid-diagram
18.5kGenerate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.
wanshuiyin / meta-optimize
18.5kAnalyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026)
wanshuiyin / paper-claim-audit
18.5kZero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias
wanshuiyin / paper-illustration
18.5kGenerate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop
wanshuiyin / paper-illustration-image2
18.5kGenerate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation.
wanshuiyin / paper-poster-html
18.5kDEFAULT 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
wanshuiyin / paper-slides
18.5kGenerate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script
wanshuiyin / paper-talk
18.5kEnd-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).
wanshuiyin / patent-pipeline
18.5kFull patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models
wanshuiyin / render-html
18.5kRender 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
wanshuiyin / research-implement-feature
18.5kBuild a working artifact from a plain \"implement X for me\" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BEFORE the code that depends on it and a cross-model sweep for the ones that slipped through undecla…
wanshuiyin / research-pipeline
18.5kFull end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF
wanshuiyin / research-refine
18.5kTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review
wanshuiyin / research-wiki
18.5kPersistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern
wanshuiyin / resubmit-pipeline
18.5kWorkflow 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)
wanshuiyin / result-to-claim
18.5kUse when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm).
wanshuiyin / serverless-modal
18.5kRun GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero
wanshuiyin / slides-polish
18.5kPer-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 s…
wanshuiyin / auto-review-loop-llm
18.5kAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
wanshuiyin / experiment-plan
18.5kTurn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core probl…
wanshuiyin / figure-spec
18.5kGenerate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG
wanshuiyin / overleaf-sync
18.5kTwo-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI
wanshuiyin / semantic-scholar
18.5kSearch published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR
wanshuiyin / citation-crosscheck
18.5kDouble-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web while blind to the .bib, and a third extractor emits a mechanical field-by-field delta to catch dropped/re-ordered authors,…
wanshuiyin / dse-loop
18.5kAutonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout
wanshuiyin / integrity-forensics
18.5kRun the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher — then convert the verdict into a typed policy gate…
wanshuiyin / lean-formalize
18.5kDevelop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff
wanshuiyin / proof-orchestrator
18.5kManage a stateful, run-directory-based proof project: 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
wanshuiyin / rebuttal
18.5kWorkflow 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
wanshuiyin / research-review
18.5kGet a deep critical review of research from a selected reviewer (Codex by default, Gemini, Grok, Claude Code, or manual)
wanshuiyin / auto-review-loop-minimax
18.5kAutonomous multi-round research review loop using MiniMax API
wanshuiyin / idea-discovery
18.5kWorkflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas
wanshuiyin / paper-figure
18.5kGenerate publication-quality figures and tables from experiment results
wanshuiyin / paper-plan
18.5kGenerate a structured paper outline from review conclusions and experiment results
wanshuiyin / run-experiment
18.5kDeploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU
wanshuiyin / alphaxiv
18.5kQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback
wanshuiyin / deepxiv
18.5kSearch and progressively read open-access academic papers through DeepXiv
wanshuiyin / feishu-notify
18.5kSend notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify
wanshuiyin / firecrawl-search
18.5kWeb search and page scraping via Firecrawl, returning full-page markdown
wanshuiyin / gemini-search
18.5kSearch research papers via Gemini for broad literature discovery
wanshuiyin / openalex
18.5kSearch academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information
wanshuiyin / qzcli
18.5kManage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool
wanshuiyin / specification-writing
18.5kWrite the full patent specification from claims and invention disclosure
wanshuiyin / training-check
18.5kPeriodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs
wanshuiyin / formula-derivation
18.5kStructures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document
wanshuiyin / meta-apply
18.5kPrivileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury and human approval at landing
wanshuiyin / ablation-planner
18.5kUse when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
wanshuiyin / invention-structuring
18.5kStructure a raw invention idea into a formal invention disclosure
wanshuiyin / patent-review
18.5kGet an external patent examiner review of a patent application
wanshuiyin / research-refine-pipeline
18.5kRun an end-to-end workflow that chains `research-refine` and `experiment-plan`
wanshuiyin / figure-description
18.5kProcess user-provided patent figures and generate formal drawing descriptions
wanshuiyin / idea-creator
18.5kGenerate and rank research ideas given a broad direction