spike-faye-lei
- 254 skills
- 0 followers
- 1 day ago last updated
- ▌ Auto Review Loop · spike-faye-leiAutonomous multi-round research review loop. Repeatedly reviews via external reviewer backend (Codex or manual), implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
- ▌ Autosci Discover · spike-faye-lei bundleBuild a ranked shortlist of candidate papers (anchor-driven, topic-driven, or derived from current wiki state) that the user — or an upstream skill — may decide to feed into `/ingest`. Use whenever the user asks "what should I read next", "find papers similar to this one", "recommend related work", "what's around this topic", or whenever `/ingest` is invoked with `--discover`. Does not ingest; only proposes.
- ▌ Autosci Exp Eval · spike-faye-leiExperiment verdict gate — Review LLM independently judges results → 4 verdict paths → auto-update the linked idea's status / failure_reason and graph edges
- ▌ Autosci Rebuttal · spike-faye-leiParse review comments → atomize concerns (Rvx-Cy) → map to wiki ideas/methods → check evidence → Review LLM stress-test → generate rebuttal
- ▌ Autosci Research · spike-faye-leiEnd-to-end research orchestrator — idea discovery → experiment design → execution → verdict → paper writing, with human gates and session-resumable state
- ▌ Experiment Queue · spike-faye-lei bundleSSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.
- ▌ Semantic Scholar · spike-faye-leiSearch 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.
- ▌
- ▌ Experiment Bridge · spike-faye-leiWorkflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
- ▌ Paper Claim Audit · spike-faye-leiZero-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. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
- ▌
- ▌ Research Pipeline · spike-faye-leiFull 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.
- ▌ Resubmit Pipeline · spike-faye-leiWorkflow 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.
- ▌ 2chat Automation · spike-faye-leiAutomate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.
- ▌ Alphaxiv · spike-faye-leiQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
- ▌ Openalex · spike-faye-leiSearch academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.
- ▌ Vast Gpu · spike-faye-leiRent, 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.
- ▌
- ▌ Autosci Paper Plan · spike-faye-leiCompile a paper outline from the idea graph — evidence map → narrative structure → section plan + figure plan + citation plan, Review LLM review mandatory
- ▌ Paper Illustration · spike-faye-leiGenerate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
- ▌ 21risk Automation · spike-faye-leiAutomate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
- ▌ Interview Cheatsheet · spike-faye-leiGenerate 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). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.
- ▌ Design Taste Frontend · spike-faye-leiAnti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
- ▌ Monitor Experiment · spike-faye-leiMonitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
- ▌ Chiang Kai Shek Wisdom · spike-faye-leiApply Chiang Kai-shek's governance and strategic endurance frameworks for asymmetric competition and organizational reform. Triggers: Chiang Kai-shek, strategic patience, endurance, retreat-reflect-rebuild, self-cultivation. 运用蒋介石的治理与战略韧性框架应对弱势方博弈与组织改革。触发：蒋介石、忍耐待机、退省建攻、修身。
- ▌ Michael Jackson Wisdom · spike-faye-leiActivate Michael Jackson's creative genius, performance philosophy, and humanitarian spirit. Respond in MJ's voice — hee-hee, shamone, love and magic. Triggers: Michael Jackson, MJ, moonwalk, King of Pop, heal the world, 迈克尔杰克逊, shamone, hee-hee, 太空步. 激活迈克尔·杰克逊的创意天才、表演哲学与人道主义精神。以 MJ 口吻回应。触发：迈克尔杰克逊、MJ、太空步、heal the world。
- ▌ Autosci Daily Arxiv · spike-faye-lei bundleRun or manage the daily arXiv recommendation feed. Use for one-off fresh-paper recommendations, scheduled GitHub Actions setup/status/disable, email digests, and explicit high-confidence auto-ingest through /ingest.
- ▌ Autosci Paper Draft · spike-faye-leiDraft a LaTeX paper from PAPER_PLAN — write each section from wiki sources + generate figures/tables + BibTeX verification + de-AI polish
- ▌ Exa Search · spike-faye-leiAI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).
- ▌ Paper Talk · spike-faye-leiEnd-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.
- ▌ Auto Review Loop LLM · spike-faye-leiAutonomous 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".
- ▌ Idea Discovery Robot · spike-faye-leiWorkflow 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. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.
- ▌ Figure Spec · spike-faye-leiGenerate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
- ▌ Paper Write · spike-faye-lei bundleDraft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTeX content from a paper plan.
- ▌ Autosci Exp Pilot Run · spike-faye-leiPilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
- ▌
- ▌ Autosci Exp Pilot Eval · spike-faye-leiPilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
- ▌
- ▌ Start My Day · spike-faye-lei bundle论文阅读工作流启动 - 生成今日论文推荐笔记 / Paper reading workflow starter - Generate daily paper recommendations
- ▌ Kill Argument · spike-faye-leiTwo-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. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.
- ▌ Patent Review · spike-faye-leiGet 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.
- ▌ Proof Checker · spike-faye-leiRigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.5 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. 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.
- ▌ Paper Analyze · spike-faye-lei bundle深度分析单篇论文，生成详细笔记和评估，图文并茂 / Deep analyze a single paper, generate detailed notes with images
- ▌ Auto Review Loop Minimax · spike-faye-leiAutonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
- ▌ Patent Pipeline · spike-faye-leiFull 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.
- ▌ Ablation Planner · spike-faye-leiUse when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.
- ▌ Experiment Audit · spike-faye-leiAudit experiment integrity before claiming results. Uses cross-model review (GPT-5.5) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
- ▌ Serverless Modal · spike-faye-leiRun 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.
- ▌ Auto Paper Improvement Loop · spike-faye-leiAutonomously improve a generated paper via GPT-5.5 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
- ▌ Patent Novelty Check · spike-faye-leiAssess 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.
- ▌
- ▌
- ▌ Writing Systems Papers · spike-faye-leiParagraph-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.
- ▌ Paper Illustration Image2 · spike-faye-lei bundleGenerate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to `paper-illustration`, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.