AI论文复现主协调器，基于 README 优先策略，提供端到端的最小可信复现流程，包括仓库读取、目标选择、环境搭建、可信执行、补丁约束、证据记录并生成标准化输出包。
该技能（llllllama/ai-paper-reproduction）是一个专注于AI论文代码复现的自动化协调器。其核心原则是 `README-first`：首先读取仓库文档，从中选择最小的已验证推理或评估目标作为入口点。然后依次执行仓库摄取、环境搭建、可信执行（默认不可信，仅在确认安全时切换为可信）、可选的可信训练、可选的仓库结构分析以及可选的论文与代码差异修复（paper-gap resolution）。在整个流程中，严格遵循保守补丁规则（不修改未明确允许的文件），并实时记录所有证据、假设、偏差和人工决策点，最终生成标准化 `repro_outputs/` 目录作为结果。该技能适用于主流AI Agent平台（如Claude Code、Codex等），旨在解决AI论文复现中常见的“黑盒执行”“无证据保留”“环境破坏”等问题，确保复现过程可追溯、可审计且最小化对用户环境的干扰。
npx skills add https://github.com/lllllllama/ai-paper-reproduction-skill/tree/main/skills/ai-paper-reproductionInstalled? Explore more 研究与数据分析 skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →
AI论文复现主协调器，基于 README 优先策略，提供端到端的最小可信复现流程。适用于用户希望从仓库出发，选择最小的文档化推理或评估目标，协调仓库摄取、环境搭建、可信执行、可选的可信训练、可选的仓库分析及可选的论文与代码差异修复，执行保守补丁规则，记录所有证据、假设、偏差和人工决策点，并生成标准化 repro_outputs/ 输出包。请勿用于论文摘要、通用环境搭建、孤立的仓库扫描、独立的命令执行、静默协议变更或脱离仓库基础的广泛研究辅助。
This repo contains 4 individual skills — each has its own dedicated page.
Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.
RigorPilot trusted execution and reporting skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Agent skill repository discovered by 10x-chat research.
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.