科研 Skill
通用深度文献综述研究
food-deep-research
General-purpose deep research producing a source-validated, fully written literature review via a 12-subagent team. Use for a thorough review or deep-dive needing verified sources.
SKILL.md
Deep-Research — Source-Validated Literature Review Engine
Answer a hard question properly and hand back a written, formatted, integrity-
checked literature review — not just notes. Scope → design → discover → screen
by journal ranking → validate sources → extract & verify evidence → synthesize →
stress-test → write → review-loop → final report. Original work; architecture
informed by open community food-deep-research skills (see the repo README
Acknowledgements). Usable standalone, or as the deep-dive engine called by
food-research.
Modes
- quick brief — scope → discover → screen (Tier 1) → light synthesis → short sourced answer. Skips the full validation/compile/review loop.
- full — the default: the complete 12-subagent pipeline below with the iterate-to-saturation and compile↔review loops, ending in a finished review.
Subagent team (dispatch via the Agent tool)
| # | Subagent | Job |
|---|---|---|
| 1 | research_scope | Comprehensive scope brief: background, problem, significance, central + sub-questions, concepts, boundaries, success criteria. |
| 2 | research_architect | Methodology blueprint: review type, search strategy, inclusion criteria, analytical framework, reporting standard, stopping criteria. |
| 3 | investigator | Pass 1 discover candidate sources; Pass 2 extract evidence from validated sources only (parallel per sub-question). |
| 4 | source_screener | Prioritize candidates by journal ranking (Tier 1 Q1/Q2 + Nature/Science/Cell + other-discipline Q1/Q2; Tier 2 Q3; avoid Tier 4). |
| 5 | source_verifier | Validate each prioritized source (existence/DOI, venue legitimacy, retraction, predatory, methodology, COI) → Source Quality Matrix. |
| 6 | bibliography | Deduplicate + format references (APA 7.0 default, or target-journal style via journal-selector); build the citation map + .bib/.ris. |
| 7 | claim_verifier | Verify each load-bearing claim against its validated source; classify fact/hypothesis/contested/speculation. |
| 8 | synthesizer | Evidence matrix, thematic synthesis, conflict reconciliation, evidence grading, coverage advisory, gap agenda, narrative arc. |
| 9 | critic | Devil's advocate on the synthesis; loop back to investigate if gaps. |
| 10 | compiler | Write & format the literature-review draft (APA 7.0 / target journal); cite by key only; no fabrication. |
| 11 | editor | Editorial review of the draft (5 weighted dimensions, verdict + prioritized feedback). |
| 12 | ethics_reviewer | Integrity/ethics review of the draft (citation integrity, faithful representation, bias, COI, disclosure). |
Workflow
flowchart TD
A[research_scope<br/>scope brief] --> B[research_architect<br/>methodology blueprint]
B --> C[investigator Pass 1<br/>discover candidate sources]
C --> D[source_screener<br/>journal-ranking tiers]
D --> E[source_verifier<br/>validate → Source Quality Matrix]
E --> F[bibliography<br/>dedupe + format + citation map]
E --> G[investigator Pass 2<br/>extract evidence from validated sources]
G --> H[claim_verifier<br/>verify claims vs validated sources]
H --> I[synthesizer<br/>matrix, themes, conflicts, grading, gaps]
I --> J[critic<br/>stress-test synthesis]
J -- gaps --> C
J -- sound --> K[compiler<br/>write + format review<br/>APA 7.0 / target journal]
F --> K
K --> L[editor + ethics_reviewer<br/>editorial + integrity review]
L -- minor/major revision --> K
L -- accept --> M[Final literature review]
Two loops: (1) evidence loop — critic sends gaps back to investigator
(cap ~2–3); (2) writing loop — editor/ethics_reviewer send revisions back
to compiler until Accept (cap ~2–3), then deliver.
First move — set up full-text access (once)
The evidence loop reads actual articles, not abstracts. At the start, run the
food-fetch first-run setup (python3 scripts/food_fetch_setup.py status): if the
user hasn't set up access, surface the one-time highlighted request to provide their
EndNote .Data folder (or Zotero/Mendeley / a PDF folder) or institutional
access, warning that without non-open-access access the accuracy is substantially
limited; save the choice so it isn't re-asked. If they chose "open-access only",
remind briefly of that accuracy limit each run. Don't block — proceed at
open-access + abstract level and flag paywalled sources. Full rules: food-fetch/SKILL.md
and food-research/references/full-text-access.md.
Source discipline (non-negotiable)
- Investigation and claim-checking operate only on validated sources — those that passed
source_screener(ranking) andsource_verifier(validity). Retracted/unresolvable sources are excluded and logged. - Journal ranking favors Tier 1 (Q1/Q2 food-science & nutrition, Nature/Science/Cell families, Q1/Q2 in any other discipline); Tier 2 (Q3) only to fill gaps; Tier 4 avoided.
- Every claim carries a source and locator; inference is labelled as inference.
Formatting — resolve the target journal once
At the start, load journal-selector/SKILL.md (a shared procedure, not an
installed skill), which asks which journal the review
targets (they may answer 'generic' → APA 7.0). Ask once: record the
choice and reuse it in bibliography and compiler to format the review to that
journal's structure, limits, and reference style — don't ask again. Reuse a
journal already resolved by food-research/food-pipeline; re-resolve only if the
user asks to switch journals.
Principles
Every claim sourced; fact separated from interpretation; disagreement shown, not
averaged; uncertainty surfaced. Upstream evidence beats parametric knowledge —
mark missing evidence [EVIDENCE GAP], never fabricate.
References (load as needed)
references/reasoning-and-fallacies.md—synthesizer/critic: sound argument + fallacies.food-research/references/literature-sources.md— databases/APIs forinvestigator.food-research/references/full-text-access.md— reading the actual full text forinvestigator/source_verifier(open access → connected tool → user PDFs → library session, legitimate access only); mark anything unread rather than summarizing.food-research/references/source-quality-hierarchy.md— evidence grading forsource_verifier/synthesizer.food-research/references/reporting-guidelines.md— EQUATOR/PRISMA/CONSORT/STROBE.food-paper/references/apa7-quickref.md— APA 7.0 forbibliography/compiler(default style).food-paper/references/writing-style.md+food-paper/references/human-writing.md—compiler: academic style + remove AI tells, applied together — academic register as a human scientist, machine tells stripped, calibrated hedging and journal form kept.food-review/references/ethics-integrity-checklist.md— forethics_reviewer.food-paper/references/faithfulness-and-citation.md— grounding + four-gate citation check forbibliography,source_verifier,claim_verifier,compiler. Never invent sources/data; runscripts/verify_citations.py.food-paper/references/privacy-and-confidentiality.md— privacy scan before delivering the report (no local paths/secrets);scripts/privacy_scan.py.
Handoff
Standalone → deliver the final review. Called by food-research → return the
validated synthesis (or the finished review) to fold into the evidence brief.
Limitations
scripts/verify_citations.py (added in this override) only checks DOI existence and
retraction status via Crossref (gates 1/3 of the four-gate check); gate 2 (identity)
and gate 4 (semantic support) still need a human/agent read of the actual source.
示例提示词
帮我针对发酵食品抗氧化活性这个问题写一份来源验证的综述。
所属插件
安装该插件会一并获得同领域的 20 个 Skill / MCP。
同插件的其他科研 Skill
- 农业深度研究综述Deep research producing a source-validated literature review for an agricultural question, ranked by journal quartile. Reuses food-deep-research machinery. Use for an agronomy deep dive.
- 农业科学论文撰写系统Multi-subagent manuscript system for agricultural science with field-trial/soil/animal reporting standards. Reuses food-paper machinery. Use for an agronomy or soil-science manuscript.
- 农业研究全流程编排Orchestrates the full agricultural research-to-publication workflow: journal selection, research, writing, figures, peer review, revision. Use to manage an agronomy project end to end.
- 农业综述转可编辑PPTConverts an agricultural-science report or manuscript into a fully editable PowerPoint deck, reusing food-ppt machinery with agronomy framing. Use for slides from a field-trial report.
- 农业遥感作物制图Maps crop types from Sentinel-2 imagery with Random Forest, extracts NDVI phenology, estimates LAI, and predicts yield via Google Earth Engine. Use for field/county crop remote sensing.
- 农业文献证据综合Multi-source literature and evidence-synthesis workflow for agricultural science, ranked by journal quartile. Reuses food-research machinery. Use for an agronomy or soil-science evidence review.
- 农业论文多审稿人模拟Simulates an editorial peer-review panel for an agricultural manuscript, grounded in cited and field literature. Use for a pre-submission review or mock referee report in agriculture.
- 作物生长模拟Simulates crop growth with WOFOST/AquaCrop via PCSE, pulls weather from NASA POWER, and runs yield-gap analysis under climate scenarios. Use for agronomic intervention evidence.
- 田间试验混合模型分析Analyzes RCBD, split-plot, and multi-site field-trial data with mixed models in R (lme4) or Python (statsmodels), using correct error strata. Use for a crop or soil field-trial analysis.
- 学术文献全文合法获取Lawfully acquires full-text PDFs via open access, the user’s reference manager, or their logged-in library session; never bypasses paywalls. Use to fetch papers before research or review.
- 食品营养论文图表系统Builds publication-ready figures (bar/box, dose-response, PCA, heatmaps, forest plots) to a target journal’s spec, with a privacy scan before delivery. Use for a journal-ready figure.
- 食品科学论文撰写系统Multi-subagent manuscript system for food/nutrition science: frames questions, analyzes data, writes statistics, drafts, polishes, and reformats for a journal. Use to write or revise a paper.
- 食品研究全流程编排Orchestrates the whole food/nutrition research-to-publication workflow with quality gates: journal selection, research, writing, figures, review, revision. Use to manage a paper end to end.
- 食品研究报告转可编辑PPTConverts a food/agriculture report or manuscript into a fully editable PowerPoint deck with python-pptx: outline, grounded slide text, themed layout. Use to make slides from a paper.
- 科研基金申请书编排Orchestrates a food/agriculture funding proposal to a scheme’s format (headings, length limit, criteria), drafting or revising via the research/paper/review skills. Use for a grant application.
- 食品营养文献综合研究Runs a multi-source literature and evidence-synthesis workflow for food/nutrition science: search, two-phase screening, synthesis, evidence grading. Use for a deep review or systematic-review scope.
- 食品论文多审稿人模拟Simulates an editorial peer-review panel for a food/nutrition manuscript, grounded in cited and field literature first. Use for a pre-submission review or mock referee report.
- FAOSTAT食品系统数据分析Analyzes FAOSTAT food-balance, dietary-diversity, and trade/production data for cross-country food-systems indicators. Use for a country-comparison food-security dataset.
- 土壤数据空间分析Pulls and analyzes soil properties from SoilGrids (global) and SSURGO (US-only), computes SOC stock, and runs kriging interpolation. Use for a soil-property or soil-carbon map.
常见问题
通用深度文献综述研究能做什么?
General-purpose deep research producing a source-validated, fully written literature review via a 12-subagent team. Use for a thorough review or deep-dive needing verified sources。
如何安装通用深度文献综述研究?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「通用深度文献综述研究」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。
通用深度文献综述研究需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
通用深度文献综述研究经过官方审核吗?
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。