ANDYPENG09/catalyst-search-skill

催化文献检索 (Catalyst Search)

何时使用 | When to use

• 用户要"查催化文献 / 找催化剂论文 / 检索 XX 催化剂 / 文献综述 / 催化剂研究进展 / 帮我找几篇 XX 的文章"
  • Users asking to "search catalyst literature / find catalyst papers / retrieve XX catalyst / do a literature review / catalyst research progress / find me some papers on XX"
• 典型输入：催化剂主题、反应类型（HER/OER/ORR/PEMWE/光催化）、材料体系（Pt/C、PtCo、HEA、SAC、IrO₂ 等）
  • Typical input: catalyst topic, reaction type (HER/OER/ORR/PEMWE/photocatalysis), material system (Pt/C, PtCo, HEA, SAC, IrO₂, etc.)

何时不使用 | When NOT to use

• 催化剂设计/选型建议（组分、合成路线）→ 用 catalyst-design（本技能只检索文献，不给设计建议）
  • Catalyst design/selection advice (composition, synthesis route) → use catalyst-design (this skill only retrieves literature, gives no design advice)
• 非催化领域的文献检索（如纯有机合成、药物化学）→ 不适用
  • Non-catalysis literature search (e.g., pure organic synthesis, medicinal chemistry) → not applicable
• 仅需查一个已知 DOI 的论文 → 用 WebFetch 直接抓取即可
  • Just fetching a paper with a known DOI → use WebFetch directly

前置条件 | Prerequisites

• 需 WebSearch（topic=academic）与 WebFetch 工具可用；二者不可用则无法检索
  • Requires WebSearch (topic=academic) and WebFetch; without them retrieval is impossible
• 本技能自带检索要点（references/）与输出模板（templates/），不依赖任何付费数据库账号
  • Ships with search essentials (references/) and output templates (templates/); depends on no paid-database account

输入接口 | Input interface

• 必填 | Required：检索主题（自然语言，含以下之一即可：反应类型 / 材料体系 / 性能目标）
  • Search topic (natural language; must contain at least one of: reaction type / material system / performance target)
• 可选 | Optional：时间范围、语种偏好、是否仅限 OA
  • Time range, language preference, OA-only restriction

催化领域检索要点（通用检索维度，用于构造检索式） | Search essentials (generic dimensions for building queries)

• 反应类型 | Reaction types：hydrogen evolution reaction (HER)、oxygen evolution reaction (OER)、oxygen reduction reaction (ORR)、overall water splitting（全解水/双功能）、proton exchange membrane water electrolysis (PEMWE)、anion exchange membrane (AEM)、photocatalysis、plastic upcycling
  • 务必区分酸性 / 碱性介质 | Always distinguish acidic vs alkaline media：同一反应在酸/碱下机理、催化剂、评价基准差异大（如酸性 OER 只有 Ir/Ru 基稳定；碱性 HER 速控步是水解离）。
    • The mechanism, catalyst, and benchmark for the same reaction differ greatly between acid and base (e.g., only Ir/Ru-based catalysts are stable for acidic OER; the rate-determining step of alkaline HER is water dissociation).
  • 各反应体系（HER/OER/ORR/全解水）的专门检索词表、性能基准、机理与表征关键词详见 references/reaction_systems.md（含文献支撑基准值，用于判断文献相关性与先进性）。
    • Reaction-specific keyword lists, performance benchmarks, and mechanism/characterization terms are detailed in references/reaction_systems.md (with literature-backed benchmark values for judging relevance and advancement).
• 催化剂体系 | Catalyst systems：Pt/C、Pt-Co alloy / intermetallic、high-entropy alloy (HEA)、single-atom catalyst (SAC)、core-shell、IrO₂ / IrOₓ、Ru@IrOₓ、N/S-doped carbon、MOF-derived
• 性能指标 | Performance metrics：overpotential @10 mA cm⁻²、ECSA、mass activity (MA, A/mgₚₜ)、turnover frequency (TOF)、Tafel slope、stability / durability
• 表征与测试 | Characterization & testing：XRD (particle size)、TEM、XPS、rotating disk electrode (RDE)、membrane electrode assembly (MEA)
• 合成方法 | Synthesis methods：Joule heating、strong electrostatic adsorption (SEA)、microwave-assisted、continuous-flow
• 缩写扩展 | Abbreviation expansion：PtCo→"Pt-Co alloy" OR "Pt cobalt intermetallic"；HEA→"high-entropy alloy"；SAC→"single-atom catalyst"
• 期刊/来源分布 | Journals / source distribution：优先选用高影响因子（IF）期刊、高被引文章与近 5–10 年内的文献。英文文献以高 IF 期刊（如 Adv. Energy Mater.、Nat. Commun.、Angew. Chem.、Energy Environ. Sci.、J. Power Sources、Chem. Eng. J，及 ScienceDirect/Elsevier、ACS、RSC、Nature 子刊等）与高被引文章为优先来源（既有期刊可作参考）；中文文献不指定具体期刊，不做期刊级别来源限制；标准 / 专利（TCASMES 400-2024、T/CRES 0030-2025、企业专利）仍可作来源。
  • Journal / source distribution: prioritize high-impact-factor (IF) journals, highly cited papers, and literature from the last 5–10 years. English: use high-IF journals (Adv. Energy Mater., Nat. Commun., Angew. Chem., Energy Environ. Sci., J. Power Sources, Chem. Eng. J, ScienceDirect/Elsevier, ACS, RSC, Nature family) and highly cited papers as priority sources (existing journals serve as reference). Chinese: do NOT specify particular journals and impose NO journal-tier restriction. Standards/patents (TCASMES 400-2024, T/CRES 0030-2025, corporate patents) remain valid sources.

工作流 | Workflow

1. 语义解析 + 检索式生成 | Semantic parsing + query generation：按"反应类型 + 催化剂体系 + 性能指标/表征"组合；缩写按上节扩展；同义词用 OR 连接。
   • Combine "reaction type + catalyst system + performance/characterization"; expand abbreviations per above; connect synonyms with OR.
2. 并行检索 | Parallel search：用 WebSearch（topic=academic）并行检索各组；权威来源优先 ScienceDirect（https://www.sciencedirect.com/）、arXiv（https://arxiv.org/）、OpenAlex（https://openalex.org/）、Google Scholar。
   • Use WebSearch (topic=academic) in parallel per group; prioritize authoritative sources: ScienceDirect, arXiv, OpenAlex, Google Scholar.
   • 失败降级（M2b）| Fallback (M2b)：若某组返回空或超时 → 放宽（拆 AND 为 OR、去限定词）或换源（直接检索 Google Scholar / OpenAlex）；若全部为空 → 如实告知"未检索到相关文献"，不得编造。
     • If a group returns empty or times out → relax (split AND to OR, drop qualifiers) or switch source (search Google Scholar / OpenAlex directly); if all empty → state honestly that no relevant literature was found; never fabricate.
3. 抓取摘要 | Fetch abstracts：对最相关 3-5 篇用 WebFetch 抓摘要页（优先期刊官网 / Semantic Scholar / arXiv / PubMed；付费墙内抓到摘要 + 元数据 + DOI 即可）。仅凭摘要即可判断是否为目标文献，无需下载或引用全文。
   • For the 3-5 most relevant papers, use WebFetch to grab the abstract page (prefer journal site / Semantic Scholar / arXiv / PubMed; behind a paywall, abstract + metadata + DOI suffices). Abstracts alone are enough to judge relevance; full-text download or citation is unnecessary.
4. 提取元数据 | Extract metadata：标题、作者、期刊/来源、年份、DOI、摘要要点。
   • Title, authors, journal/source, year, DOI, abstract highlights.
5. 过滤去重 + 排序 | Filter, deduplicate, rank：按相关性、影响因子（IF）/ 被引量、时效性（优先近 5–10 年）排序；标注 OA 可获取状态（已获取 / 在线 / 付费 / 手动）。
   • Rank by relevance, impact factor (IF) / citation count, and recency (prefer last 5–10 years); label OA availability (obtained / online / paywalled / manual).
   • 结果校验（M5b）| Result validation (M5b)：对每篇用 WebFetch 验证 DOI/摘要可访问（付费墙至少元数据存在）；去重（同 DOI/规范化标题）；仅保留摘要明确含目标反应类型与催化剂体系的文献，剔除仅关键词命中但不相关者。
     • Verify DOI/abstract accessibility via WebFetch for each paper (paywalled at least metadata must exist); deduplicate (same DOI / normalized title); keep only papers whose abstract explicitly contains the target reaction type and catalyst system; drop keyword-only hits.
6. 输出 | Output：按 templates/literature_matrix.md 输出文献矩阵 + 支撑结论 + 验证建议。引用格式见 templates/citation_gb7714.md。
   • Output the literature matrix + supporting conclusions + validation suggestions per templates/literature_matrix.md. Citation format: templates/citation_gb7714.md.

输出接口（标准格式，供 catalyst-design 消费） | Output interface (standard format, consumed by catalyst-design)

• 必须以 templates/literature_matrix.md 的表格格式输出文献矩阵，字段：序号 / 标题 / 作者 / 期刊·来源 / 年份 / DOI / 反应类型 / 催化剂体系 / 关键指标 / OA状态 / 摘要要点 / 相关性
  • Output the literature matrix in the table format of templates/literature_matrix.md with fields: No. / Title / Authors / Journal·Source / Year / DOI / Reaction type / Catalyst system / Key metrics / OA status / Abstract highlights / Relevance
• 矩阵后附两段：支撑结论（对研究问题的证据总结）、验证建议（XRD/TEM/XPS 表征、RDE/MEA 测试、对照实验）
  • After the matrix, append two sections: Supporting conclusions (evidence summary for the research question) and Validation suggestions (XRD/TEM/XPS characterization, RDE/MEA tests, control experiments)
• 本输出即视为"文献检索结果"，可直接作为 catalyst-design 的输入（参见 catalyst-design 的"输入接口"）
  • This output is treated as the "literature search result" and can be fed directly into catalyst-design (see catalyst-design's "Input interface")

数据源 | Data sources

• ScienceDirect（https://www.sciencedirect.com/）、arXiv（https://arxiv.org/）、OpenAlex（https://openalex.org/）、Google Scholar
• 催化剂结构数据参考 Materials Project（https://next-gen.materialsproject.org/apps），用 WebFetch 检索其公开页面；本技能不内置计算
  • Catalyst structural data refer to Materials Project; retrieve its public pages via WebFetch. This skill does no built-in computation.

能力边界 | Capability boundaries

• 详见 references/capabilities.md
  • See references/capabilities.md

与其他能力分工 | Division of labor

• 本技能仅负责文献检索与整理；催化剂设计建议由 catalyst-design 负责
  • This skill only retrieves and organizes literature; catalyst design advice is handled by catalyst-design.
• 仅使用 WebSearch(academic) 与 WebFetch；不内置、不复制任何其他专用检索工具的内部接口
  • Only WebSearch(academic) and WebFetch are used; no built-in or copied internal interfaces of other specialized search tools.

注意事项 | Notes

• 多重 AND 组合过苛易返回空，宜放宽或拆组（如 HER + Pt + HEA 三组分别检索再合并）
  • Over-strict AND combinations easily return empty; relax or split groups (e.g., search HER + Pt + HEA separately then merge).
• 引用文献必须真实可查；用 WebFetch 验证 DOI/摘要，不得编造
  • Cited papers must be verifiable; validate DOI/abstract via WebFetch; never fabricate.
• 输出末尾注明检索来源（开放网络）与可获取状态
  • Note the search source (open web) and availability status at the end of output.
• 检索结果字段差异大，WebSearch 返回块需自行解析标题/作者/来源/年份
  • Search-result fields vary widely; parse title/authors/source/year from WebSearch output blocks yourself.
• 安全与权限 | Safety & permissions：本技能仅用 WebSearch/WebFetch 访问公开学术网页；不执行系统命令、不写入用户文件、不登录任何付费数据库、不收集或外传用户数据。
  • This skill only accesses public academic pages via WebSearch/WebFetch; runs no system commands, writes no user files, logs into no paid database, collects or exfiltrates no user data.

示例 | Example

• 输入：检索"碱性 HER 单原子催化剂，近 5 年"
• 输出：文献矩阵（3–5 篇，含标题/作者/期刊/年份/DOI/反应类型/催化剂体系/关键指标η₁₀与Tafel/OA状态/摘要要点/相关性）+ 支撑结论（如"Ru SAs/N-C 的 η₁₀ 低至 29 mV，水解离能垒降至 ~0.5 eV"）+ 验证建议（XPS 确认单原子分散、RDE 测 η₁₀/Tafel、DFT 算 ΔG_H*）。
  • Input: search "alkaline HER single-atom catalysts, last 5 years"
  • Output: a literature matrix (3–5 papers with full fields) + supporting conclusions (e.g., Ru SAs/N-C reaches η₁₀ 29 mV, water-dissociation barrier ~0.5 eV) + validation suggestions (XPS for atom dispersion, RDE for η₁₀/Tafel, DFT for ΔG_H*).

项目主页 | Project home

• GitHub：https://github.com/ANDYPENG09/catalyst-search-skill （源码、更新与 Issue 反馈 | source, updates & issues）
• 配套技能 | Companion：https://github.com/ANDYPENG09/catalyst-design-skill （催化剂设计指导 | catalyst design guidance）