literature-review-sprint

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Literature Review Sprint

文献综述冲刺

Turn a broad topic, rough idea, or uncertain project direction into a ranked literature map and concrete research implications.

Use this skill when:

a user needs to understand a new field quickly
novelty depends on whether close prior work already exists
a project needs canonical, closest, and recent/concurrent papers before algorithm or experiment design
a paper draft has weak related-work positioning but the goal is still field understanding, not final citation cleanup
an advisor meeting needs a crisp paper map, gap analysis, or next reading plan
early experiments or writing reveal that the project may be in the wrong literature frame

Do not use this skill as a metadata or BibTeX checker. Use

citation-audit

for citation correctness and

citation-coverage-audit

for submission-time missing-reference review.

Pair this skill with:

```
research-project-memory
```
when literature findings should persist as risks, actions, claims, or positioning decisions
```
research-idea-validator
```
before or after the sprint when the result should become a pursue/revise/park/kill decision
```
algorithm-design-planner
```
when the map clarifies the closest baseline and the method now needs specification
```
experiment-design-planner
```
when the map implies required baselines, datasets, metrics, or diagnostics
```
paper-evidence-board
```
when literature risks should be linked to paper claims, sections, figures, and reviewer risks
```
citation-coverage-audit
```
later, after the paper is close to submission

将宽泛的主题、粗略的想法或不确定的项目方向转化为排名论文图谱和具体的研究启示。

在以下场景使用此技能：

用户需要快速了解一个新领域
创新性取决于是否存在相近的已有研究
项目在算法或实验设计前，需要经典、相近以及最新/同期的论文
论文草稿的相关工作定位较弱，但目标仍是理解领域，而非最终的引用整理
导师会议需要清晰的论文图谱、缺口分析或后续阅读计划
早期实验或写作发现项目可能处于错误的文献框架中

请勿将此技能用作元数据或BibTeX检查工具。引用正确性检查请使用

citation-audit

，提交阶段缺失参考文献检查请使用

citation-coverage-audit

。

搭配以下技能使用：

当文献发现需作为风险、行动、主张或定位决策持久保存时，搭配
```
research-project-memory
```
当冲刺结果需转化为推进/修订/搁置/终止决策时，在冲刺前后搭配
```
research-idea-validator
```
当图谱明确了最接近的基线，且方法需要明确规范时，搭配
```
algorithm-design-planner
```
当图谱暗示所需基线、数据集、指标或诊断方法时，搭配
```
experiment-design-planner
```
当文献风险需关联到论文主张、章节、图表及审稿风险时，搭配
```
paper-evidence-board
```
当论文接近提交阶段时，稍后搭配
```
citation-coverage-audit
```

Skill Directory Layout

技能目录结构

text

<installed-skill-dir>/
├── SKILL.md
└── references/
    ├── memory-writeback.md
    ├── paper-taxonomy.md
    ├── reading-priority.md
    ├── search-protocol.md
    └── synthesis-template.md

text

<installed-skill-dir>/
├── SKILL.md
└── references/
    ├── memory-writeback.md
    ├── paper-taxonomy.md
    ├── reading-priority.md
    ├── search-protocol.md
    └── synthesis-template.md

Progressive Loading

渐进式加载

Always read

references/search-protocol.md

references/paper-taxonomy.md

, and

references/reading-priority.md

Read
```
references/synthesis-template.md
```
before writing the final sprint report.
Read
```
references/memory-writeback.md
```
when a project has
```
memory/
```
, component
```
.agent/
```
folders, or the user asks for cross-session memory.
If the user asks about recent, concurrent, accepted, or current work, verify with current sources through web search, OpenReview, proceedings pages, arXiv, DBLP, Semantic Scholar, ACL Anthology, PMLR, CVF, or user-provided papers.
If web access is unavailable, state that the output is a provisional reading plan and mark unverified papers or gaps explicitly.

务必阅读

references/search-protocol.md

、

references/paper-taxonomy.md

和

references/reading-priority.md

。

在撰写最终冲刺报告前，阅读
```
references/synthesis-template.md
```
。
当项目存在
```
memory/
```
、组件
```
.agent/
```
文件夹，或用户要求跨会话记忆时，阅读
```
references/memory-writeback.md
```
。
如果用户询问最新、同期、已接收或当前研究，通过网络搜索、OpenReview、会议页面、arXiv、DBLP、Semantic Scholar、ACL Anthology、PMLR、CVF或用户提供的论文验证信息。
如果无法访问网络，需说明输出为临时阅读计划，并明确标记未验证的论文或缺口。

Core Principles

核心原则

Optimize for project decisions, not an exhaustive bibliography.
Separate canonical background, closest competitors, adjacent tools, and recent/concurrent threats.
Treat unknown closest work as a major novelty risk.
Rank papers by decision value: what changes the project if this paper is strong?
Convert literature findings into baselines, ablations, claims to avoid, and writing positions.
Preserve search provenance: where searched, when, which queries, and what was excluded.
Do not overclaim novelty from absence of evidence.
End with a next action that changes the project trajectory.

以项目决策为优化目标，而非追求详尽的参考文献列表。
区分经典背景、最接近的竞品、相邻工具以及最新/同期研究威胁。
将未知的相近研究视为重大创新性风险。
按决策价值对论文排名：若该研究结论明确，会如何改变项目？
将文献发现转化为基线、消融实验、需避免的主张及写作定位。
保留搜索来源记录：搜索地点、时间、使用的查询词以及排除的内容。
勿因无证据而过度宣称创新性。
以能改变项目轨迹的后续行动收尾。

Step 1 - Define the Sprint Question

步骤1 - 定义冲刺问题

Recover:

topic, project idea, paper claim, or draft section
target area and venues, if known
intended contribution type
known seed papers, baselines, datasets, or methods
what decision the sprint must support
time budget: quick scan, focused half-day, full sprint, novelty check, baseline check, or positioning check
project memory IDs such as
```
CLM-###
```
,
```
RSK-###
```
, or
```
ACT-###
```
, if present

Rewrite the sprint question as:

text

For [topic/claim], determine whether [proposed contribution] is novel and important relative to [closest families], and identify [papers/baselines/gaps] that change the next project decision.

If the user only asks for "papers about X", still produce a decision-oriented map.

梳理：

主题、项目想法、论文主张或草稿章节
目标领域和会议（若已知）
预期贡献类型
已知的种子论文、基线、数据集或方法
本次冲刺需支持的决策
时间预算：快速扫描、半天聚焦冲刺、完整冲刺、创新性检查、基线检查或定位检查
项目记忆ID（如
```
CLM-###
```
、
```
RSK-###
```
或
```
ACT-###
```
，若存在）

将冲刺问题重写为：

text

针对[主题/主张]，判断[拟议贡献]相对于[最接近的研究类别]是否具备创新性和重要性，并识别能改变下一项目决策的[论文/基线/研究缺口]。

若用户仅询问“关于X的论文”，仍需生成面向决策的图谱。

Step 2 - Build a Search Protocol

步骤2 - 构建搜索方案

Read

references/search-protocol.md

Create:

seed concepts and synonyms
method names and older terminology
venue filters and likely communities
canonical-source search paths
recent/concurrent search paths
backward and forward citation plan
OpenReview or proceedings search plan when venue style matters
stopping criteria

For current literature, record source names and dates. Prefer primary sources over blog posts, slides, or secondhand summaries.

阅读

references/search-protocol.md

。

创建：

核心概念及同义词
方法名称及旧术语
会议筛选条件及目标社群
经典来源搜索路径
最新/同期研究搜索路径
反向和正向引用计划
当会议风格重要时，制定OpenReview或会议搜索计划
停止搜索的标准

对于当前文献，记录来源名称和日期。优先选择原始来源，而非博客文章、幻灯片或二手摘要。

Step 3 - Collect and Classify Candidate Papers

步骤3 - 收集并分类候选论文

Read

references/paper-taxonomy.md

Classify each candidate into one or more roles:

foundational or canonical
closest prior work
direct competitor
baseline method
benchmark, dataset, or metric source
adjacent method family
theory or analysis source
empirical survey or taxonomy
recent or concurrent threat
negative result or limitation evidence
writing or positioning exemplar

For each important paper, extract a compact card:

text

Paper:
Role:
Core idea:
What it proves or demonstrates:
Relation to our project:
Decision impact:
Read priority:
Verification/source:

阅读

references/paper-taxonomy.md

。

将每篇候选论文归类为一个或多个角色：

基础或经典研究
最接近的已有研究
直接竞品
基线方法
基准、数据集或指标来源
相邻方法类别
理论或分析来源
实证调研或分类体系
最新或同期研究威胁
负面结果或局限性证据
写作或定位范例

针对每篇重要论文，提取简洁卡片：

text

论文：
角色：
核心观点：
证明或展示的内容：
与我们项目的关联：
决策影响：
阅读优先级：
验证/来源：

Step 4 - Prioritize Reading

步骤4 - 确定阅读优先级

Read

references/reading-priority.md

Assign:

```
read-now
```
: can change novelty, baseline selection, method design, or project viability
```
skim
```
: useful for context or framing, unlikely to change the core decision
```
defer
```
: relevant but not needed for this sprint's decision
```
ignore-for-now
```
: out of scope, weakly related, or superseded for current purpose

Every

read-now

paper must have a reason tied to a project decision.

阅读

references/reading-priority.md

。

分配优先级：

```
read-now
```
：可能改变创新性、基线选择、方法设计或项目可行性
```
skim
```
：有助于背景或框架理解，但不太可能改变核心决策
```
defer
```
：相关但本次冲刺决策无需
```
ignore-for-now
```
：超出范围、关联性弱或当前用途已被替代

每篇

read-now

的论文必须有与项目决策相关的理由。

Step 5 - Synthesize the Literature Map

步骤5 - 合成文献图谱

Build:

method-family map
chronology of key ideas
closest-work comparison table
baseline implications
dataset, metric, or protocol implications
theory or assumption implications
open gaps and saturated claims
terminology map for search and writing

Flag:

```
novelty-risk
```
: close work may already cover the idea
```
baseline-risk
```
: a missing baseline would weaken experiments
```
positioning-risk
```
: the project is framed in the wrong community or contribution type
```
evidence-risk
```
: available experiments do not address the field's standard concern
```
scope-risk
```
: the literature is too broad for the current project shape

构建：

方法类别图谱
关键观点时间线
相近研究对比表
基线启示
数据集、指标或方案启示
理论或假设启示
开放缺口和已饱和的主张
用于搜索和写作的术语图谱

标记风险：

```
novelty-risk
```
：相近研究可能已覆盖该想法
```
baseline-risk
```
：缺失基线会削弱实验说服力
```
positioning-risk
```
：项目框架不符合目标社群或贡献类型
```
evidence-risk
```
：现有实验未解决领域的标准关注点
```
scope-risk
```
：文献范围过宽，不符合当前项目规模

Step 6 - Convert Findings into Project Decisions

步骤6 - 将发现转化为项目决策

Return concrete implications:

should the idea be pursued, revised, parked, or killed?
what is the closest prior work to beat or distinguish from?
what claim is still defensible?
what claim should be avoided?
what baseline must be implemented or cited?
what experiment, theorem, diagnostic, or analysis becomes mandatory?
what writing frame is likely reviewer-friendly?
what next skill should be used?

If the literature map changes the project direction, route to

research-idea-validator

algorithm-design-planner

before experiments.

返回具体启示：

该想法应推进、修订、搁置还是终止？
最接近的已有研究是什么，需超越或区分？
哪些主张仍可辩护？
哪些主张应避免？
必须实现或引用哪些基线？
哪些实验、定理、诊断或分析成为必需？
哪种写作框架更易获得审稿人认可？
下一步应使用哪个技能？

若文献图谱改变了项目方向，在实验前转至

research-idea-validator

或

algorithm-design-planner

。

Step 7 - Write the Sprint Report

步骤7 - 撰写冲刺报告

Read

references/synthesis-template.md

If saving to a project and no path is given, use:

text

docs/literature/literature_sprint_YYYY-MM-DD_<short-name>.md

The report must include:

sprint question
search log and limitations
ranked paper map
closest-work risks
method taxonomy
baseline and evaluation implications
project decision implications
next reading or experiment actions
memory update section

阅读

references/synthesis-template.md

。

若需保存至项目且未指定路径，使用：

text

docs/literature/literature_sprint_YYYY-MM-DD_<short-name>.md

报告必须包含：

冲刺问题
搜索日志及局限性
排名论文图谱
相近研究风险
方法分类体系
基线和评估启示
项目决策启示
后续阅读或实验行动
记忆更新部分

Step 8 - Write Back to Project Memory

步骤8 - 写入项目记忆

Read

references/memory-writeback.md

when memory exists.

Update the smallest useful set of entries:

```
memory/decision-log.md
```
: literature-driven project or positioning decisions
```
memory/risk-board.md
```
: closest-work, baseline, evidence, and positioning risks
```
memory/action-board.md
```
: read-now papers, baseline checks, implementation tasks, or writing tasks
```
memory/claim-board.md
```
: claims to keep, revise, narrow, park, or cut
```
memory/evidence-board.md
```
: planned baseline, dataset, metric, theorem, or diagnostic evidence
```
paper/.agent/
```
when related-work or positioning notes affect a draft

Use:

```
verified
```
for facts checked against primary sources
```
user-stated
```
for papers or constraints supplied by the user
```
inferred
```
for risk judgments and positioning implications
```
unverified
```
for search leads not yet checked

当存在项目记忆时，阅读

references/memory-writeback.md

。

更新最小必要的条目集：

```
memory/decision-log.md
```
：基于文献的项目或定位决策
```
memory/risk-board.md
```
：相近研究、基线、证据和定位风险
```
memory/action-board.md
```
：需立即阅读的论文、基线检查、实现任务或写作任务
```
memory/claim-board.md
```
：需保留、修订、缩小范围、搁置或删除的主张
```
memory/evidence-board.md
```
：计划中的基线、数据集、指标、定理或诊断证据
```
paper/.agent/
```
：当相关工作或定位笔记影响草稿时

使用标记：

```
verified
```
：已通过原始来源验证的事实
```
user-stated
```
：用户提供的论文或约束条件
```
inferred
```
：风险判断和定位启示
```
unverified
```
：尚未验证的搜索线索

Final Sanity Check

最终合理性检查

Before finalizing:

search scope and limitations are explicit
papers are ranked by decision impact, not merely listed
closest-work risk is named even if unresolved
recent/concurrent search status is stated
baseline implications are concrete
project claims are adjusted when needed
next skill or next action is unambiguous
memory writeback is performed when the project has memory

定稿前确认：

搜索范围和局限性明确
论文按决策影响排名，而非仅罗列
即使未解决，也明确标注了相近研究风险
最新/同期研究的搜索状态已说明
基线启示具体明确
必要时已调整项目主张
下一步技能或行动清晰明确
当项目存在记忆时已完成记忆写入