ワンクリックで
chess-experiments
chess-experiments には Xmaster6y から収集した 22 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
How to change code, tests, configs, and launch in this repo; output is concrete edits and run commands.
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.
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.
Turn grouped literature notes into background or related-work text; no claims beyond what the notes support.
Map claims in the paper to results, configs, or code; avoid unsupported claims.
Patterns and checklists for designing and refining experiments in this research template.
One-paper-per-note structure and grouping by theme; output is structured notes usable for background/related work.
Structured patterns for searching, selecting, and summarizing prior work relevant to this project.
Queries, venues, time windows, and inclusion/exclusion criteria; output is a list of papers with short rationale.
Evaluate novelty and contribution clarity (are contributions stated and supported?).
Identify open questions and missing details (what a reviewer would ask).
Identify strengths of the paper with evidence (what works well and why).
Identify weaknesses of the paper with evidence (what is lacking or problematic).
Guidance for drafting and refining LaTeX sections for this research project.
Read and update docs/PROJECT_STATUS.md; schema and conventions for planning and recording outcomes.
Apply the reproducibility checklist to assess whether experiments can be re-run reliably.
Guides the project through its main research phases (setup, ideation, baseline, contribution, review) with lightweight, conversational checklists.
Structured internal review and revision patterns focused on rigor, clarity, and reproducibility.
Small, reviewable LaTeX edits and rewrite patterns for paper sections.
First-time template setup checklist: metadata, structure, environment.
Dependency and environment setup for this template (uv, LaTeX, cluster).
Create initial docs/README.md and meta docs for the project.