By ALLBLUEUK
Agent-assisted structural modeling and dynamic simulation pipeline for economics graduate research (DSGE, CGE, heterogeneous-agent, dynamic programming). Includes academic-paper composition skills that produce publication-grade LaTeX manuscripts, not pipeline reports.
Show what the strucmod plugin can do and how to use it.
Start a brand-new structural-modeling research project (creates academic project layout + invites you to describe the model).
代码语言惯例评议子 agent。审查 Dynare / Julia / MATLAB / GAMS / Python 实现的语言惯例、可读性、错误处理、路径规范、日志规范,以及与 spec 是否对齐。求解前应通过本评议。
数学一致性评议子 agent。审查方程系统的维度匹配、变量计数、单位一致性、FOC 推导、状态变量分类,以及方程数 = 未知数的硬约束。任何方程落入代码之前必须过这一关。
经济逻辑评议子 agent。审查 spec.md 中的研究问题、机制设定、变量分类、方程系统是否经济上自洽、与文献对齐、与研究问题相称。任何模型代码动手之前都要过这一关。
数值方法评议子 agent。审查求解器选择、网格、初值、收敛准则、稳定性、Blanchard-Kahn 条件、特征值、迭代次数等数值层面的问题。
学术论文质量评议子 agent。审查由 write-* skill 产出的论文 section 与由 render-paper 编出的最终 PDF。守住 academic-writing-style 规则的所有禁忌与必备项。**不**评议经济机制或数值(那是 model-reviewer / math-reviewer / numerics-reviewer / verifier 的事)。
组装校准表 / 矩比对表 / IRF 表 / 反事实表为 CSV 与 LaTeX。当用户说"做表"、"build tables"、"出 LaTeX 表"、"摘要表"时调用。
从数据/文献/矩条件组装 calibration.csv,记录每个参数来源。当用户说"校准参数"、"calibrate"、"匹配矩"、"match moments"、"对齐数据"、"找出 beta / alpha 取多少"时调用。本技能是任何 solve-* 系列的强制前置。
git 提交:检查 .gitignore、生成提交信息、避免提交受保护文件。当用户说"提交"、"commit"、"push"、"git"时调用。
跑反事实 / 过渡路径 / 政策实验,对比 baseline。当用户说"反事实"、"counterfactual"、"政策实验"、"transition path"、"如果……会怎样"时调用。
反方拷问:质疑模型机制、识别策略、数值结果。当用户说"挑刺"、"反驳一下"、"devils advocate"、"audit"时调用。
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An AI-agent pipeline that turns one-line research questions into publication-grade economics papers.
DSGE, CGE, heterogeneous-agent, dynamic-programming — model spec → calibration → solve → simulate → write a real academic paper (introduction, model, calibration, solution, results, robustness, conclusion, references) → compile to PDF.
Output of UIBE 2025 Graduate Education Reform Project · AI Multi-Tool Coordinated Empowerment of Graduate Structural Modeling and Dynamic Simulation Research and Practice · 贾宁远.
setup-dsge, setup-cge-gtap, setup-ha-bewley, calibrate-from-moments, solve-perturbation, solve-vfi, simulate-irf, counterfactual-run, plus 8 paper-composition skills (paper-structure, write-introduction, write-model-section, write-calibration-section, write-solution-section, write-results-section, write-conclusion, manage-bibliography, render-paper).model-reviewer, math-reviewer, numerics-reviewer, code-reviewer, pedagogy-reviewer, paper-reviewer, verifier.orchestrator-protocol, plan-first-modeling, numerical-validation-protocol, replication-protocol, modeling-coding-conventions, academic-writing-style (zero implementation leak, formal voice, citation discipline).main.tex + 7 section skeletons + appendix + a starter references.bib pre-filled with canonical citations.What it produces: a self-contained research project (paper/, code/, data/, results/, slides/, references/) and a publication-grade paper/paper.pdf — 8–15 pages with full academic structure, zero implementation leakage.
Inside Claude Code:
/plugin marketplace add https://github.com/ALLBLUEUK/structural-modeling-for-economists
/plugin install strucmod
That's it. Every Claude Code session in any directory knows the pipeline. No per-project setup.
.claude/cd ~/my-research-project
git clone https://github.com/ALLBLUEUK/structural-modeling-for-economists.git \
.claude/plugins/strucmod
Restart Claude Code in the project; the plugin auto-loads.
git clone https://github.com/ALLBLUEUK/structural-modeling-for-economists.git \
~/.claude/plugins/strucmod
Codex natively reads AGENTS.md (agents.md spec). The plugin ships an AGENTS.md template that tells Codex where to find skills and rules.
# 1) Install plugin once (global recommended):
git clone https://github.com/ALLBLUEUK/structural-modeling-for-economists.git \
~/.claude/plugins/strucmod
# 2) In each research project, drop AGENTS.md into the project root:
cd ~/my-research-project
cp ~/.claude/plugins/strucmod/templates/adapters/AGENTS.md ./AGENTS.md
# 3) Start Codex:
codex
Codex automatically reads AGENTS.md and follows the pipeline's procedures.
Cursor uses .cursor/rules/*.mdc for project rules.
cd ~/my-research-project
git clone https://github.com/ALLBLUEUK/structural-modeling-for-economists.git \
~/.claude/plugins/strucmod
mkdir -p .cursor/rules
cp ~/.claude/plugins/strucmod/templates/adapters/cursor/rules/strucmod.mdc \
.cursor/rules/strucmod.mdc
cp ~/.claude/plugins/strucmod/templates/adapters/AGENTS.md ./AGENTS.md
Open the project in Cursor; the rule auto-loads.
cd ~/my-research-project
git clone https://github.com/ALLBLUEUK/structural-modeling-for-economists.git \
.claude/plugins/strucmod
cp .claude/plugins/strucmod/templates/adapters/.aider.conf.yml ./.aider.conf.yml
cp .claude/plugins/strucmod/templates/adapters/AGENTS.md ./AGENTS.md
aider
cd ~/my-research-project
git clone https://github.com/ALLBLUEUK/structural-modeling-for-economists.git \
~/.claude/plugins/strucmod
cp ~/.claude/plugins/strucmod/templates/adapters/.windsurfrules ./.windsurfrules
cp ~/.claude/plugins/strucmod/templates/adapters/AGENTS.md ./AGENTS.md
npx claudepluginhub allblueuk/structural-modeling-for-economists --plugin strucmod经管类本科建模与写作 AI 智能体辅助工作流:6 阶段课程项目 + 提示词 + 证据归档
Auto-opening HTML dashboard that tracks context window usage across Claude Code sessions. Zero token cost.
Detect AI-like phrasing, templated rhetoric, and economics-specific writing problems in academic manuscripts.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.