Browse the metahub catalog

Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.

Zero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.

Measure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.

Structured logging, distributed tracing, and alerting for AI systems and traditional services. You can't fix what you can't see.

Designs and coordinates multi-agent pipelines where specialized agents collaborate to complete complex tasks. Includes communication protocols, failure handling, and state management.

Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.

Test real system boundaries, not mocks of mocks. Integration tests verify that components work together, not that they work in isolation.

Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.

Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.

Detects and mitigates LLM hallucinations in production pipelines. Validates AI-generated facts, code, and decisions before they reach end users or downstream systems.

Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.

Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.

Graceful degradation and meaningful error messages. Errors are first-class citizens, not afterthoughts. Every error path is designed, not discovered.

Document decisions, not just implementations. ADRs for architectural choices, inline docs for non-obvious code, and runbooks for operational knowledge.

Systematic root cause analysis for production and development bugs. Hypothesis-driven debugging — never guess-and-check.

Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.

Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.

Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.

Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.

Build a pitch deck for a crypto project. Use when the user says "pitch deck", "demo day", "investor presentation", "grant application slides", "accelerator application", "help me pitch", or needs slides for a hackathon final.

Find and validate what to build in crypto. Use when the user asks "what should I build", "validate this idea", "is this worth building", "find me a startup idea", "crypto idea", or wants blunt feedback on a project concept before writing code.

Prepare a winning hackathon submission. Use when the user says "hackathon submission", "submit to hackathon", "demo script", "demo video", "which track should I enter", "Colosseum", "help me win the hackathon", or asks about hackathon grants and Superteam Earn.

Core Solana dev kit: agents, workflow commands, go-to-market skills, MCP servers, and dev hooks. The full install (install.sh) additionally ships .claude/rules, the permissions/sandbox policy, and 18 ext/ submodules.

Unified skill hub for Solana development. Routes to external submodule skills (solana-foundation, sendai, solana-game, trailofbits, cloudflare, qedgen, colosseum, solana-new, ghostsecurity, defending-code) and local skills. Progressive disclosure — read only what you need.

Skill synchronization and management for Claude Code, Codex, GitHub Copilot, and Cursor. Provides 36 MCP tools for validation, sync, intelligence, research, and tracing.

Write thorough tests following TDD and BDD principles

Systematic debugging approach for identifying and fixing issues

Provides coding assistance with best practices and code review

Design RESTful APIs with best practices for consistency and usability

Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.

A shared knowledge base for developers and AI agents. Provides slash commands to save, load, search, and brainstorm with project planning documents stored in Pad.

🤖 Build powerful AI agents with TypeScript. Agenite makes it easy to create, compose, and control AI agents with first-class support for tools, streaming, and multi-agent architectures. Switch seamlessly between providers like OpenAI, Anthropic, AWS Bedrock, and Ollama.

Structured design-before-code workflow: HLD → LLD → EARS specs → Implementation plan

Experimental LID skills with opt-in installation and explicit lifecycle (promotion or retirement). Layers on top of linked-intent-dev and arrow-maintenance.

Scaling layer for linked-intent-dev. Tracks spec-to-code coherence across large projects via docs/arrows/ index. Includes brownfield bootstrap for mapping existing codebases.

Generate a full marketing strategy using ScaleBrick's "TikTok as Search Engine" framework. Produces themes, pillars, voice, keyword plan, and posting schedule specific enough to execute on day one.

Research high-intent TikTok and Instagram search keywords using ScaleBrick's framework. Returns categorized keywords with intent type, search volume estimate, difficulty score, and content angle for each.

Audit competitors using ScaleBrick's 3-surface framework (social, web/pages, SEO). Categorizes their pricing, features, and landing pages. Identifies gaps you can exploit, positioning angles no one is claiming, and specific moves you can make this week.

Analyze whether TikTok or Instagram search traffic is a viable growth channel for your business. Uses ScaleBrick's framework to evaluate demand, competition, content fit, and intent categories. Ends with a go/no-go recommendation.

Delegate implementation, web research, and codebase exploration to the OpenCode CLI (headless opencode run). Part of cc-multi-cli-plugin. Requires the `multi` plugin.

Hub plugin for cc-multi-cli-plugin: contains the companion runtime, subagents, setup wizard, and customization skills.

Delegate implementation, web research, and codebase exploration to the Cursor CLI (headless agent -p). Part of cc-multi-cli-plugin. Requires the `multi` plugin.

Delegate read-only research and codebase exploration to Google Antigravity via its headless agy CLI (Gemini 3.5 Flash). EXPERIMENTAL. Requires the multi plugin and the agy CLI installed + signed in.

MetaHarness — mint a custom AI agent harness from any repo. Paste a GitHub URL or start blank; output runs on Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, or RVM. WASM kernel (Rust → wasm-bindgen + NAPI-RS), 6 hosts, witness-signed Ed25519 releases, GCP Secret Manager validation. Browser Studio + `npx metaharness` CLI.

测试 use-self 替身会议的辩论质量。给定 persona + 3 个决策场景，运行完整三阶段辩论并按 5 个维度评分，输出质量报告。

测试 use-persona 的角色扮演一致性。给定 persona + 10 个对话场景，生成回复并按 5 个维度评分，输出一致性报告。

召唤你的数字替身进行决策辅助。多个版本的你同时分析一个决定，帮你看清局中看不清的自己。

以某个人的身份和你对话。用 ta 的语气、习惯、互动方式回应你。