一键在 Manus 中运行任何 Skill

academic-paper-pipeline

星标0

分支0

更新时间2026年5月15日 05:16

Orchestrates academic paper production from topic/proposal to manuscript, analysis, figures, submission files, and defense slides. Use for research-proposal planning, paper architecture, section-by-section drafting, evidence-gap tracking, statistical handoff, figure handoff, DOCX/PDF/LaTeX/PPTX delivery, revision workflows, and coordinating multiple research-writing skills without losing the paper ledger.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

Vambrocop

Vambrocop/EmpiriForge

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Academic Paper Pipeline

Use this skill when the user wants to move an academic paper through the whole production line: topic, proposal, structure, draft, evidence, analysis, figures, submission package, and presentation.

Core Principle

Keep the paper moving through three nodes:

Topic: question, contribution, feasibility, literature gap.
Manuscript: structure, evidence, methods, results, interpretation.
Delivery: Word/PDF/LaTeX/PPTX, figures, tables, appendices, response files.

Do not polish prose before the research ledger is coherent. Do not generate delivery files before evidence, figures, tables, and claims are checked.

Intake

Identify:

current stage: proposal, outline, drafting, analysis, figures, submission, revision, or defense;
discipline and target journal if known;
paper type: empirical paper, systematic review, meta-analysis, clinical paper, omics paper, methods paper, thesis, or proposal;
language: Chinese, English, or bilingual;
available files: draft, notes, data, code, figures, tables, references, journal instructions;
target artifact: proposal, manuscript outline, full draft, revision plan, DOCX, PDF, LaTeX, PPTX, or checklist.

Load:

references/paper-skill-stack.md for external and internal skill routing.
references/agricultural-systems-scope-fit.md when an agricultural, digital-agriculture, AI, remote-sensing, LCA, farm-systems, or agronomic paper needs a systems-journal scope-fit audit.
templates/paper-production-ledger.md to track the paper from idea to delivery.
templates/agricultural-systems-scope-fit-audit.md when judging whether a manuscript has enough system boundary, interaction, trade-off, and decision relevance for an agricultural-systems journal.
templates/submission-delivery-checklist.md before final submission or defense.

Route internally:

empirical design or reproducibility: empirical-research-forge;
identification critique: econ-identification-skeptic;
causal ML: causal-ml-estimator-selector;
Stata/code package: stata-econometrics-runner;
publication figures: publication-figure-forge;
systematic review/meta-analysis: use EvidenceForge.

Workflow

Build or update the paper production ledger.
Name the target artifact and deadline.
Check whether the research question and contribution are stable.
Create the manuscript architecture before drafting.
Track every claim to evidence, table, figure, citation, or planned analysis.
Route data/statistics/figures to the right skill or tool.
Draft section by section, keeping [evidence needed] markers visible.
Run a pre-submission audit: claims, methods, results, figures, references, reproducibility, formatting.
Create delivery files only after content gates pass.
For defense, convert the paper ledger into a slide narrative.

Output Modes

Pipeline Plan

Stage:
Target artifact:
Current blocker:
Next three actions:
Skill/tool route:
Expected output:

Paper Ledger

Use templates/paper-production-ledger.md.

Delivery Checklist

Use templates/submission-delivery-checklist.md.

Skill Stack Recommendation

Task:
Primary skill:
Supporting skill:
Why:
What to provide:
What not to ask yet:

Agricultural Systems Scope-Fit Audit

Use templates/agricultural-systems-scope-fit-audit.md when the paper risks being a tool, model, single-trial, or single-outcome paper rather than a systems paper.

Guardrails

Do not invent citations, results, methods, or journal requirements.
Do not let a writing skill hide missing evidence.
Do not treat grammar polish as scientific revision.
Do not generate submission files before figures/tables/citations are stable.
Do not route a meta-analysis to an empirical-paper workflow; use EvidenceForge instead.
Do not route identification critique to a generic writing workflow.
Do not overinstall skills; choose the few needed for the current stage.
Do not call an agricultural manuscript systems-oriented unless it makes the system boundary, interactions, trade-offs, scale, and decision relevance visible.

同仓库更多 Skills

同仓库

causal-ml-estimator-selector

Vambrocop/EmpiriForge

Selects, audits, and explains causal machine learning workflows for heterogeneous treatment effects and graph-based causal ML. Use for CATE, ITE, uplift modeling, S/T/X/R/DR learners, causal forests, matching, propensity scores, IV/DRIV, CEVAE/DragonNet, causal GNNs, graph neural networks with causal claims, therapeutic perturbation prediction, optimal intervention design, causal disentangled graphs, LLM-enhanced GNN mechanism identification, fault-diagnosis causal subgraphs, treatment targeting, policy personalization, Python CausalML/EconML-style projects, validation of causal-ML claims, and boundary checks between treatment-effect estimation and causal-invariant/stable prediction.

2026-05-190

empirical-research-forge

Vambrocop/EmpiriForge

Orchestrates bilingual empirical research workflows from research question to reproducible paper package. Use when writing, reviewing, replicating, or packaging empirical economics/social-science papers; designing DID, IV, RDD, event-study, panel, synthetic-control, matching, or causal ML workflows; auditing tables and identification claims; checking method-source alignment; or turning research practice into reusable agent skills.

2026-05-190

prediction-modeling-forge

Vambrocop/EmpiriForge

Builds and audits tabular-data prediction-model workflows for research papers. Use for clinical, environmental, biological, social-science, environmental-economics, or economics prediction models; tidymodels, random forest, XGBoost, logistic-regression baselines, partial least squares regression, PLS VIP, NDVI or environmental indicator models, enterprise carbon-emission forecasting, stable time-series prediction, causal-invariant prediction, distribution shift, cross-region/cross-industry/cross-policy validation, train/test splits, cross-validation, hyperparameter tuning, ROC/AUC, calibration, decision-curve analysis, bootstrap uncertainty, confidence intervals, prediction bands, variable importance, leakage checks, and manuscript-ready methods/results language.

2026-05-040

publication-figure-forge

Vambrocop/EmpiriForge

Creates and audits publication-ready scientific figures in R. Use for ggplot2, corrplot, journal figure standards, TIFF/EPS/PDF export, COSTAR prompts, scatterplots, boxplots, bar charts, line plots, heatmaps, correlation matrices, correlograms, corrplot significance plots, volcano plots, Kaplan-Meier curves, forest plots, multi-panel figures, clinical figures, omics figures, ecology/environment figures, and reviewer-proof visualization checks.

2026-05-040

econ-identification-skeptic

Vambrocop/EmpiriForge

Acts as a skeptical applied-economics identification reviewer. Use when evaluating DID, IV, RDD, event-study, panel fixed effects, synthetic control, matching, or causal ML designs; auditing robustness checks; preparing referee-style critiques; assigning causal-credibility verdicts; or strengthening the identification section of an empirical economics paper.

2026-04-300

stata-econometrics-runner

Vambrocop/EmpiriForge

Work with Stata-based empirical economics projects. Use when reading, editing, running, or auditing Stata .do/.ado files, .log files, Stata replication packages, regression-table workflows, or Stata-to-R/Python conversion in applied economics. Can execute Stata when a local Stata executable is available; otherwise performs code/log/package review.

2026-04-280