Explore

Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.

Provides a structured verification workflow for code and prompt outputs. Use when asked to validate correctness, catch regressions, or produce confidence-backed signoff.

Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.

Defines practical standards for implementation-focused coding agents. Use when creating or editing code, especially when reliability, clarity, and low-risk delivery are required.

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

Comprehensive research assistant that synthesizes information from multiple sources with citations. Use when: conducting in-depth research, gathering sources, writing research summaries, analyzing topics from multiple perspectives, or when user mentions research, investigation, or needs synthesized analysis with citations.

Full DeepScientist research pipeline: scout → baseline → idea → experiment → analysis → optimize → write → review → finalize. End-to-end autonomous research lifecycle.

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.

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.

Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.

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 published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /aris-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.

Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.

Use 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). Use after experiments finish — before writing the paper or running ablations.

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.

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

Run an end-to-end workflow that chains `aris-research-refine` and `aris-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 "串起来", 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-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research direction all the way to a submission-ready paper. 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.

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.

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.

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, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.

Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.

Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go 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.

Draft 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.

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.

Generate a conference poster (article + tcbposter LaTeX → A0/A1 PDF + editable PPTX + SVG) from a compiled paper. Use when user says "做海报", "制作海报", "conference poster", "make poster", "生成poster", "poster session", or wants to create a poster for a conference presentation.

Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.

Generate 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.

Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

Analyze 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). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.

Generate Mermaid diagrams from user requirements. Saves .mmd and .md files to figures/ directory with syntax verification. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.

Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.

Draft 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. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.

Structures 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. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.

Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Supports push-only (webhook) and interactive (bidirectional) modes. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `aris-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 problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.

Workflow 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.

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says "DSE", "design space exploration", "sweep parameters", "optimize", "find best config", or wants iterative parameter tuning.

Mandatory pre-flight compute resource check before running experiments. Detects whether local/remote GPU or compute resources are actually available. If resources are unavailable, STOPS the experiment pipeline immediately and reports to the user — preventing the model from hallucinating fake experiment results. Use when: about to run experiments, deploy training, or any GPU-intensive task.

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.

Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, 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.

Autonomously improve a generated paper via GPT-5.4 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.

Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.

Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.

Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.

Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when user mentions academic research, scholarly writing, papers, or scientific literature.

Market positioning strategy using the April Dunford framework, enriched with JTBD discovery, Moore positioning statement, and Neumeier's Onliness Test. Produces a complete positioning document, positioning statement, competitive alternatives map, and market category analysis. Use when the user wants to define or refine their market positioning, find their unique position, differentiate from competitors, craft a positioning statement, choose a market category, or figure out "how should we position this product." Triggers for "positioning", "how to position", "market position", "differentiation strategy", "positioning statement", "competitive positioning", "category strategy", "where do we fit in the market", "how are we different", "unique value proposition", or any request to define, sharpen, or rethink positioning. Works standalone — no prior startup-design or startup-competitors session needed, but leverages their output if available.

Build investor-ready pitch scripts in multiple formats (10-min, 5-min, 2-min, 1-min elevator, investor email). Produces pitch narratives, Q&A preparation, pitch scoring rubric, and optional investor roleplay practice. Use when the user wants to create a pitch, prepare for investor meetings, craft a startup pitch, write a fundraising narrative, or practice their pitch. Triggers for "pitch deck", "investor pitch", "pitch my startup", "fundraising deck", "seed deck", "how to pitch", "investor meeting", "demo day", "prepare pitch", "pitch script", "elevator pitch for investors", "pitch practice", "practice my pitch", "investor roleplay", or any request to present a startup to investors, accelerators, or partners. Works standalone — no prior startup-design session needed, but leverages its output if available.

Design, validate, and plan a startup from scratch. Covers market research, competitive analysis, business model, brand identity, product definition, financial projections, and validation experiments. Trigger when the user has a startup idea to explore, wants to validate a business concept, needs a business plan or lean canvas, asks for market sizing or competitive landscape, wants brand positioning or go-to-market strategy, or says anything like "I have an idea for..." or "is this idea worth pursuing". Also handles resuming from a previous checkpoint.

Deep competitive intelligence for any market. Analyzes competitors' products, pricing, customer sentiment, GTM strategy, and growth signals using real web data. Produces battle cards, pricing landscape, and feature matrix. Use when the user wants to understand their competitive landscape, analyze competitors, compare products in a market, or research who they're competing against. Triggers for "who are my competitors", "competitive analysis", "competitor research", "battle cards", "pricing comparison", "competitor pricing", "market players", "competitive intelligence", "competitive landscape", "who else is in this space", "competitive moat", or any request to profile, compare, or map competitors in a category. Works standalone — no prior startup-design session needed.

Search the user's past AI coding sessions. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

Spec and no-spec planning workflows derived from local slash commands (requirements, design, tasks).

Triage, repair, and close MCP attribution issues from the local report API with evidence-driven decisions and isolated Worktrunk worktrees. Use this skill when Codex needs to process `tool` attribution issues and skills-related attribution issues, inspect related runs, decide whether the issue is actionable in `mcp/src` or `config/source/skills`, update attribution fields as `owner=codex`, and then complete the fix loop through GitHub issue tracking, worktree-based code changes, PR submission, and follow-up iteration when the problem is repairable.

Documentation and extension workflows derived from local slash commands (docs, explanation, issues, prototypes, tutorials, MCP design review).

Use when the user wants to develop, run, preview, save, deploy, or roll back a CloudBase Web app in this conversation as a Lovable/Codex-Sites-like vibe- coding session — i.e. any request that maps to "spin up a React+Vite project, see it live in the browser, iterate, save versions, deploy". Activate ONLY for browser-rendered Web projects based on the CloudBase official React (or Vue) + Vite template. Do NOT activate for: WeChat/Alipay mini-program, React Native / Flutter / Electron, pure cloud functions / CloudRun backends, or Next.js / Nuxt / Astro / Remix / SvelteKit (those frameworks are explicitly out of scope).