Verified:GitHub

research-progress-tracker

Track research code development with experiment logs and consistency checks.

Updated May 13, 2026

Search Tags:#git #pipeline management #experiment tracking #research workflow #progress logging #configuration consistency #conda environment

Ready to run

npx skills add https://github.com/Ricardo-Vae/codex-research-skills --skill research-progress-tracker

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-progress-tracker
Source: https://github.com/Ricardo-Vae/codex-research-skills/tree/main/skills/research-progress-tracker
Command: npx skills add https://github.com/Ricardo-Vae/codex-research-skills --skill research-progress-tracker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

它解决科研代码迭代缺乏可追溯记录、实验结果难以复盘、以及训练/评估配置不一致导致的评估失真问题。

Core Features & Use Cases

Git 进度与提交规范：每次完成有意义的代码改动后按文件粒度执行 git add 并生成清晰的中英文 commit message，同时在推送时要求使用指定的 SSH key 方式，并在提交前先征得用户同意。
项目级进度/管线/实验登记：维护根目录的 PROGRESS.md、PIPELINE.md 与 EXPERIMENTS.md/EXPERIMENTS.csv，将每次改动、pipeline 变化、实验（含失败）系统化记录，便于持续迭代与回溯。
一致性检查器与环境提醒：启动、评估前、训练后触发一致性检查（如 mask-logit / all-logit 推理参数匹配、数据生成与训练配置匹配），并检查当前 conda 环境是否符合项目建议。

Quick Start

仅在你需要开始进行科研代码进度管理时，精确输入“科研启动”，并按提示说明你本次要做的具体代码或实验任务。

Frequently Asked Questions about research-progress-tracker

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I track experiment progress and maintain reproducible research workflows?▼

To track experiment progress and maintain reproducible research workflows, you can enforce end-to-end experiment tracking through systematic updates to PROGRESS.md, PIPELINE.md, and EXPERIMENTS.md alongside strict git commit discipline.

How do I ensure configuration consistency before model training and evaluation?▼

You ensure configuration consistency before model training and evaluation by running automated consistency checks that validate matching inference parameters, such as mask-logit and all-logit settings, against your data generation and training configurations.

What is the best way to log failed experiments for academic model training?▼

The best way to log failed experiments for academic model training is to systematically register all pipeline changes and experiment outcomes, including failures, into EXPERIMENTS.md and EXPERIMENTS.csv for continuous iteration and historical traceability.

Does this research workflow tracker validate my conda environment before running scripts?▼

Yes, this research workflow tracker validates your conda environment before running scripts by checking whether your current environment aligns with the project's recommended conda configuration during the startup and evaluation gating phases.

How do I start managing my research code iteration using this workflow?▼

To start managing your research code iteration, you trigger the workflow by typing the exact phrase “科研启动” and then describe your specific code or experiment task, which activates the progress logging and consistency gating mechanisms.