科研 Skill
综述写作助手
surveymaster
端到端文献搜集、综述写作与 DOCX 交付
Skill 说明
端到端学术综述写作编排 skill;从写作约束采集、文献搜集、文献库构建、综述大纲生成、正文撰写和终稿检查,到 DOCX、LaTeX、BibTeX 导出及可选 PDF。 | 输入:综述主题、学科、语言、引用格式、输出目录、目标论文数量、重点方向和额外要求 | 输出:writing_constraints、papers.json、outline、mainbody.tex、references.bib、DOCX、LaTeX 及可选 PDF
SKILL.md
Role
This is the top-level SurveyMaster orchestration skill. It coordinates the child instruction files and helper scripts in this directory to produce a complete academic survey and final deliverables.
In SpeedClaw/Codar, the skill loader registers only this top-level SKILL.md
as the surveymaster skill. Nested SKILL.md files are not registered as
separate loadable skills. Treat the files listed below as child instruction
files: read them lazily from this skill directory immediately before the stage
that needs them, resolve their scripts/assets relative to their own directory,
and follow their stage contracts.
This top-level file defines the required execution order, handoff files, confirmation gates, and browser-use requirements.
Child Instruction Files
Read child instruction files lazily, immediately before the stage that needs them:
surveymaster-identify/SKILL.mdsurveymaster-literature-library/SKILL.mdsurveymaster-generate-outline/SKILL.mdwrite_section/surveymaster-write-section/SKILL.mdsurveymaster-finalize/SKILL.md
Supporting/reference instruction files used by the stages:
surveymaster-browser-search/SKILL.mdsurveymaster-check-and-merge/SKILL.mdsurveymaster-figure-types/SKILL.mdsurveymaster-table-types/SKILL.mdsurveymaster-export/SKILL.md
Required Inputs
Collect or infer the following before starting:
topic— survey topic.subject— discipline or research field.language—zhoren.citation_style— one supported style, confirmed before Stage 1 completes.output_dir— survey workspace directory.- Optional:
target_paper_count,focus_points,reference_surveys,year_range,extra_requirements,total_length_target, andsection_length_policy.
If output_dir is not provided, create or choose a dedicated workspace and use
that path consistently as $WORK.
Workspace Contract
All stages operate on the same $WORK directory.
Canonical files:
| Stage | File |
|---|---|
| Stage 1 | $WORK/writing_constraints.json, $WORK/writing_constraints.md |
| Stage 2 | $WORK/papers.json |
| Stage 3 | $WORK/outline.json, $WORK/outline.md |
| Stage 4 | $WORK/mainbody.tex, $WORK/figures/ |
| Stage 5 | $WORK/references.bib, final .docx, .tex, optional .pdf |
Do not duplicate source-of-truth data in prompts when a downstream script can read the canonical file directly.
File Write Policy
Use Write or Edit for file writes performed by the agent. Do not use shell
heredocs for LaTeX or JSON content because backslashes can be corrupted.
Helper scripts may write their own outputs normally.
Stage 0 — Preflight
Before running child instruction files:
- Confirm
$WORKexists or create it. - Confirm the current request has
topic,subject, andlanguage. - If the request provides an unambiguous supported
citation_style, pass it through to Stage 1. - If
citation_styleis missing, unsupported, or ambiguous, do not ask from this top-level file. Readsurveymaster-identify/SKILL.mdand follow its Citation Style gate exactly.
The top-level orchestrator must not duplicate or override the citation-style
option list. Stage 1 owns the supported-style list, the ask_user prompt, and
the citation_style_confirmed value.
Stage 1 — Identify Writing Constraints
Read surveymaster-identify/SKILL.md.
Goal: create:
$WORK/writing_constraints.json$WORK/writing_constraints.md
Pass the topic, subject, language, optional citation style, and optional user constraints.
This stage:
- preserves user intent as operational constraints;
- records focus points, target paper count, year range, length policy, and venue/style notes;
- detects and resolves user-provided seed papers using browser-use or remote-browser only;
- records venue/style constraints, using browser-use or remote-browser only when the user asks for target journal or venue-specific requirements;
- writes
citation_style,citation_style_confirmed, andfigure_color_policy. For economics empirical-style templates only, Stage 1 may ask the user once whether generated mechanism/workflow/review schematic figures should use low-saturation academic color or black-and-grayscale journal style.
Gate:
- Do not proceed unless
writing_constraints.jsonexists andcitation_style_confirmedis true. - Display
writing_constraints.mdas an informational summary. - Do not ask for a second confirmation of writing constraints.
Stage 2 — Build Literature Library
Read surveymaster-literature-library/SKILL.md.
Goal: create and validate:
$WORK/papers.json
Execution:
-
Insert resolved seed papers from
writing_constraints.json. -
Decompose the topic and focus points into 3-5 English search phrases.
-
For Stage 2 candidate discovery, use browser-use or remote-browser only. Treat browser-use/remote-browser as a capability category and required infrastructure, not as a literal tool-name requirement or an optional search backend. It includes any runtime-exposed browser automation tool that can open real web pages, navigate/search, inspect page content, and write extracted candidates, including deferred MCP tools such as
mcp_remote_browser_*. Do not start, continue, recover, or supplement withPaperSurveyToFile,PaperSearch, academic search APIs, generic WebSearch, DOI/title lookup APIs, OpenAlex/Crossref/Semantic Scholar/CORE/Lens API endpoints, or any other non-browser retrieval tool. Opening an API endpoint in browser-use/remote-browser does not make it a valid browser discovery branch. OpenAlex/Crossref may be used only bydiscover_and_resolve_papers.pyafter the merged browser candidate file has already been written. Do not ask the user to choose between browser-use and academic-search, and never mark academic-search or any non-browser search tool as recommended. Have the agent call browser-use, remote-browser, or an equivalent discovered browser MCP tool and write candidates to$WORK/.cache/scratch/browser_candidates.json. When the runtime supports multiple browser-use/remote-browser sessions, run independent query/site searches in parallel and save each branch under$WORK/.cache/scratch/browser_candidates.<branch>.json; after all branches finish, merge/deduplicate them into$WORK/.cache/scratch/browser_candidates.json, then resolve and import them with:python3 <literature_skill_dir>/scripts/discover_and_resolve_papers.py \ --work "$WORK" \ --candidates-json "$WORK/.cache/scratch/browser_candidates.json" \ --library "$WORK/papers.json" \ --bibliography-script "<literature_skill_dir>/scripts/bibliography_library.py" -
If browser-use/remote-browser does not appear available, do not infer final unavailability from planning context, a missing convenience shortcut, or the absence of a literal tool named
browser-use. First run the runtime's tool discovery/find_tools mechanism with queries such asbrowser,remote-browser,remote browser,browser automation, andMCP remote browser. If tools such asmcp_remote_browser_*are discovered, activate and use them as browser-use/remote-browser equivalents. Only after discovery and an actual invocation failure showing the browser service is not started may the agent treat browser tooling as unavailable; then stop Stage 2 and ask the user to enable browser-use/remote-browser. Do not offer academic-search, PaperSearch, PaperSurveyToFile, WebSearch, or DOI/title lookup as a fallback or selectable alternative. Do not callask_user,request_user_input, or any choice UI with non-browser search options; if a UI prompt is unavoidable, it may only ask the user to enable browser-use/remote-browser or stop Stage 2, and it must not include any recommended fallback. -
If browser-use/remote-browser is available but individual searches fail, retry with browser-use/remote-browser using adjusted sites, queries, or timing. Access/CAPTCHA/rate-limit failures are reported as browser failures; they do not authorize non-browser search tools.
-
Manual
batch.jsoninsertion is not a search fallback and is not available for Stage 2 candidate discovery or abstract/digest supplementation timeouts. If abstract supplementation times out, first count successfully supplemented records with information-rich abstracts. When the count is at least 30, stop searching and proceed with those records. When the count is below 30, retry supplementation once with an about-25-second timeout and 4-6 concurrent branches where supported. If the retry still leaves fewer than 30 successful records, ask the user whether to continue browser-use/remote-browser searching/supplementing, narrow scope, or proceed. Abstract supplementation must use browser-opened source pages such as publisher, journal, PubMed/PMC, CNKI detail, NBER, SSRN, RePEc, CEPR, IZA, author, or institutional repository pages. Do not use OpenAlex/Crossref API responses as the primary abstract source. Do not createbatch.jsonfrom search previews, browser candidates, non-browser search output, or half-resolved candidates after abstract timeout. -
Validate after every import:
python3 <literature_skill_dir>/scripts/bibliography_library.py validate \ --library "$WORK/papers.json" -
Run
statsfor compact reporting. Do not read the entire rawpapers.jsonsolely to report progress.
Gate:
papers.jsonmust exist and validate.- If coverage is far below
target_paper_count, ask the user whether to proceed, narrow scope, expand year range, or add papers.
Stage 3 — Generate Outline
Read surveymaster-generate-outline/SKILL.md.
Goal: create:
$WORK/outline.json$WORK/outline.md$WORK/.cache/scratch/outline_self_check.json
Execution:
-
Generate a structured outline from topic,
writing_constraints.json, andpapers.json. -
Write the generated JSON to
$WORK/outline.json. -
Normalize and render with:
python3 <outline_skill_dir>/scripts/save_outline.py \ --file "$WORK/outline.json" -
Run the mandatory outline self-check described by
surveymaster-generate-outline. -
Save or update
outline.mdthrough the platform's user-visible file preview/update mechanism, then display/preview it for the user. -
Ask the Stage 3 outline approval gate with
ask_userandallow_other: false.
Hard gate:
- Do not proceed to Stage 4 until the user selects
Accept and start writing/接受,开始写作in the Stage 3ask_usergate. - If the user selects
I want changes/我要修改, stop and ask the user to provide the requested outline changes in the next message. Do not start writing. - If
ask_useris unavailable, times out, returns no answer, or returns a fallback/proceed-best-judgment message, treat the outline as unconfirmed. Stop and wait for explicit user input; do not proceed to Stage 4. - After receiving requested changes, mutate
outline.jsonfirst, re-runsave_outline.py, re-display/preview the outline, and ask the sameask_userconfirmation gate again. - Never edit
outline.mddirectly as the source of truth.
Stage 4 — Write Full Body
Read write_section/surveymaster-write-section/SKILL.md.
Goal: create:
$WORK/mainbody.tex$WORK/figures/<id>.pngwhen figures are planned
Execution:
- Build compact paper context through
surveymaster-literature-libraryusingbuild-write-context. - Write a single complete
mainbody.texbody fragment in one pass. - Do not create separate section files.
- Ensure
mainbody.texstarts with\begin{abstract}and contains:\keywords{}\maketitle\tableofcontents- all required
\section{}entries
- Do not include LaTeX wrappers such as
\documentclass,\usepackage,\begin{document},\end{document}, bibliography commands, or manual reference lists. - Use only
\cite{key}keys allowed by the compact citation map. - If figures are planned, read
surveymaster-figure-types/SKILL.mdto build% FIGUREprompts, call the agent'simage_gentool to generate matching$WORK/figures/<id>.pngfiles. - If tables are planned, read
surveymaster-table-types/SKILL.mdto build compliant domain-specific tables. - Validate and promote the scratch
mainbody.texusingsurveymaster-check-and-merge/scripts/survey_checks.py repair-structure.
Gate:
mainbody.texmust exist and pass structure validation.- Figure/table count warnings may be reported, but unresolved fatal structure errors must be fixed before Stage 5.
Stage 5 — Finalize And Export
Read surveymaster-finalize/SKILL.md.
Goal: produce and persist final deliverables:
$WORK/references.bib$WORK/<stem>.docx$WORK/<stem>.tex$WORK/<stem>.pdfwhen the default optional PDF attempt succeeds
Execution order is owned by surveymaster-finalize/SKILL.md and must not be
reordered:
- Citation audit.
- Initial BibTeX export from
mainbody.texandpapers.json. - Metadata verification and volume/pages resolution.
- Final BibTeX sync.
- Full deterministic checks.
- Mandatory single LLM fix pass.
- Structure validation of fixed body.
- Rebuild
references.bibafter fix pass. - Unified export through
surveymaster-export/SKILL.md.
PDF is attempted by default as an optional deliverable, and is not a fallback
artifact. The only valid PDF is produced by
surveymaster-export/scripts/export_all.py through latexmk -xelatex and is
reported with engine=latexmk-xelatex or pdf_engine=latexmk-xelatex. Do not
use HTML-to-PDF, browser print-to-PDF, screenshots, Pandoc-to-PDF, or any
separate PDF conversion skill/tool for this workflow.
10. Final cite consistency check against references.bib.
11. Persist all required deliverables, and persist PDF only when it succeeds.
Important:
references.bibis generated in Stage 5 bysurveymaster-literature-library/scripts/bibliography_library.py export-bib.- It is first created during Step 5-A Phase 2.
- It is rebuilt after the Step 5-B fix pass so it matches the final
mainbody.texcitation set. - Do not run export with a stale
references.bib.
Post-Export Revision Routing
Any change after export makes previous deliverables stale.
Route requests as follows:
- Export-only change: rerun Stage 5.
- Local content/style change: run Stage 4 in rewrite mode or a refinement skill, then Stage 5.
- Figure/table insertion/removal/regeneration: edit
mainbody.texandoutline.jsonconsistently, regenerate local image assets when needed, re-runsave_outline.py, then Stage 5. - Paper/library change: update
papers.json, validate, decide whether Stage 3 or Stage 4 must be rerun, then Stage 5. - Outline change: mutate
outline.json, re-renderoutline.md, get explicit user confirmation, rerun Stage 4, then Stage 5. - Language change: rerun Stage 1, Stage 3, get outline confirmation, rerun
Stage 4, then Stage 5. Never machine-translate existing
.texfiles.
Reporting
At each gate, report concise status and the next required action.
Final response after Stage 5 must include:
- what was completed;
- deliverable status by format;
- any failed or skipped formats;
- any user-actionable warnings.
Do not present stale deliverables as current.
相关科研 Skill
中药材分子鉴定用ITS2等DNA条形码鉴定药材基原物种,处理多基原与降解样品局限。适用于药材真伪鉴别研究,不替代法定检验。
中药网络药理学用TCMSP等数据库构建成分-靶点-通路网络并做富集分析,批判性讨论方法学局限。适用于中药机制假设生成与论文方法复核。
中医术语标准与知识图谱建立中医药术语与WHO/ICD-11标准的映射,设计本体并用Neo4j构建知识图谱。适用于数据整合与科研检索,不作临床决策系统。
方剂配伍规律挖掘对方剂做药名规范化、关联规则与网络聚类分析,发现候选核心药组。适用于用药规律挖掘,结果仅为待验证假设,不作处方依据。
证候与症状数据分析对症状量表数据做术语规范、潜在类别与因子分析,探索统计学证候模式。适用于证候分型研究,结果不用于个体辨证诊断。
泵用混合物热力学计算Calculates thermodynamic properties and mixture phase behavior for pump applications using the thermo Python library’s DIPPR/NIST correlations. Use for VLE or mixture property calculations.
常见问题
综述写作助手能做什么?
端到端学术综述写作编排 skill;从写作约束采集、文献搜集、文献库构建、综述大纲生成、正文撰写和终稿检查,到 DOCX、LaTeX、BibTeX 导出及可选 PDF。 | 输入:综述主题、学科、语言、引用格式、输出目录、目标论文数量、重点方向和额外要求 | 输出:writing_constraints、papers.json、outline、mainbody.tex、references.bib、DOCX、LaTeX 及可选 PDF。
如何安装综述写作助手?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「综述写作助手」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
综述写作助手需要哪些权限?
该科研 Skill声明需要:本地文件。安装前会再次列出,由你确认后才会生效。
综述写作助手经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。