By sustainable-finance-partners
Agent Skills for the Phronesis energy-transition forecasting platform. Teaches an agent how to request decision forecasts across 12 verticals (energy, compute, healthcare, climate, regulatory, supply-chain, space, robotics, AI/AGI, physics/materials, longevity, quantum) and cross-vertical intersections, how to read the structured Decision API output, and how to verify forecasts via Trust Receipts and the Calibration Leaderboard.
Request, read, and verify cross-vertical forecasts from the Phronesis platform — decisions that live at the intersection of two verticals (e.g. AI/AGI x Regulatory, Energy x Compute, Climate x Supply-Chain). Use this skill when a decision depends on how two domains interact rather than on either alone.
Request, read, and verify physics and materials-discovery forecasts from the Phronesis platform — AI-driven materials discovery, physics-experimentation cadence, battery-chemistry breakthroughs, superconductor discovery, and advanced-manufacturing substrate. Use this skill when an agent needs a structured, uncertainty-banded, audit-verifiable forecast about scientific discovery rather than a free-text guess.
Request, read, and verify longevity and human-health forecasts from the Phronesis platform — lifespan-extension trajectories, biomarker-clock validation, geroscience-trial outcomes, longevity-therapy pipelines, and cellular-rejuvenation substrate. Operates on population-aggregate data only. Use this skill when an agent needs a structured, uncertainty-banded, audit-verifiable forecast about longevity science.
Request, read, and verify quantum-computing forecasts from the Phronesis platform — quantum-supremacy milestones, qubit-scaling trajectories, post-quantum-crypto migration, quantum-chemistry simulation, and quantum-vendor canonical attestation. Enforces a US-and-allied vendor-citation governance rule. Use this skill when an agent needs a structured, uncertainty-banded, audit-verifiable forecast about quantum computing.
Request, read, and verify energy-transition forecasts from the Phronesis platform — grid resilience, demand-load, capacity planning, renewable deployment, and carbon intensity. Use this skill when an agent needs a structured, uncertainty-banded, audit-verifiable forecast about energy systems rather than a free-text guess.
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.
Agent Skills for Phronesis — an energy-transition AI forecasting platform built by Sustainable Finance Partners.
Phronesis is a future-state intelligence engine for the energy transition and its adjacent frontier domains. Specialist AI agents ingest research, energy and climate data, policy, and customer context, then produce decision forecasts that overlay emerging technology trajectories on current business models. Phronesis sells primarily via API/MCP to AI agents, and secondarily via a thin SaaS UI to human capital allocators.
All twelve verticals are live on production — each ring-active and governed by a
per-vertical Themis rule cluster — and the 12-vertical-deep substrate is published as
a verifiable manifest at GET /v1/substrate/completeness.
Every Phronesis forecast is delivered through a structured Decision API output:
a point forecast, a p10 / p50 / p90 uncertainty band, explicit assumptions, cited
sources, and a per-call cost attestation. Forecasts are individually verifiable
through signed Trust Receipts, and per-vertical accuracy is published openly on
the Calibration Leaderboard.
Phronesis exposes co-equal MCP and REST transports — neither is the "real" API; both pass through the same governance boundary. The production base URL is:
https://phronesis-jrstinehour.replit.app
This repository contains Claude Code Agent Skills that teach an agent how to actually use Phronesis: which archetypes each vertical supports, how to call the forecast endpoint, how to read the structured Decision API output, and how to verify a forecast after the fact. There is one skill per vertical, plus a cross-vertical skill for forecasting at the intersection of two verticals.
Each skill is a SKILL.md file with YAML frontmatter (name, description) and a
markdown instruction body, located at
plugins/phronesis/skills/<skill-name>/SKILL.md.
| Skill | Directory | Scope |
|---|---|---|
phronesis-energy-forecasting | v1_energy | Energy forecasting — grid resilience, demand-load, capacity planning, renewable deployment |
phronesis-compute-forecasting | v2_compute | Compute & AI-infrastructure capacity forecasting — chips, datacenters, training/inference demand |
phronesis-healthcare-forecasting | v3_hygieia | Healthcare forecasting — drug pipeline, trials, policy; HIPAA-Safe-Harbor / population-aggregate only |
phronesis-climate-forecasting | v4_climate | Climate physical-risk forecasting for insurance and reinsurance |
phronesis-regulatory-forecasting | v5_regulatory | Cross-cutting regulatory-compliance and policy-shift forecasting |
phronesis-supply-chain-forecasting | v6_supply_chain | Supply-chain forecasting — critical minerals, freight, agriculture |
phronesis-space-forecasting | v7_space | Space & space-economy forecasting — launch cadence, constellations, monitoring |
phronesis-robotics-forecasting | v8_robotics | Robotics safety & deployment forecasting |
phronesis-ai-agi-forecasting | v9_ai_agi | AI/AGI capability & safety forecasting |
phronesis-physics-materials-forecasting | v10_physics_materials | Physics & materials-discovery forecasting |
phronesis-longevity-forecasting | v11_longevity | Longevity & human-health forecasting |
phronesis-quantum-forecasting | v12_quantum | Quantum-computing forecasting (US-and-allied vendor citation governance) |
phronesis-cross-product-forecasting | cross_product | Cross-vertical forecasting at V#X x V#Y intersections |
Add this repository as a plugin marketplace, then install the phronesis plugin:
/plugin marketplace add sustainable-finance-partners/skills
/plugin install phronesis@phronesis-skills
npx skills add sustainable-finance-partners/skills
These skills are companions to the live Phronesis service. The agent-discoverable entry point is:
https://phronesis-jrstinehour.replit.appGET /.well-known/agent-discovery.jsonGET /v1/catalogGET /v1/pricingPOST /v1/decision/forecastGET /v1/substrate/completenessGET /v1/trust/receipt/{forecast_id}GET /calibration/leaderboardAll /.well-known/*.json surfaces and the catalog/pricing/leaderboard endpoints are
public-by-design. The forecast endpoint requires a JWT.
Phronesis is built so an agent can trust a forecast on evidence, not brand claims:
npx claudepluginhub sustainable-finance-partners/skills --plugin phronesisUI/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.