正在加载仓库 README…
已展示 20 / 20 个已收集 Skill。
Trim a user-specified proportion of removable whitespace from PDF pages while preserving the document page aspect ratio and enforcing one common output crop size across all pages. Use for PDFs with oversized margins, uneven whitespace, scanned or generated…
原文语言：英语
Revise existing technical writing into clear, audience-facing prose while preserving evidence, technical meaning, uncertainty, and scope, including planned multi-agent section or issue-cluster revision for substantial artifacts when workers are available. Use…
原文语言：英语
Coordinate research as either a standalone staged planning pass or a durable orchestrated multi-skill workflow with shared artifacts, explicit work items, paper-level commitment, verifier-backed transitions, checkpoints, replay, observability, stage gates,…
原文语言：英语
Run a stringent, adversarial novelty review over a concrete research idea, method, protocol, artifact, or claimed finding. Use when asked to assess novelty, position a paper or project, build a prior-art matrix, decide whether something is incremental, or…
原文语言：英语
Turn supported claims and evidence into a research paper plan that works either as a standalone manuscript-structuring pass or as the paper stage inside a coordinated research workflow. Use when asked to outline a paper, map claims to evidence, bind audited…
原文语言：英语
Run or audit literature discovery and evidence synthesis with explicit review profiles, high-recall discovery, seed and challenge-set testing, citation searching, corpus freezing, PRISMA 2020 core accounting, evidence extraction, confidence grading, and…
原文语言：英语
Audit ML/statistics experiment outputs for validity, confounds, statistical support, calibration, and mismatch between measured results and claimed conclusions. Use when asked to interpret results, sanity-check benchmarks, review ablations, assess robustness…
原文语言：英语
Convert a concrete research claim into a tracked, decisive experiment plan that works either as a standalone planning artifact or as the experiment stage inside a coordinated research workflow. Use when asked to design experiments, define baselines or…
原文语言：英语
Pedantic, adversarial stress-testing of documents with claim-by-claim scrutiny, internal consistency checks, citation auditing, and up-to-date fact-checking. Use when asked to critique, peer-review, red-team, verify references, pressure-test time-sensitive…
原文语言：英语
Generate, filter, rank, and hand off grounded research ideas from a broad research direction, problem area, literature landscape, Zotero corpus, paper limitation, or user notes. Use when asked to brainstorm publishable research ideas, find a direction, turn a…
原文语言：英语
Run iterative adversarial review over research plans, experiment outputs, and drafts with claim ledgers, issue tracking, evidence checks, and explicit closure criteria. Use when asked to red-team a research artifact across multiple rounds, maintain issue…
原文语言：英语
Run evidence-gated commercialization analysis for academic research by translating a bounded research asset into workflow pain, current workarounds, buyer and budget logic, commercialization paths, risk-retirement tests, and kill/pivot/continue decisions. Use…
原文语言：英语
source-grounded market, competitor, procurement, funding, regulatory, and patent-landscape diligence for academic research commercialization. use when codex needs to search public market or patent information for a research asset, technology, prototype,…
原文语言：英语
Run academic paper review with OCR extraction, ChatGPT-native multi-agent critique, local visualization, and section-level review workflows integrated into the research skill suite. Use when Codex needs an initial or first-pass review of one paper artifact or…
原文语言：英语
Draft venue-aware academic rebuttals and author responses from reviewer comments, scores, and paper artifacts. Use when concrete reviewer comments already exist and Codex needs to analyze reviews, build a reviewer issue board, plan evidence or manuscript…
原文语言：英语
Sync, inspect, and export Zotero user or group libraries for literature-heavy research workflows. Use when Codex needs to reuse a Zotero library or collection as a curated paper corpus, export BibTeX or CSL-JSON, inspect collections/tags/groups, prepare…
原文语言：英语
Improve the flow, shape, and readability of existing prose while preserving substance, specificity, tone, and constraints, including planned multi-agent section, paragraph-range, or chunk-level revision for substantial documents when workers are available.…
原文语言：英语
Read a specified set of documents and distill them into a reusable, source-grounded memory pack. Use when Codex is asked to ingest project documents, papers, specs, notes, policies, or mixed corpora and create durable memory artifacts such as canonical facts,…
原文语言：英语
Convert mathematical derivations, research notes, and textual specs into runnable, product-ready Jupyter notebooks (.ipynb) with clear narrative, LaTeX, modular code, plots, and sanity checks/tests. Use when asked to turn an exposition/paper/spec into a…
原文语言：英语
Assemble book-style PDFs from one or more source PDFs using CLI PDF tools. Use when Codex needs to collate PDFs in a specific order, drop repeated cover/JSTOR pages, add chapter/section bookmarks, rotate landscape pages to portrait, or optionally crop shared…
原文语言：英语
复制这段 Prompt，发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/yananlong/codex-skills.该仓库没有可展示的 Markdown README。你仍可浏览下方已收录的 Skill。