一键在 Manus 中运行任何 Skill

开始使用

literature-search

星标1

分支0

更新时间2026年3月16日 19:56

Queries, venues, time windows, and inclusion/exclusion criteria; output is a list of papers with short rationale.

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

Literature Search Skill

When to Use

The user wants to find new papers on a topic (e.g. for background, baselines, or related work).
You need to propose search directions and produce a candidate list with rationale.

Instructions

Input: Precise topic, constraints (e.g. domain, task), and any seed papers or venues.
Output: A list of papers (citation + 1–2 line relevance) plus short rationale for inclusion (why each fits the topic/constraints).

Process:

Ask for (or infer): topic, constraints, seed papers, preferred venues or time window.
Propose 2–5 search directions: concrete query strings (e.g. for Google Scholar, ACL Anthology, arXiv), venues (conferences/journals), and optional time window (e.g. last 3 years).
Define inclusion/exclusion criteria in one sentence (e.g. "Empirical ML for X; exclude pure theory").
For each candidate paper, record: citation (authors, year, venue, title) and 1–2 line relevance. Add a short overall rationale (e.g. "Selected for baselines and method proximity").
Do not summarize paper content here; that is done by the literature-notes skill.

同仓库更多 Skills

同仓库

experiment-implementation

Xmaster6y/chess-experiments

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

2026-03-171

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

name	literature-search
description	Queries, venues, time windows, and inclusion/exclusion criteria; output is a list of papers with short rationale.

Literature Search Skill

When to Use

The user wants to find new papers on a topic (e.g. for background, baselines, or related work).
You need to propose search directions and produce a candidate list with rationale.

Instructions

Input: Precise topic, constraints (e.g. domain, task), and any seed papers or venues.
Output: A list of papers (citation + 1–2 line relevance) plus short rationale for inclusion (why each fits the topic/constraints).

Process:

Ask for (or infer): topic, constraints, seed papers, preferred venues or time window.
Propose 2–5 search directions: concrete query strings (e.g. for Google Scholar, ACL Anthology, arXiv), venues (conferences/journals), and optional time window (e.g. last 3 years).
Define inclusion/exclusion criteria in one sentence (e.g. "Empirical ML for X; exclude pure theory").
For each candidate paper, record: citation (authors, year, venue, title) and 1–2 line relevance. Add a short overall rationale (e.g. "Selected for baselines and method proximity").
Do not summarize paper content here; that is done by the literature-notes skill.