By igor-holt
Persistent project state + unified skill registry for stateless LLMs (Grok, OpenClaw, Claude Code, Cursor and compatible agents). Eliminates amnesia between turns so long-running autonomous agent work becomes reliable and memoryful. Remembers goals, decisions, open tasks, artifacts, Smithery namespaces/connections across sessions. Trigger on 'remember the project state', 'load persistent memory', 'continue from where we left off'. Install: clawhub install grok-persistent-state. Foundational component of the Genesis Conductor OpenClaw skills trio by @invariantx for reliable agent orchestration.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
@invariantx (Igor Holt) — https://x.com/invariantx
Production-grade agent infrastructure extracted from previous Genesis Conductor sessions (soul capsules, clawbot-grok persistent state patterns, A2A coordination, thermodynamic verification mindset).
These three skills form a complete, designed-to-compose professional stack for reliable, memoryful, securely orchestrated autonomous agents on the OpenClaw + Smithery + MCP substrate.
Follow @invariantx on X for all updates, deeper threads, and the full series.
These three skills form a complete professional stack:
Persistent project state + unified skill registry for stateless LLMs (Grok, OpenClaw, Claude Code, etc.).
Solves the fundamental "amnesia" problem. Agents can now remember goals, decisions, open tasks, artifacts, and active Smithery namespaces/connections across every turn.
Install: clawhub install grok-persistent-state
Turn any MCP server into first-class, versioned OpenClaw skills.
Extract the most valuable tools/resources from an MCP server (discovered via Smithery or otherwise) and publish them as permanent, triggerable ClawHub skills that any agent can install.
Install: clawhub install mcp-openclaw-bridge
Discover, securely connect, scope tokens, and orchestrate 100K+ tools from Smithery inside OpenClaw agents.
Canonical workflows for namespaces, long-lived MCP connections, advanced token policies with rpcReqMatch restrictions, handling auth_required flows, and piped JSONL output — all explicitly paired with the persistent state and MCP bridge skills above.
Install: clawhub install smithery-mcp-orchestrator
These skills power live autonomous agent systems, including:
- @invariantx ↔ DiamondNodeBot on Telegram — OpenClaw (with persistent state, MCP bridging, and Smithery orchestration) connected through the InvariantX identity layer to the DiamondNodeBot Telegram channel for reliable, attested, multi-channel agent operation.
This deployment demonstrates the full trio in production: durable memory across turns, safe exposure of MCP tools, and professional Smithery-driven discovery + token scoping for Telegram-based agent interfaces.
LidLift Pareto Lifecycle: MCP Tool Dissonance Scoring Dashboard
https://clawdash.genesisconductor.io (secure canonical production)
Status: Custom domain DNS is pending configuration.
The dashboard is currently accessible via the GitHub Pages mirror: https://igor-holt.github.io/openclaw-skills/
See EXECUTION_CHECKLIST.md (Phase 2) for exact DNS + GitHub Pages + HTTPS steps, including gcloud commands.
Once live, the secure dashboard will be the canonical surface for the OpenClaw skills stack (Genesis Conductor + @invariantx + DiamondNode).
- Use smithery-mcp-orchestrator to find and connect to new services safely. - Use grok-persistent-state to remember active namespaces, connection IDs, and scoped tokens. - Use mcp-openclaw-bridge to promote the best discovered capabilities into permanent, published skills for the whole community.
Together they give agents professional-grade discovery + memory + security + distribution on the Smithery + OpenClaw + MCP stack.
These skills prioritize: - Correctness & verifiability (thermodynamic/topological mindset from Genesis Conductor) - Clear trigger surfaces (agents know exactly when to activate them) - Explicit safety & privacy boundaries (especially around credentials and token scoping) - Real production patterns (not toy examples)
They are designed to compose with the dominant tactical skills in the ClawHub ecosystem (browser automation, code review, tool discovery, etc.).
All skills follow strict semantic versioning + detailed changelogs on every publish.
MIT-0 / open contribution friendly.
@invariantx (Igor Holt)
Creator of Genesis Conductor. Shipping the professional OpenClaw skills trio for production autonomous agents (thermodynamic verification + topological orchestration applied to real infrastructure).
- X: https://x.com/invariantx (primary updates + threads) - GitHub: https://github.com/igor-holt - Main site: https://genesisconductor.io
All work in this repository and the associated ClawHub skills is authored and maintained by @invariantx. Follow on X for ongoing Genesis Conductor agent infrastructure releases, DiamondNode integrations, and production patterns.
Part of the broader effort to raise the reliability and architectural floor of the open agent ecosystem.
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 claimnpx claudepluginhub igor-holt/openclaw-skills --plugin grok-persistent-stateDiscover, securely connect, scope tokens, and orchestrate 100K+ MCP tools from Smithery inside OpenClaw, Grok and compatible agents. Provides namespace discipline, long-lived MCP connections, advanced token policies with rpcReqMatch restrictions, auth_required flow handling, and piped JSONL output. Explicitly designed to pair with grok-persistent-state (memory of namespaces, connections, scoped tokens) and mcp-openclaw-bridge (promote valuable discoveries into permanent published skills). Install: clawhub install smithery-mcp-orchestrator. The secure discovery and orchestration layer of the professional Genesis Conductor OpenClaw stack by @invariantx.
Bridge Model Context Protocol (MCP) servers into first-class, versioned, discoverable OpenClaw / ClawHub skills. Extract valuable tools, resources and prompts from any MCP server (Smithery, local or remote) and publish them as permanent, triggerable skills with explicit safety boundaries, privacy declarations and auditable thin adapters. Ideal for turning production MCP capabilities into community-installable ClawHub skills. Install: clawhub install mcp-openclaw-bridge. Perfectly composes with the other two skills in the Igor Holt OpenClaw bundle.
Production MCP server and analysis engine for tool-dissonance control. Exposes discover_vendor_tools and rank_tools over remote MCP transport. Live at https://api.optimizationinversion.com/mcp. Installable component for Genesis Conductor agents requiring pre-execution safety scoring and alternative ranking. Pairs with persistent-state skills for long-horizon guardrail memory and OpenClaw bridges for skill publishing.
UI/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.