- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add fcakyon/labrat --skill reproduce -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add fcakyon/labrat --skill reproduce -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add fcakyon/labrat --skill reproduce -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add fcakyon/labrat --skill reproduce -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/fcakyon/labrat/tree/HEAD/plugin/skills/reproduce來自發布者
Reproducing an ML paper often means filling gaps the authors didn't ship, training scripts, hyperparameter tables, augmentation specifics, exact dataset splits. This skill walks seven stages from "I have an arxiv link" to "I have a replication run with measurable delta vs the paper's number."
Each stage has a separate reference file under references/ so this overview stays scannable.
The user just said any of:
Walk them in order. Each stage has its own success criteria; do not advance to the next until the current one passes.
For each paper reproduction, set up a dedicated workspace:
repro/<paper-arxiv-id>/
├── paper.md # structured extract from stage 1
├── inventory.md # what exists / missing from stage 2
├── gaps_filled.md # hyperparam table with provenance from stage 3
├── code/ # implementation from stage 4 (or cloned + extended)
├── data/ # dataset symlinks or actual data from stage 5
├── dataset_substitution.md # if a public dataset stood in for a private one
├── smoke_logs/ # outputs from stage 6
└── results.md # replication outcomes from stage 7
This keeps reproductions self-contained and easy to revisit later.
/labrat:paper-check skill for a round-trip check ("did I really capture every hyperparam the paper mentions")./labrat:debug skill, not to ad-hoc fixes./labrat:launch checklist before any multi-hour run./labrat:compare skill at the paper's reported epochs (never current-vs-final).For each reproduction, the final artifact is results.md with absolute deltas (not just %) and one of three labels per metric:
[matched within 0.X pp]: within the paper's reported variance[gap, hypothesis: ...]: measurable underperformance, with a stated hypothesis for the cause[fundamental disagreement, see X]: the result and the paper's claim are inconsistent in a way that needs investigation, not just more computeIf the workspace is on a public repo, link the workspace README from the project's main reproduction-tracking doc.
End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private dat
---name: reproducedescription: End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or…---# plugin/skills/reproduce/SKILL.md總覽
End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private datasets via similar-public-dataset substitution. Use when the user asks to reproduce, implement, replicate, or re-run a paper from scratch, or pastes an arxiv URL with reproduction intent.
常見問題
從發布者下載 plugin/skills/reproduce/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/fcakyon/labrat。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。