research-lookup

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Information Lookup

研究信息检索

Overview

概述

This skill provides real-time research information lookup with intelligent backend routing:

parallel-cli search (parallel-web skill): Primary and default backend for all research queries. Fast, cost-effective web search with academic source prioritization. Uses
```
parallel-cli search
```
with
```
--include-domains
```
for scholarly sources.
Parallel Chat API (
```
core
```
model): Secondary backend for complex, multi-source deep research requiring extended synthesis (60s-5min latency). Use only when explicitly needed.
Perplexity sonar-pro-search (via OpenRouter): Used only for academic-specific paper searches where scholarly database access is critical.

The skill automatically detects query type and routes to the optimal backend.

该技能具备智能后端路由功能，可实时查询研究信息：

parallel-cli搜索（parallel-web技能）：所有研究查询的主要及默认后端。快速、低成本的网页搜索，优先返回学术来源。使用
```
parallel-cli search
```
搭配
```
--include-domains
```
参数筛选学术资源。
Parallel Chat API（
```
core
```
模型）：次要后端，适用于需要多源深度整合的复杂研究（延迟60秒-5分钟）。仅在明确需要时使用。
Perplexity sonar-pro-search（通过OpenRouter）：仅用于需访问学术数据库的特定学术论文搜索场景。

该技能会自动检测查询类型，并将其路由至最优后端。

When to Use This Skill

使用场景

Use this skill when you need:

Current Research Information: Latest studies, papers, and findings
Literature Verification: Check facts, statistics, or claims against current research
Background Research: Gather context and supporting evidence for scientific writing
Citation Sources: Find relevant papers and studies to cite
Technical Documentation: Look up specifications, protocols, or methodologies
Market/Industry Data: Current statistics, trends, competitive intelligence
Recent Developments: Emerging trends, breakthroughs, announcements

当你需要以下服务时，可使用该技能：

最新研究信息：最新研究、论文及成果
文献验证：对照当前研究核实事实、统计数据或主张
背景研究：为科学写作收集背景信息及支撑证据
引用来源：查找可引用的相关论文与研究
技术文档：查询规格、协议或方法学内容
市场/行业数据：当前统计数据、趋势、竞争情报
最新进展：新兴趋势、突破成果、公告信息

Visual Enhancement with Scientific Schematics

借助科学原理图优化视觉呈现

When creating documents with this skill, always consider adding scientific diagrams and schematics to enhance visual communication.

If your document does not already contain schematics or diagrams:

Use the scientific-schematics skill to generate AI-powered publication-quality diagrams
Simply describe your desired diagram in natural language

bash

python scripts/generate_schematic.py "your diagram description" -o figures/output.png

使用该技能创建文档时，务必考虑添加科学图表与原理图以增强视觉传达效果。

若你的文档尚未包含原理图或图表：

使用scientific-schematics技能生成AI驱动的出版级图表
只需用自然语言描述你想要的图表即可

bash

python scripts/generate_schematic.py "your diagram description" -o figures/output.png

Automatic Backend Selection

自动后端选择

The skill automatically routes queries to the best backend based on content:

该技能会根据内容自动将查询路由至最优后端：

Routing Logic

路由逻辑

Query arrives
    |
    +-- Contains academic keywords? (papers, DOI, journal, peer-reviewed, etc.)
    |       YES --> Perplexity sonar-pro-search (academic search mode)
    |
    +-- Needs deep multi-source synthesis? (user says "deep research", "exhaustive")
    |       YES --> Parallel Chat API (core model, 60s-5min)
    |
    +-- Everything else (general research, market data, technical info, analysis)
            --> parallel-cli search (fast, default)

查询进入
    |
    +-- 是否包含学术关键词？（papers、DOI、journal、peer-reviewed等）
    |       是 --> Perplexity sonar-pro-search（学术搜索模式）
    |
    +-- 是否需要多源深度整合？（用户提及"deep research"、"exhaustive"）
    |       是 --> Parallel Chat API（core模型，延迟60秒-5分钟）
    |
    +-- 其他情况（通用研究、市场数据、技术信息、分析）
            --> parallel-cli搜索（快速、默认）

Default: parallel-cli search (parallel-web skill)

默认：parallel-cli搜索（parallel-web技能）

Primary backend for all standard research queries. Fast, cost-effective, and supports academic source prioritization.

For scientific/technical queries, run two searches to ensure academic coverage:

bash

undefined

所有标准研究查询的首选后端。快速、低成本，支持优先返回学术来源。

针对科学/技术类查询，需执行两次搜索以确保覆盖学术资源：

bash

undefined

1. Academic-focused search

1. 学术定向搜索

parallel-cli search "your research query" -q "keyword1" -q "keyword2"
--json --max-results 10 --excerpt-max-chars-total 27000
--include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,semanticscholar.org,biorxiv.org,medrxiv.org,ncbi.nlm.nih.gov,nature.com,science.org,ieee.org,acm.org,springer.com,wiley.com,cell.com,pnas.org,nih.gov"
-o sources/research_<topic>-academic.json

2. General search (catches non-academic sources)

2. 通用搜索（覆盖非学术来源）

parallel-cli search "your research query" -q "keyword1" -q "keyword2"
--json --max-results 10 --excerpt-max-chars-total 27000
-o sources/research_<topic>-general.json


Options:
- `--after-date YYYY-MM-DD` for time-sensitive queries
- `--include-domains domain1.com,domain2.com` to limit to specific sources

Merge results, leading with academic sources. For non-scientific queries, a single general search is sufficient.

All other queries route here by default, including:

- General research questions
- Market and industry analysis
- Technical information and documentation
- Current events and recent developments
- Comparative analysis
- Statistical data retrieval
- Fact-checking and verification

parallel-cli search "your research query" -q "keyword1" -q "keyword2"
--json --max-results 10 --excerpt-max-chars-total 27000
-o sources/research_<topic>-general.json


可选参数：
- `--after-date YYYY-MM-DD`：适用于时间敏感型查询
- `--include-domains domain1.com,domain2.com`：限定特定来源

合并搜索结果，优先展示学术来源。针对非科学类查询，单次通用搜索即可满足需求。

默认情况下，以下类型的查询均会路由至此：

- 通用研究问题
- 市场与行业分析
- 技术信息与文档
- 当前事件与最新进展
- 对比分析
- 统计数据检索
- 事实核查与验证

Academic Keywords (Routes to Perplexity)

学术关键词（路由至Perplexity）

Queries containing these terms are routed to Perplexity for academic-focused search:

Paper finding:

find papers

find articles

research papers on

published studies

Citations:
```
cite
```
,
```
citation
```
,
```
doi
```
,
```
pubmed
```
,
```
pmid
```

Academic sources:

peer-reviewed

journal article

scholarly

arxiv

preprint

Review types:

systematic review

meta-analysis

literature search

Paper quality:

foundational papers

seminal papers

landmark papers

highly cited

包含以下术语的查询会被路由至Perplexity进行学术定向搜索：

论文查找：

find papers

、

find articles

、

research papers on

、

published studies

引用相关：
```
cite
```
、
```
citation
```
、
```
doi
```
、
```
pubmed
```
、
```
pmid
```

学术来源：

peer-reviewed

、

journal article

、

scholarly

、

arxiv

、

preprint

综述类型：

systematic review

、

meta-analysis

、

literature search

论文质量：

foundational papers

、

seminal papers

、

landmark papers

、

highly cited

Deep Research (Routes to Parallel Chat API)

深度研究（路由至Parallel Chat API）

Only used when the user explicitly requests deep, exhaustive, or comprehensive research. Much slower and more expensive than parallel-cli search.

仅在用户明确要求深度、详尽或全面研究时使用。相比parallel-cli搜索，速度慢得多且成本更高。

Manual Override

手动指定后端

You can force a specific backend:

bash

undefined

你可以强制使用特定后端：

bash

undefined

Force parallel-cli search (fast web search)

强制使用parallel-cli搜索（快速网页搜索）

parallel-cli search "your query" -q "keyword" --json --max-results 10 -o sources/research_<topic>.json

Force Parallel Deep Research (slow, exhaustive)

强制使用Parallel深度研究（慢、详尽）

python research_lookup.py "your query" --force-backend parallel

Force Perplexity academic search

强制使用Perplexity学术搜索

python research_lookup.py "your query" --force-backend perplexity

---

python research_lookup.py "your query" --force-backend perplexity

---

Core Capabilities

核心功能

1. General Research Queries (parallel-cli search — DEFAULT)

1. 通用研究查询（parallel-cli搜索 — 默认）

Primary backend. Fast, cost-effective web search with academic source prioritization via the parallel-web skill.

Query Examples:
- "Recent advances in CRISPR gene editing 2025"
- "Compare mRNA vaccines vs traditional vaccines for cancer treatment"
- "AI adoption in healthcare industry statistics"
- "Global renewable energy market trends and projections"
- "Explain the mechanism underlying gut microbiome and depression"

bash

undefined

首选后端。通过parallel-web技能实现快速、低成本的网页搜索，优先返回学术来源。

查询示例：
- "2025年CRISPR基因编辑的最新进展"
- "癌症治疗中mRNA疫苗与传统疫苗的对比"
- "医疗行业AI采用率统计数据"
- "全球可再生能源市场趋势与预测"
- "肠道微生物组与抑郁症的潜在机制"

bash

undefined

Example: research on CRISPR advances

示例：CRISPR进展研究

parallel-cli search "Recent advances in CRISPR gene editing 2025"
-q "CRISPR" -q "gene editing" -q "2025"
--json --max-results 10 --excerpt-max-chars-total 27000
--include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,nature.com,science.org,cell.com,pnas.org,nih.gov"
-o sources/research_crispr_advances-academic.json

parallel-cli search "Recent advances in CRISPR gene editing 2025"
-q "CRISPR" -q "gene editing"
--json --max-results 10 --excerpt-max-chars-total 27000
-o sources/research_crispr_advances-general.json


**Response includes:**
- Synthesized findings with inline citations from search results
- Academic sources prioritized (peer-reviewed, preprints)
- Specific facts, numbers, and dates
- Sources section listing all referenced URLs grouped by type


**返回内容包括：**
- 结合搜索结果内嵌引用的整合研究发现
- 优先展示学术来源（同行评审、预印本）
- 具体事实、数据与日期
- 按类型分组列出所有参考URL的来源部分

2. Academic Paper Search (Perplexity sonar-pro-search)

2. 学术论文搜索（Perplexity sonar-pro-search）

Used for academic-specific queries. Prioritizes scholarly databases and peer-reviewed sources. Use when queries specifically ask for papers, citations, or DOIs.

Query Examples:
- "Find papers on transformer attention mechanisms in NeurIPS 2024"
- "Foundational papers on quantum error correction"
- "Systematic review of immunotherapy in non-small cell lung cancer"
- "Cite the original BERT paper and its most influential follow-ups"
- "Published studies on CRISPR off-target effects in clinical trials"

Response includes:

Summary of key findings from academic literature
5-8 high-quality citations with authors, titles, journals, years, DOIs
Citation counts and venue tier indicators
Key statistics and methodology highlights
Research gaps and future directions

适用于特定学术类查询。优先检索学术数据库与同行评审来源。当查询明确要求查找论文、引用或DOI时使用。

查询示例：
- "查找NeurIPS 2024中关于Transformer注意力机制的论文"
- "量子纠错领域的基础论文"
- "非小细胞肺癌免疫治疗的系统性综述"
- "引用原始BERT论文及其最具影响力的后续研究"
- "CRISPR临床试验中脱靶效应的已发表研究"

返回内容包括：

学术文献关键发现摘要
5-8篇高质量引用，包含作者、标题、期刊、年份、DOI
引用次数与期刊层级标识
关键统计数据与方法学亮点
研究空白与未来方向

3. Deep Research (Parallel Chat API — on request only)

3. 深度研究（Parallel Chat API — 仅按需使用）

Used only when user explicitly requests deep/exhaustive research. Provides comprehensive, multi-source synthesis via the Chat API (

core

model). 60s-5min latency.

Query Examples:
- "Deep research on the current state of quantum computing error correction"
- "Exhaustive analysis of mRNA vaccine platforms for cancer immunotherapy"

仅在用户明确要求深度/详尽研究时使用。通过Chat API（

core

模型）提供全面的多源整合内容。延迟60秒-5分钟。

查询示例：
- "量子计算纠错的当前发展现状深度研究"
- "癌症免疫治疗mRNA疫苗平台的详尽分析"

4. Technical and Methodological Information

4. 技术与方法学信息

Use parallel-cli search (default) for quick lookups:

bash

parallel-cli search "Western blot protocol for protein detection" \
  -q "western blot" -q "protocol" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  -o sources/research_western_blot.json

使用parallel-cli搜索（默认）进行快速查询：

bash

parallel-cli search "Western blot protocol for protein detection" \
  -q "western blot" -q "protocol" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  -o sources/research_western_blot.json

5. Statistical and Market Data

5. 统计与市场数据

Use parallel-cli search (default) for current data:

bash

parallel-cli search "Global AI market size and growth projections 2025" \
  -q "AI market" -q "statistics" -q "growth" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  --after-date 2024-01-01 \
  -o sources/research_ai_market.json

使用parallel-cli搜索（默认）获取当前数据：

bash

parallel-cli search "Global AI market size and growth projections 2025" \
  -q "AI market" -q "statistics" -q "growth" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  --after-date 2024-01-01 \
  -o sources/research_ai_market.json

Paper Quality and Popularity Prioritization

论文质量与影响力优先原则

CRITICAL: When searching for papers, ALWAYS prioritize high-quality, influential papers.

关键提示：查找论文时，务必优先选择高质量、高影响力的论文。

Citation-Based Ranking

基于引用量的排名

Paper Age	Citation Threshold	Classification
0-3 years	20+ citations	Noteworthy
0-3 years	100+ citations	Highly Influential
3-7 years	100+ citations	Significant
3-7 years	500+ citations	Landmark Paper
7+ years	500+ citations	Seminal Work
7+ years	1000+ citations	Foundational

论文年限	引用量阈值	分类
0-3年	20+引用	值得关注
0-3年	100+引用	高影响力
3-7年	100+引用	重要研究
3-7年	500+引用	里程碑论文
7+年	500+引用	开创性成果
7+年	1000+引用	奠基性研究

Venue Quality Tiers

期刊质量层级

Tier 1 - Premier Venues (Always prefer):

General Science: Nature, Science, Cell, PNAS
Medicine: NEJM, Lancet, JAMA, BMJ
Field-Specific: Nature Medicine, Nature Biotechnology, Nature Methods
Top CS/AI: NeurIPS, ICML, ICLR, ACL, CVPR

Tier 2 - High-Impact Specialized (Strong preference):

Journals with Impact Factor > 10
Top conferences in subfields (EMNLP, NAACL, ECCV, MICCAI)

Tier 3 - Respected Specialized (Include when relevant):

Journals with Impact Factor 5-10

一级 - 顶级期刊（优先选择）：

综合科学：Nature、Science、Cell、PNAS
医学：NEJM、Lancet、JAMA、BMJ
领域专属：Nature Medicine、Nature Biotechnology、Nature Methods
顶级CS/AI会议：NeurIPS、ICML、ICLR、ACL、CVPR

二级 - 高影响力专业期刊（优先选择）：

影响因子>10的期刊
子领域顶级会议（EMNLP、NAACL、ECCV、MICCAI）

三级 - 受认可专业期刊（相关时纳入）：

影响因子5-10的期刊

Technical Integration

技术集成

Prerequisites

前置条件

bash

undefined

bash

undefined

Primary backend (parallel-cli) - REQUIRED

主后端（parallel-cli） - 必需

Install parallel-cli if not already available:

若未安装parallel-cli，执行以下命令安装：

curl -fsSL https://parallel.ai/install.sh | bash

Or: uv tool install "parallel-web-tools[cli]"

或：uv tool install "parallel-web-tools[cli]"

Authenticate:

身份验证：

parallel-cli auth

Or: export PARALLEL_API_KEY="your_parallel_api_key"

或：export PARALLEL_API_KEY="your_parallel_api_key"

undefined

undefined

Environment Variables

环境变量

bash

undefined

bash

undefined

Primary backend (parallel-cli search) - REQUIRED

主后端（parallel-cli搜索） - 必需

export PARALLEL_API_KEY="your_parallel_api_key"

Deep research backend (Parallel Chat API) - optional, for deep research only

深度研究后端（Parallel Chat API） - 可选，仅用于深度研究

Uses the same PARALLEL_API_KEY

使用相同的PARALLEL_API_KEY

Academic search backend (Perplexity) - optional, for academic paper queries

学术搜索后端（Perplexity） - 可选，仅用于学术论文查询

export OPENROUTER_API_KEY="your_openrouter_api_key"

undefined

export OPENROUTER_API_KEY="your_openrouter_api_key"

undefined

API Specifications

API规格

parallel-cli search (PRIMARY):

Command:
```
parallel-cli search
```
with
```
--json
```
output
Latency: 2-10 seconds (fast)
Output: JSON with title, URL, publish_date, excerpts
Academic domains: Use
```
--include-domains
```
for scholarly sources
Saves results:
```
-o filename.json
```
for follow-up and reproducibility

Parallel Chat API (deep research only):

Endpoint:
```
https://api.parallel.ai
```
(OpenAI SDK compatible)
Model:
```
core
```
(60s-5min latency, complex multi-source synthesis)
Output: Markdown text with inline citations
Citations: Research basis with URLs, reasoning, and confidence levels
Rate limits: 300 req/min
Python package:
```
openai
```

Perplexity sonar-pro-search (academic only):

Model:
```
perplexity/sonar-pro-search
```
(via OpenRouter)
Search mode: Academic (prioritizes peer-reviewed sources)
Search context: High (comprehensive research)
Response time: 5-15 seconds

parallel-cli搜索（主后端）：

命令：
```
parallel-cli search
```
，搭配
```
--json
```
输出
延迟：2-10秒（快速）
输出：包含title、URL、publish_date、excerpts的JSON格式
学术域名：使用
```
--include-domains
```
参数筛选学术来源
保存结果：使用
```
-o filename.json
```
保存结果，便于后续使用与复现

Parallel Chat API（仅深度研究）：

端点：
```
https://api.parallel.ai
```
（兼容OpenAI SDK）
模型：
```
core
```
（延迟60秒-5分钟，支持复杂多源整合）
输出：带内嵌引用的Markdown文本
引用：包含URL、推理过程与置信度的研究依据
速率限制：300请求/分钟
Python包：
```
openai
```

Perplexity sonar-pro-search（仅学术）：

模型：
```
perplexity/sonar-pro-search
```
（通过OpenRouter）
搜索模式：学术（优先同行评审来源）
搜索上下文：高（全面研究）
响应时间：5-15秒

Command-Line Usage

命令行使用

bash

undefined

bash

undefined

Fast web search via parallel-cli (DEFAULT — recommended) — ALWAYS save to sources/

通过parallel-cli进行快速网页搜索（默认 — 推荐） — 务必保存至sources/目录

parallel-cli search "your query" -q "keyword1" -q "keyword2"
--json --max-results 10 --excerpt-max-chars-total 27000
-o sources/research_<topic>.json

Academic-focused search via parallel-cli — ALWAYS save to sources/

通过parallel-cli进行学术定向搜索 — 务必保存至sources/目录

parallel-cli search "your query" -q "keyword1"
--json --max-results 10 --excerpt-max-chars-total 27000
--include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,semanticscholar.org,biorxiv.org,medrxiv.org,nature.com,science.org,cell.com,pnas.org,nih.gov"
-o sources/research_<topic>-academic.json

Time-sensitive search via parallel-cli

通过parallel-cli进行时间敏感型搜索

parallel-cli search "your query" -q "keyword"
--json --max-results 10 --after-date 2024-01-01
-o sources/research_<topic>.json

Extract full content from a specific URL (use parallel-web extract)

提取特定URL的完整内容（使用parallel-web extract）

parallel-cli extract "https://example.com/paper" --json

Force Parallel Deep Research (slow, exhaustive) — via research_lookup.py

强制使用Parallel深度研究（慢、详尽） — 通过research_lookup.py

python research_lookup.py "your query" --force-backend parallel -o sources/research_<topic>.md

Force Perplexity academic search — via research_lookup.py

强制使用Perplexity学术搜索 — 通过research_lookup.py

python research_lookup.py "your query" --force-backend perplexity -o sources/papers_<topic>.md

Auto-routed via research_lookup.py (legacy) — ALWAYS save to sources/

通过research_lookup.py自动路由（旧版） — 务必保存至sources/目录

python research_lookup.py "your query" -o sources/research_YYYYMMDD_HHMMSS_<topic>.md

Batch queries via research_lookup.py — ALWAYS save to sources/

通过research_lookup.py批量查询 — 务必保存至sources/目录

python research_lookup.py --batch "query 1" "query 2" "query 3" -o sources/batch_research_<topic>.md

---

python research_lookup.py --batch "query 1" "query 2" "query 3" -o sources/batch_research_<topic>.md

---

MANDATORY: Save All Results to Sources Folder

强制要求：将所有结果保存至Sources目录

Every research-lookup result MUST be saved to the project's
sources/
folder.

This is non-negotiable. Research results are expensive to obtain and critical for reproducibility.

所有研究检索结果必须保存至项目的
sources/
目录。

这是硬性要求。研究结果获取成本高，且对复现性至关重要。

Saving Rules

保存规则

Backend	`-o` Flag Target	Filename Pattern
parallel-cli search (default)	`sources/research_<topic>.json`	`research_<brief_topic>.json` or `research_<brief_topic>-academic.json`
Parallel Deep Research	`sources/research_<topic>.md`	`research_YYYYMMDD_HHMMSS_<brief_topic>.md`
Perplexity (academic)	`sources/papers_<topic>.md`	`papers_YYYYMMDD_HHMMSS_<brief_topic>.md`
Batch queries	`sources/batch_<topic>.md`	`batch_research_YYYYMMDD_HHMMSS_<brief_topic>.md`

后端	`-o` 参数目标	文件名格式
parallel-cli搜索（默认）	`sources/research_<topic>.json`	`research_<简短主题>.json` 或 `research_<简短主题>-academic.json`
Parallel深度研究	`sources/research_<topic>.md`	`research_YYYYMMDD_HHMMSS_<简短主题>.md`
Perplexity（学术）	`sources/papers_<topic>.md`	`papers_YYYYMMDD_HHMMSS_<简短主题>.md`
批量查询	`sources/batch_<topic>.md`	`batch_research_YYYYMMDD_HHMMSS_<简短主题>.md`

How to Save

保存方法

CRITICAL: Every search MUST save results to the
sources/
folder using the
-o
flag.

CRITICAL: Saved files MUST preserve all citations, source URLs, and DOIs.

bash

undefined

关键提示：每次搜索必须使用
-o
参数将结果保存至
sources/
目录。

关键提示：保存的文件必须保留所有引用、来源URL与DOI。

bash

undefined

parallel-cli search (DEFAULT) — save JSON to sources/

parallel-cli搜索（默认） — 将JSON保存至sources/目录

parallel-cli search "Recent advances in CRISPR gene editing 2025"
-q "CRISPR" -q "gene editing"
--json --max-results 10 --excerpt-max-chars-total 27000
--include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,nature.com,science.org,cell.com,pnas.org,nih.gov"
-o sources/research_crispr_advances-academic.json

Academic paper search via Perplexity — save to sources/

通过Perplexity进行学术论文搜索 — 保存至sources/目录

python research_lookup.py "Find papers on transformer attention mechanisms in NeurIPS 2024"
-o sources/papers_20250217_143500_transformer_attention.md

Deep research via Parallel Chat API — save to sources/

通过Parallel Chat API进行深度研究 — 保存至sources/目录

python research_lookup.py "AI regulation landscape" --force-backend parallel
-o sources/research_20250217_144000_ai_regulation.md

Batch queries — save to sources/

批量查询 — 保存至sources/目录

python research_lookup.py --batch "mRNA vaccines efficacy" "mRNA vaccines safety"
-o sources/batch_research_20250217_144500_mrna_vaccines.md

undefined

python research_lookup.py --batch "mRNA vaccines efficacy" "mRNA vaccines safety"
-o sources/batch_research_20250217_144500_mrna_vaccines.md

undefined

Citation Preservation in Saved Files

保存文件中的引用保留

Each output format preserves citations differently:

Format	Citations Included	When to Use
parallel-cli JSON (default)	Full result objects: `title` , `url` , `publish_date` , `excerpts`	Standard use — structured, parseable, fast
Text (research_lookup.py)	`Sources (N):` section with `[title] (date) + URL` + `Additional References (N):` with DOIs and academic URLs	Deep research / Perplexity — human-readable
JSON ( `--json` via research_lookup.py)	Full citation objects: `url` , `title` , `date` , `snippet` , `doi` , `type`	When you need maximum citation metadata from deep research

For parallel-cli search, saved JSON files include: full search results with title, URL, publish date, and content excerpts for each result. For Parallel Chat API backend, saved files include: research report + Sources list (title, URL) + Additional References (DOIs, academic URLs). For Perplexity backend, saved files include: academic summary + Sources list (title, date, URL, snippet) + Additional References (DOIs, academic URLs).

Use
--json
when you need to:

Parse citation metadata programmatically
Preserve full DOI and URL data for BibTeX generation
Maintain the structured citation objects for cross-referencing

不同输出格式保留引用的方式不同：

格式	是否包含引用	使用场景
parallel-cli JSON（默认）	完整结果对象： `title` 、 `url` 、 `publish_date` 、 `excerpts`	标准场景 — 结构化、可解析、快速
文本（research_lookup.py）	`Sources (N):` 部分包含 `[标题] (日期) + URL` ，以及 `Additional References (N):` 部分包含DOI与学术URL	深度研究/Perplexity场景 — 易读
JSON（research_lookup.py的 `--json` 参数）	完整引用对象： `url` 、 `title` 、 `date` 、 `snippet` 、 `doi` 、 `type`	需要从深度研究中获取最大引用元数据时

对于parallel-cli搜索，保存的JSON文件包含：完整搜索结果，每条结果包含标题、URL、发布日期及内容摘要。 对于Parallel Chat API后端，保存的文件包含：研究报告 + 来源列表（标题、URL） + 附加参考文献（DOI、学术URL）。 对于Perplexity后端，保存的文件包含：学术摘要 + 来源列表（标题、日期、URL、摘要片段） + 附加参考文献（DOI、学术URL）。

当你需要以下操作时，使用
--json
参数：

以编程方式解析引用元数据
保留完整DOI与URL数据以生成BibTeX
维护结构化引用对象以便交叉引用

Why Save Everything

为何要保存所有结果

Reproducibility: Every citation and claim can be traced back to its raw research source
Context Window Recovery: If context is compacted, saved results can be re-read without re-querying
Audit Trail: The
```
sources/
```
folder documents exactly how all research information was gathered
Reuse Across Sections: Multiple sections can reference the same saved research without duplicate queries
Cost Efficiency: Check
```
sources/
```
for existing results before making new API calls
Peer Review Support: Reviewers can verify the research backing every citation

可复现性：每个引用与主张均可追溯至原始研究来源
上下文恢复：若上下文被压缩，无需重新查询即可重新读取保存的结果
审计追踪：
```
sources/
```
目录记录了所有研究信息的获取过程
跨章节复用：多个章节可引用同一保存的研究结果，无需重复查询
成本效益：发起新API调用前，先检查
```
sources/
```
目录是否已有相关结果
同行评审支持：评审人员可核实每个引用背后的研究依据

Before Making a New Query, Check Sources First

发起新查询前，先检查Sources目录

Before calling

research_lookup.py

, check if a relevant result already exists:

bash

ls sources/  # Check existing saved results

If a prior lookup covers the same topic, re-read the saved file instead of making a new API call.

调用

research_lookup.py

前，先检查是否已有相关结果：

bash

ls sources/  # 检查已保存的结果

若已有覆盖同一主题的查询结果，直接重新读取保存的文件，无需发起新API调用。

Logging

日志记录

When saving research results, always log:

[HH:MM:SS] SAVED: Research lookup to sources/research_20250217_143000_crispr_advances.md (3,800 words, 8 citations)
[HH:MM:SS] SAVED: Paper search to sources/papers_20250217_143500_transformer_attention.md (6 papers found)

保存研究结果时，务必记录日志：

[HH:MM:SS] 已保存：研究检索结果至sources/research_20250217_143000_crispr_advances.md（3800字，8条引用）
[HH:MM:SS] 已保存：论文搜索结果至sources/papers_20250217_143500_transformer_attention.md（找到6篇论文）

Integration with Scientific Writing

与科学写作的集成

This skill enhances scientific writing by providing:

Literature Review Support: Gather current research for introduction and discussion — save to
sources/
Methods Validation: Verify protocols against current standards — save to
sources/
Results Contextualization: Compare findings with recent similar studies — save to
sources/
Discussion Enhancement: Support arguments with latest evidence — save to
sources/
Citation Management: Provide properly formatted citations — save to
sources/

该技能通过以下方式助力科学写作：

文献综述支持：为引言与讨论部分收集最新研究 — 保存至
sources/
目录
方法验证：对照当前标准核实实验方案 — 保存至
sources/
目录
结果 contextualization：将研究结果与近期同类研究对比 — 保存至
sources/
目录
讨论内容增强：用最新证据支撑论点 — 保存至
sources/
目录
引用管理：提供格式规范的引用 — 保存至
sources/
目录

Complementary Tools

互补工具

Task	Tool
General web search (fast)	`parallel-cli search` (built into this skill)
Academic-focused web search	`parallel-cli search --include-domains` (built into this skill)
URL content extraction	`parallel-cli extract` (parallel-web skill)
Deep research (exhaustive)	`research-lookup` via Parallel Chat API or `parallel-web` deep research
Academic paper search	`research-lookup` (auto-routes to Perplexity)
Google Scholar search	`citation-management` skill
PubMed search	`citation-management` skill
DOI to BibTeX	`citation-management` skill
Metadata verification	`parallel-cli extract` (parallel-web skill)

任务	工具
通用网页搜索（快速）	`parallel-cli search` （内置该技能）
学术定向网页搜索	`parallel-cli search --include-domains` （内置该技能）
URL内容提取	`parallel-cli extract` （parallel-web技能）
深度研究（详尽）	`research-lookup` 通过Parallel Chat API或 `parallel-web` 深度研究
学术论文搜索	`research-lookup` （自动路由至Perplexity）
Google Scholar搜索	`citation-management` 技能
PubMed搜索	`citation-management` 技能
DOI转BibTeX	`citation-management` 技能
元数据验证	`parallel-cli extract` （parallel-web技能）

Error Handling and Limitations

错误处理与局限性

Known Limitations:

parallel-cli search: Requires
```
parallel-cli
```
to be installed and authenticated
Parallel Chat API (core model): Complex queries may take up to 5 minutes
Perplexity: Information cutoff, may not access full text behind paywalls
All backends: Cannot access proprietary or restricted databases

Fallback Behavior:

parallel-cli

is not found, install with

curl -fsSL https://parallel.ai/install.sh | bash

uv tool install "parallel-web-tools[cli]"

If parallel-cli search returns insufficient results, fall back to Perplexity or Parallel Chat API
If the selected backend's API key is missing, tries the other backend
If all backends fail, returns structured error response
Rephrase queries for better results if initial response is insufficient

已知局限性：

parallel-cli搜索：需安装并验证
```
parallel-cli
```
Parallel Chat API（core模型）：复杂查询可能耗时长达5分钟
Perplexity：存在信息截止日期，无法访问付费墙后的全文内容
所有后端：无法访问专有或受限数据库

** fallback行为：**

若未找到

parallel-cli

，执行

curl -fsSL https://parallel.ai/install.sh | bash

或

uv tool install "parallel-web-tools[cli]"

进行安装

若parallel-cli搜索返回结果不足， fallback至Perplexity或Parallel Chat API
若所选后端的API密钥缺失，尝试使用其他后端
若所有后端均失败，返回结构化错误响应
若初始响应结果不足，重新表述查询以获得更好的结果

Usage Examples

使用示例

Example 1: General Research (Routes to parallel-cli search)

示例1：通用研究（路由至parallel-cli搜索）

Query: "Recent advances in transformer attention mechanisms 2025"

Backend: parallel-cli search (default, fast)

Commands:

bash

parallel-cli search "Recent advances in transformer attention mechanisms 2025" \
  -q "transformer" -q "attention" -q "2025" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  --include-domains "arxiv.org,semanticscholar.org,nature.com,science.org,ieee.org,acm.org" \
  -o sources/research_transformer_attention-academic.json

parallel-cli search "Recent advances in transformer attention mechanisms 2025" \
  -q "transformer" -q "attention" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  -o sources/research_transformer_attention-general.json

Response: Synthesized findings with inline citations from academic and general sources, covering recent papers, key innovations, and performance benchmarks.

查询："2025年Transformer注意力机制的最新进展"

后端：parallel-cli搜索（默认、快速）

命令：

bash

parallel-cli search "Recent advances in transformer attention mechanisms 2025" \
  -q "transformer" -q "attention" -q "2025" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  --include-domains "arxiv.org,semanticscholar.org,nature.com,science.org,ieee.org,acm.org" \
  -o sources/research_transformer_attention-academic.json

parallel-cli search "Recent advances in transformer attention mechanisms 2025" \
  -q "transformer" -q "attention" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  -o sources/research_transformer_attention-general.json

响应：整合学术与通用来源的研究发现，内嵌引用，涵盖最新论文、关键创新与性能基准。

Example 2: Academic Paper Search (Routes to Perplexity)

示例2：学术论文搜索（路由至Perplexity）

Query: "Find papers on CRISPR off-target effects in clinical trials"

Backend: Perplexity sonar-pro-search (academic mode)

Response: Curated list of 5-8 high-impact papers with full citations, DOIs, citation counts, and venue tier indicators.

查询："查找CRISPR临床试验中脱靶效应的论文"

后端：Perplexity sonar-pro-search（学术模式）

响应：精选5-8篇高影响力论文，包含完整引用、DOI、引用次数与期刊层级标识。

Example 3: Comparative Analysis (Routes to parallel-cli search)

示例3：对比分析（路由至parallel-cli搜索）

Query: "Compare and contrast mRNA vaccines vs traditional vaccines for cancer treatment"

Backend: parallel-cli search (default, fast)

Response: Synthesized comparison from multiple web sources with inline citations, structured analysis, and evidence quality notes.

查询："对比癌症治疗中mRNA疫苗与传统疫苗的异同"

后端：parallel-cli搜索（默认、快速）

响应：整合多个网页来源的对比分析，内嵌引用，结构化分析内容，附带证据质量说明。

Example 4: Market Data (Routes to parallel-cli search)

示例4：市场数据（路由至parallel-cli搜索）

Query: "Global AI adoption in healthcare statistics 2025"

Backend: parallel-cli search (default, fast)

bash

parallel-cli search "Global AI adoption in healthcare statistics 2025" \
  -q "AI healthcare" -q "adoption statistics" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  --after-date 2024-01-01 \
  -o sources/research_ai_healthcare_adoption.json

Response: Current market data, adoption rates, growth projections, and regional analysis with source citations.

查询："2025年全球医疗行业AI采用率统计数据"

后端：parallel-cli搜索（默认、快速）

bash

parallel-cli search "Global AI adoption in healthcare statistics 2025" \
  -q "AI healthcare" -q "adoption statistics" \
  --json --max-results 10 --excerpt-max-chars-total 27000 \
  --after-date 2024-01-01 \
  -o sources/research_ai_healthcare_adoption.json

响应：当前市场数据、采用率、增长预测与区域分析，附带来源引用。

Summary

总结

This skill serves as the primary research interface with intelligent tri-backend routing:

parallel-cli search (default): Fast, cost-effective web search with academic source prioritization via the parallel-web skill
Parallel Chat API (
```
core
```
model): Deep, exhaustive multi-source synthesis (on explicit request only)
Perplexity sonar-pro-search: Academic-specific paper searches only
Automatic routing: Detects query type and routes to the optimal backend
Manual override: Force any backend when needed
Academic prioritization: Two-search pattern ensures scholarly sources surface for scientific queries

该技能作为核心研究接口，具备智能三后端路由功能：

parallel-cli搜索（默认）：通过parallel-web技能实现快速、低成本的网页搜索，优先返回学术来源
Parallel Chat API（
```
core
```
模型）：深度、详尽的多源整合内容（仅明确请求时使用）
Perplexity sonar-pro-search：仅用于特定学术论文搜索
自动路由：检测查询类型并路由至最优后端
手动指定：按需强制使用任意后端
学术优先：双搜索模式确保科学类查询能获取学术资源