Prism-Shadow

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5)…

Create a reusable skill from staged training examples and matching answers.

Northstar Health Plan payer-operations task execution — prior authorization, appeals, payment integrity, peer-to-peer, and finance margin analysis against the shared payer environment. Produces structured JSON determinations matching an answer template.

Process Northstar Health Plan payer-operations review tasks (prior auth, appeals, payment integrity, P2P, margin queues) against the shared Northstar environment API, producing structured JSON determinations with full basis audit trails.

Reusable operating rules for reconciling and certifying data-quality collections against the Asteria Fleet Data Quality Hub REST API.

Complete a Cedar Ridge Intake Coordination Portal intake/audit task. Query the live portal for a roster, batch, or program; reconcile the records against the task's answer_template.json; and return one JSON object built only from the template's controlled…

Audit a Cedar Ridge Intake Coordination Portal batch (patients, referrals, transfers, or program candidates) and return a single JSON object that conforms to a staged answer_template.json. Use for any task pointing at the Cedar Ridge portal that demands…

Audit a batch of Cedar Ridge Intake Coordination Portal records — new-patient access verification, referral readiness, dialysis transfer review, or a chronic-care enrollment panel — and produce one JSON object that conforms to the task's answer_template.json.…

Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing…

Use whenever the user wants to build an agent application — their own program with an embedded agent, such as an AI app, an agentic app or a RAG app. This is writing application code on the Penguin Harness SDK, not configuring an Agent State inside…

Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server.

Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.

Use when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page or the docs site to click through it, screenshot it, or reproduce a report. Covers the four dev entry points and their ports, which data…

Deploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents.

Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.

Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.

Guidance for using the AgentHub Python SDK (`agenthub-python`). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention AgentHub, request `agenthub-python`, or already import it.

Guidance for using the AgentHub TypeScript SDK (`@prismshadow/agenthub`). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention AgentHub, request `@prismshadow/agenthub`, or already import it.

Fixed workflow for developing AgentHub itself — adding or updating model support. Use when asked to support a new model or protocol version in this repository, sync llmsdk_docs, or implement a provider client. Covers doc syncing, live API capture, paired…

Run the Verify LLM Vendors benchmark using the PyPI-installed `agent-vendor-verifier` CLI; before each test run validate that config.yaml is complete, ask the user for any missing required config values, then read config and confirm with the user the list of…