experiment-implementation

星标1

分支0

更新时间2026年3月17日 13:35

How to change code, tests, configs, and launch in this repo; output is concrete edits and run commands.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

Xmaster6y

Xmaster6y/chess-experiments

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Experiment Implementation Skill

When to Use

You have an experiment design (from experimental-design) and need to implement it in this template (configs, code, tests, launch).
You need to propose concrete file edits and commands to run the experiment.

Instructions

Use references/implementation-notes.md for this template's layout (scripts, configs, results, tests, launch).
Configs: Add or edit YAML under configs/<script_name>/; ensure defaults in configs/run_experiment.yaml reference the right groups; suggest CLI overrides (e.g. demo=first).
Code: Edit src/chess_experiments/ or script modules under scripts/ in small, reviewable steps; avoid large refactors in one go.
Tests: Add or extend tests under tests/; run with uv run pytest. Prefer unit tests for core logic.
Launch: If the user runs on a cluster, point to launch/ scripts and configs/hydra/launcher/ for submitit/slurm.
Output: For each change, list concrete edits (file path + what to change) and the exact run command(s) (e.g. uv run -m scripts.run_experiment demo=first). Mention that outputs go to results/ (untracked).

同仓库更多 Skills

同仓库

lczerolens

Xmaster6y/chess-experiments

Provides guidance for interpretability of Leela Chess Zero (lc0) neural networks. Use when loading lc0 models, encoding chess boards, running inference, visualizing heatmaps, probing concepts, evaluating on puzzles, or pairing with tdhook, captum, zennit, or nnsight for XAI.

2026-03-171

tdhook

Xmaster6y/chess-experiments

Provides guidance for interpreting and manipulating neural network internals using tdhook with TensorDict and PyTorch hooks. Use when needing attribution maps, activation analysis, probing, steering, activation patching, or weight-level interventions on PyTorch or TensorDict models.

2026-03-171

background-writing

Xmaster6y/chess-experiments

Turn grouped literature notes into background or related-work text; no claims beyond what the notes support.

2026-03-161

claims-evidence

Xmaster6y/chess-experiments

Map claims in the paper to results, configs, or code; avoid unsupported claims.

2026-03-161

experimental-design

Xmaster6y/chess-experiments

Patterns and checklists for designing and refining experiments in this research template.

2026-03-161

literature-notes

Xmaster6y/chess-experiments

One-paper-per-note structure and grouping by theme; output is structured notes usable for background/related work.

2026-03-161

name	experiment-implementation
description	How to change code, tests, configs, and launch in this repo; output is concrete edits and run commands.

Experiment Implementation Skill

When to Use

You have an experiment design (from experimental-design) and need to implement it in this template (configs, code, tests, launch).
You need to propose concrete file edits and commands to run the experiment.

Instructions

Use references/implementation-notes.md for this template's layout (scripts, configs, results, tests, launch).
Configs: Add or edit YAML under configs/<script_name>/; ensure defaults in configs/run_experiment.yaml reference the right groups; suggest CLI overrides (e.g. demo=first).
Code: Edit src/chess_experiments/ or script modules under scripts/ in small, reviewable steps; avoid large refactors in one go.
Tests: Add or extend tests under tests/; run with uv run pytest. Prefer unit tests for core logic.
Launch: If the user runs on a cluster, point to launch/ scripts and configs/hydra/launcher/ for submitit/slurm.
Output: For each change, list concrete edits (file path + what to change) and the exact run command(s) (e.g. uv run -m scripts.run_experiment demo=first). Mention that outputs go to results/ (untracked).