Thin orchestrator for geopolitical forecasting simulations. Scaffolds, runs, bundles, and grades simulations from multiple decoupled upstream templates (lean LLM-council and snowglobe-style actor-simulation variants).
Create a new geopolitical-forecasting simulation workspace by cloning one of the registered upstream templates. Use when the user wants to "start a new geopol simulation", "set up a forecast", "scaffold a forecasting run", or asks which simulator template to use. Interactively presents the template registry with cost/depth tradeoffs, clones the chosen template into a new workspace, wires the .env file, seeds a scenario.md, and drops a .template-id sentinel.
One-time setup of a persistent archive for all simulation runs across workspaces and templates. Use when the user wants to "set up a runs archive", "configure where runs are stored", or asks where their forecasts are kept. Creates the runstore directory, persists the path via the plugin-data-storage convention so it survives plugin updates, and registers existing workspaces.
Edit the simulation participants in a workspace — actor persona briefs (snowglobe-style templates) or council-member panel models (council-style templates). Use when the user wants to "update actors", "edit personas", "swap a model in the panel", "add an actor", or "change the council members". Sentinel-aware: dispatches based on whether the workspace template supports actor editing.
Pull the latest changes from each registered upstream simulation template. Use when the user says "update templates", "pull template updates", "refresh simulators", or wants to check whether the upstream Geopol-Forecast-Council / Geopol-Forecaster repos have new commits. Reports what changed per template.
Take a completed simulation run and produce a shareable artifact — a blog post, a PDF, or both. Use when the user wants to "publish this forecast", "bundle a run", "make a blog post from this simulation", "generate a PDF report", or "share this forecast". Strips internal-only fields, formats horizons as concrete dates, and pipes through existing publishing flows where available.
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.
A thin orchestrator for running geopolitical-forecasting simulations from multiple decoupled upstream templates. The plugin doesn't ship simulator code itself — it scaffolds workspaces from the live upstream repos, dispatches runs by sentinel file, archives results, and grades past predictions for accuracy.
Two are registered out of the box, with very different cost / depth tradeoffs:
| Template | Shape | Cost | Best for |
|---|---|---|---|
| Geopol-Forecast-Council | Lean 5-LLM panel, no actor sim | Cheap (a few model calls per run) | Short-horizon (24h / 1w / 1m) forecasts on fast-moving situations |
| Geopol-Forecaster | Snowglobe-style: ~40 actors over 4 timesteps + 6-lens council | Expensive (hundreds of calls per run) | Longer horizons, counterfactuals, when individual-actor dynamics matter |
New templates can be added with a single entry in templates/registry.json — no skill rewrites required.
scaffold-simulation — interactive template picker, clones chosen upstream into a new workspace, wires .env, drops a .template-id sentinel.run-simulation — sentinel-dispatched run + resume.update-actors — for snowglobe templates, edit persona briefs; for council templates, swap panel models.update-templates — git pull each registered template clone, report what changed.setup-runstore — one-time setup of a persistent runs archive (~/geopol-runs/ by default) so all runs across templates land in one queryable place.bundle-run — turn a completed run into a blog post, PDF, or both.grade-run — backward accuracy assessment with per-prediction grading and panel calibration stats. Seed of the self-improving loop.claude plugins marketplace add danielrosehill/Claude-Code-Plugins
claude plugins install geopol-sim@danielrosehill
Plugin-with-decoupled-templates: the plugin is a thin orchestrator over template repos that live independently. Push template improvements upstream without bumping the plugin; push plugin improvements without touching templates. See the pattern note for the full writeup.
MIT
npx claudepluginhub danielrosehill/claude-code-plugins --plugin geopol-simUI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
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.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
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.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Claude Code plugin: ideation and planning workflow — capture, evaluate, rank, simulate, and plan ideas, with ideation/single-idea-eval/multi-idea-ranking/feature-ideas/simulation/idea-capture variants.
First-pass data analysis toolkit: correlations, PII flagging, anomalies, hypothesis tests, data dictionaries, and trend analysis on a dataset in a folder.
Claude Code plugin for generating personal user manuals and private documentation for codebases. Creates personalized, private reference guides with PDF output support.
Research, filter, compare, and evaluate AI models on OpenRouter — discover models by capability (tool use, vision, audio), get cost/context-aware recommendations, run head-to-head comparisons, and conduct deep research that goes beyond the OpenRouter catalog.
Claude Code plugin for writing assistance, proofreading, style editing, and text transformation workflows.