Customer-facing GroundX agent harness for API use, schema-first extraction, on-prem deployment, architecture, and approved GTM guidance.
Customer-facing GroundX API reference for document ingest, search, RAG, source attribution, document understanding, buckets, groups, workflows, account health, API keys, SDK usage, and REST fallback. Try the hosted GroundX API MCP connector before direct REST. If tools are not visible, instruct the user to connect the GroundX API connector and retry tool discovery; use REST only when connector attachment fails or a needed tool is missing. REST fallback uses the `X-API-Key` header and keeps raw keys out of tool arguments, browser code, logs, transcripts, examples, and generated files.
Customer-facing source of truth for GroundX architecture facts: pipeline, components, trust model, data flow, search, extraction architecture, observability, residency, and deployment-invariant system behavior.
Use this skill when an agent needs to extract structured data from a PDF or other document using GroundX. Triggers include drafting or iterating an extraction YAML schema, compiling workflow JSON, running an extraction, comparing output to ground truth, debugging missing or wrong fields, and planning a serious extraction pilot. Platform API operations delegate to `groundx-api`.
Deployment operator's reference for GroundX: how to deploy, configure, scale, and run GroundX on Kubernetes, including AWS EKS, Azure AKS, generic Kubernetes, OpenShift, private cloud, minikube, and air-gapped on-prem deployments.
Customer-facing Valantor company and category messaging reference: Visual Intelligence, AI plus humans accountability, company value props, category framing, and brand hierarchy.
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.
GroundX Agent Harness gives Claude, Codex, and other coding agents GroundX-specific working knowledge. Install it when you want an agent to understand how to use GroundX well enough to help with:
The harness gives the agent instructions and reference material. To let the agent make
authenticated GroundX API calls, also connect the hosted GroundX API MCP app at
https://api.groundx.ai/mcp.
Choose the client you use.
From inside Claude Code, add the GroundX marketplace and install the plugin:
/plugin marketplace add GroundX-Studio/groundx-agent-harness
/plugin install groundx-agent-harness@groundx-agent-harness
Then start a new Claude Code session.
CLI equivalent:
claude plugin marketplace add GroundX-Studio/groundx-agent-harness
claude plugin install groundx-agent-harness@groundx-agent-harness
If you use Claude Code inside VS Code, run the same Claude plugin commands in the Claude Code session:
/plugin marketplace add GroundX-Studio/groundx-agent-harness
/plugin install groundx-agent-harness@groundx-agent-harness
Restart the Claude Code session inside VS Code after installing.
In Codex:
https://github.com/GroundX-Studio/groundx-agent-harness
main.The plugin gives Codex the GroundX agent instructions. The hosted MCP app gives Codex authenticated GroundX API tools.
Open Settings -> Apps in Codex.
Click Advanced.
Click New App.
Enter:
Name: GroundX Studio
MCP Server URL: https://api.groundx.ai/mcp
Authentication: OAuth
Leave advanced OAuth fields empty unless Codex asks you to review discovered settings. Codex should discover the OAuth metadata from the MCP server.
Accept the custom MCP server warning.
Click Create.
Complete the GroundX authorization screen with a GroundX API key.
Return to Settings -> Apps, open GroundX Studio, and click Refresh if the action list is empty.
Expected result: the app information shows URL https://api.groundx.ai/mcp,
authorization supported/used as OAuth, and actions such as bucket_list,
document_ingestlocal, search_content, or groundx_account_context.
For clients that support remote MCP or hosted connectors but not plugins, connect the hosted GroundX API MCP endpoint:
https://api.groundx.ai/mcp
Use the deployment-managed OAuth/connector flow. Do not put API keys, refresh tokens, client secrets, or user auth state in prompts or checked-in files.
Use non-secret checks first:
List the GroundX Agent Harness skills you have available.
Use the GroundX Agent Harness references to explain the safest document ingest -> status polling -> search flow. Do not ask me for an API key.
If the GroundX API connector is connected:
Show my GroundX account context using the connector. Do not include raw credentials.
You can also run the local helper from a checkout of this repository:
node scripts/doctor.mjs
Do not commit customer documents, answer keys, private pilot notes, comparison outputs, credentials, or local run artifacts to this repository.
npx claudepluginhub groundx-studio/groundx-agent-harness --plugin groundx-agent-harnessUI/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.