my_codex_skills

Deep, critical paper-reading workflow that produces a structured reading note. Use when the user wants to read, understand, summarize, break down, or take notes on a single research paper. English triggers: "read this paper", "read the paper", "paper reading", "paper notes", "deeply read", "critically read", "summarize this paper", "break down the paper", "explain this paper", "walk me through this paper", "help me understand this paper". Chinese triggers: "读论文", "精读论文", "理解论文", "拆解 论文", "整理论文笔记", "帮我看这篇论文", "分析这篇论文". Also triggers when the user hands over a .pdf, an arXiv URL or ID, or a paper title and asks for deep understanding. NOT for quick one-paragraph overviews (use alphaxiv), broad literature surveys (use research-lit), or simulated peer review (use mock-review).

Quick 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.

Structured co-authoring workflow for specifications, proposals, decision docs, PRDs, RFCs, and other substantial written artifacts. Use when Codex should help a user gather context, shape document structure, draft section by section, and test whether the document works for a cold reader before handoff.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with reference numerals.

Structure and derive research formulas when the user wants to 推导公式, derive a theory line, build equations from a problem statement, clarify assumptions, separate formal derivation from remarks, or turn messy theory notes into a paper-ready derivation skeleton. Use for research-style formula development, not for fully rigorous theorem proving once the claim is already fixed.

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.

Operate the local MiniMax CLI (`mmx`) from Codex. Use when Codex needs to run MiniMax-specific text chat, web search, vision, image generation, video generation, speech synthesis, music generation, quota inspection, or MiniMax file operations through the installed `mmx` command, especially when the user explicitly mentions MiniMax or `mmx`.

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.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when writing a benchmark paper, structuring a benchmark paper, checking whether a benchmark idea is substantive, drafting a benchmark Introduction, or planning the data-construction pipeline or experiments.

Advises on the design of the three core figures in a technical paper: the Motivated Example (Figure 1), the Solution Overview (Methodology), and the Experimental Results figures. Recommends the right design paradigm, layout, labelling, and tool for each figure type, then runs a quality-control audit. Use when the user asks to 'design a figure', 'draw Figure 1', 'plot experiment results', 'choose the right chart type', 'which figure tool to use', or 'figure looks unprofessional'.

Evaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader) plus idea-lifecycle and student-capability matching, paradigm-shift probing, and a fatal-flaws audit. Returns a reviewer-style verdict. Use when the user has a draft research idea and asks whether it is worth pursuing, asks to 'evaluate this idea', 'score this idea', 'assess feasibility', 'novelty check', 'is this a good research direction', or before committing to a paper scope.

Drafts a 6-paragraph Introduction outline for a technical paper from a structured Flowchart: background and running example, existing limitations, problem essence and goal, key challenges, solution overview, contributions. Positions the paper as Technique or New Problem/Setting and aligns contributions with challenges. Use when the user asks to 'draft the Introduction', 'outline the Introduction', 'intro logic needs clarifying', 'help structure the paper story', or before writing any Introduction prose.

Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy (CRITICAL / MAJOR / MINOR) and flags banned AI-tone vocabulary and em-dash misuse. Use when the user asks to 'review this paper', 'audit before submission', 'check the draft', 'find issues', 'proofread', or within one week of a submission deadline.

Structures a technical paper's full logical skeleton using a thinking-template table (research background, limitations, key idea or goal, challenges, methodology modules, contributions), positions the paper as Technique or New Problem/Setting, and runs a four-point self-consistency check. Use when the user is brainstorming a paper, discussing progress with an advisor, or planning the paper before drafting. Also use for 'paper skeleton', 'paper logic chain', 'thinking template', 'paper-structure planning'.

Guides AI-assisted research across three sub-flows, Vibe Coding, Vibe Figure, and Vibe Writing, with behavioural rules that keep the user in charge of academic judgment while delegating mechanical work to AI. Recommends the right tool (Cursor, Claude Code, Codex, Figma, Gemini) for the current stage. Use when the user asks 'how to use AI for research', 'Vibe Coding tips', 'AI-assisted writing workflow', 'which AI tool for this', or starts an AI-assisted work session.

Use this skill any time a .pptx file is involved in any way - as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

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.

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.

Theme-selection and theme-application workflow for slides, documents, reports, and lightweight HTML artifacts. Use when Codex should apply one of the bundled curated themes from `themes/`, show the theme showcase, or derive a new theme with coherent colors, fonts, contrast, and repeated visual motifs.

Create or update a structured source map (Markdown + JSON) for any project directory. Use when Codex needs to (1) index an unfamiliar workspace before doing work in it, (2) refresh a stale source map after files are added, removed, or renamed, (3) prepare quick navigation context for a multi-turn task that touches many files, or (4) preserve a reusable structured inventory of the project. Auto-detects whether to create a new map or update an existing one based on the presence of `x_temp/SOURCE_MAP.md` or `SOURCE_MAP.md` at the workspace root. Outputs are human-readable Markdown for navigation and structured JSON for programmatic queries. Curated file summaries in a separate JSON file persist across regenerations.

Spreadsheet workflow for `.xlsx`, `.xlsm`, `.csv`, and `.tsv` files. Use when Codex needs to create, inspect, repair, clean, reformat, or extend a spreadsheet; preserve workbook structure while editing an existing file; add formulas, charts, or sheets; or convert messy tabular data into a deliverable spreadsheet file.

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.

Use when creating research figures, paper posters, academic presentation visuals, or conceptual diagrams as an editable draw.io/diagrams.net draft plus PNG/SVG/PDF exports that pass strict visual QA. Especially for paper figures/posters where Codex must read source materials, reuse extracted paper images or plots when useful, and produce editable draw.io/SVG/PDF assets that the user can keep editing directly in draw.io.

Mock peer-review workflow for manuscript authors preparing conference or journal submissions. Use when the user asks in English or Chinese for mock review, simulated review, rebuttal preparation, reviewer-style critique, or asks Codex to review a manuscript according to a named venue/journal such as ACM MM, NeurIPS, CVPR, ICLR, ICCV, IEEE journals, or a user-provided review template. The skill researches official review requirements, optionally extracts user-provided review templates in PDF/Markdown/image/text form, scans PDFs for manuscript artifact risks, studies related literature and experimental baselines, and writes a simulated review for author preparation that must not replace real peer review or impersonate an official reviewer.

Long-running survey workflow for robotics, embodied AI, computer vision, world models, navigation, manipulation, 3D scene understanding, and adjacent research. Use when Codex needs to create or continue a multi-round literature review task, maintain stable task documents (`task.md`, `round_log.md`, `current_task.md`, `survey.md`), search Nature/Science plus top CV and robotics venues before arXiv, migrate relevant local PDFs from `papers/` into task-local `sources/`, read PDFs in chunks of at most 10 pages, and incrementally write a Chinese Markdown survey with relative local citations or web links.

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across a project. 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.