Audit and rewrite B2B website messaging, positioning, and value propositions.
Project overview
Revenue Messaging Framework audits a B2B homepage, scores its messaging, explains weaknesses section by section, and returns rewritten headlines, value propositions, calls to action, and a three-layer narrative. It is meant to clarify what a go-to-market team should change on its own site, combining an open methodology with a Claude Code skill. The output is an audit and rewrite, not a general page builder.
Run and benchmark reusable agent skills that coordinate MCP tools.
Project overview
Open Agent Skills is a lightweight, provider-agnostic framework for combining domain instructions with MCP tools across GitHub, filesystem, and browser tasks. It extends MCPMark with skill-based runs so developers can compare task completion and context usage under the same evaluation setup. Running it requires Python 3.11+, model credentials, and any task-specific services or containers. The project describes itself as a starting point, and some included skills remain narrowly tailored, so scripts should be reviewed before production use.
Coordinate multiple LLM agents for task solving and behavioral simulations.
Project overview
AgentVerse offers separate frameworks for collaborative task solving and for simulating interactions among multiple LLM-based agents. Its examples cover software teams, classroom environments, games, and other research scenarios, with support for hosted APIs and selected local-model setups. The simulation code is being refactored, and the project directs users who need a stable simulation-only version to the release-0.1 branch.
Experiment with building Tauri desktop apps through a Deno-based framework.
Project overview
Use Deno to create WebView windows, communicate between frontend and backend code, and compile experimental Tauri desktop applications into executables or installers. Development requires Deno, a stable Rust toolchain, and Tauri's platform prerequisites. The repository is explicitly unmaintained, its published demo is documented as failing, and several planned capabilities remain incomplete. It is therefore better suited to studying an earlier Deno–Tauri integration approach than to serving as a dependable foundation for a new application.
Build browser, mobile, and desktop apps with component-based JavaScript and HTML.
Project overview
Aurelia 2 is a front-end framework for browser, mobile, and desktop applications that stays close to web standards and favors conventions over configuration. Applications are composed from JavaScript or TypeScript classes paired with HTML templates, and developers can start with the project generator or study the repository's loader and bundler examples. The supplied documentation describes Aurelia 2 as beta software, with untested public API areas and additional breaking changes still possible.
Build restrained, data-led presentations with reusable HTML, CSS, and React pieces.
Project overview
Peg helps you create consistent slide decks and data-heavy presentations without starting in a design tool. It supplies opinionated HTML templates, CSS design tokens, React components, and entrance or transition animations built around typography, restrained color, and flat layouts. Chinese typography and reduced-motion preferences are handled explicitly, while static exports preserve the completed visual state.
Configure and run web, mobile, and load tests through one QA command line.
Project overview
An interactive setup adds test infrastructure to TypeScript or Python projects, while one CLI dispatches Playwright web tests, Appium mobile tests, or k6 load tests. AI planner, generator, and healer definitions are currently focused on TypeScript, and several other test types, including API, accessibility, and visual regression, are still planned.
Keeps spec-driven AI development lean, right-sized, reuse-first, and test-verified.
Project overview
Go Lean SDD sizes planning to the change: minor work stays in conversation, while larger features earn durable artifacts. Every change includes colocated tests plus a mutation-style discrimination check that proves the test can fail, and the agent searches the project, dependencies, standard library, framework, and platform before adding new code. It keeps durable context in one AGENTS.md instead of a stale scaffolding tree.
Audit code, documents, and other artifacts with traceable red-team checks
Project overview
universal-audit-skill classifies almost any work product, selects relevant verification domains, and produces a numbered audit record with severity-rated findings and remediation links. It supports code, applications, APIs, architecture, infrastructure, reports, spreadsheets, and media across Claude, Codex, Cursor, Gemini, and Copilot. Constructive and adversarial passes can be combined, while external standards and facts still need current validation for the project.
FrameworkAI and agent developmentModel Context Protocol
superagentx
@superagentxai·Python
Build multi-agent workflows with approvals, persistent state, and audit trails.
Project overview
SuperAgentX coordinates modular agents that can carry out multi-step workflows across browsers, APIs, databases, conventional tools, and MCP integrations. Sensitive actions can pause for human approval, while execution state, memory, and audit logs are retained. It is aimed at applications that need agents to take actions without giving up governance or operator control.
Build extensible C++17 component systems behind stable interfaces.
Project overview
Velk helps C++ applications define components through interfaces with typed properties, events, functions, and metadata. Runtime implementations live in a shared library while consumers depend on stable public contracts, allowing internals to evolve without rebuilding every client. Its registries, plugin loading, object factory, and dense storage suit modular systems that need runtime extension and introspection.
FrameworkAI and agent developmentModel Context Protocol
agentsilex
@howl-anderson·Python
Builds a small, readable agent framework with swappable models, tools, sessions, and handoffs.
Project overview
AgentSilex is a roughly 300-line Python framework built around readable Agent, Runner, Session, and tool abstractions. LiteLLM lets it switch among more than 100 model providers, while the framework adds tool calls, session history, multi-agent handoffs, MCP clients, streaming, and structured output. OpenTelemetry tracing is included for inspecting execution, and the package requires Python 3.12 or newer.
Assemble scattered inputs into structured Chinese government and enterprise proposals
Project overview
solution-drafter turns chats, meeting notes, and emails into formatted Chinese government or enterprise proposal documents. Its framework, document types, and domain plugins are separate, while five file-based stages handle intake, asset gathering, outline filling, content drafting, and revision. Missing source material stays marked for completion instead of being invented, and long documents are written section by section so completed work remains on disk if a run stops. The final output is a font-compliant DOCX.
Scaffold and maintain opinionated full-stack projects with Claude Code.
Project overview
ASCENT scaffolds a containerized Express, SQLite-WAL, React, and Vite project, then keeps it organized with ADRs, phase-gated delivery, tests, health checks, and session-resumption files. Its parent Claude skill routes work by engineering role and operation mode, while embedded ascent-* skills audit the project as it grows. The framework is deliberately opinionated, so it suits teams that want strong conventions rather than a minimal or freely chosen stack.
Reduce LLM token use by pruning context, caching prompts, and routing models.
Project overview
Token-Diet lays out an ordered optimization workflow for LLM applications: prune retrieved context first, reuse cached material, route work by complexity, keep structured state, and compress prose only at the final step. It also defines metrics and guardrails for token use, latency, cost, and quality, while excluding code, schemas, legal text, URLs, and identifiers from linguistic compression.
General skillSoftware developmentAgent2Agent protocol
improve-ai-readiness
@mynk-s-rwt·JavaScript
Raise a public website from basic crawler visibility to agent-ready access in measured levels.
Project overview
Use this framework to audit and improve a public website one readiness level at a time. It guides the addition of discovery files, crawler policies, Markdown negotiation, MCP/A2A and skill catalogs, OAuth metadata, WebMCP, and related public surfaces, then reruns an external audit to show progress. Platform notes cover common Next.js, Astro, SvelteKit, Cloudflare, Vercel, Netlify, and static-site setups; commerce protocols are opt-in and should appear only when the site has a real commerce or payment flow.
Remove common AI-writing patterns from Claude Code output.
Project overview
Make Claude Code prose less formulaic with six layers: persistent rules, a slash command, a Write/Edit hook, a reviewer subagent, and a scoring CLI. The framework covers 38 patterns and four domain profiles, so academic, documentation, blog, and commit writing can use different exceptions instead of one blunt filter.
Teach AI and civic literacy through a six-stage, context-first method.
Project overview
This methodology begins with tangible ideas such as sand, silicon, switches, and binary, then builds step by step toward the internet and AI. Its six-stage arc—Ground, Build, Participate, Reframe, Mirror, and Connect—is designed for learners with little technical experience or understandable distrust of institutions. The repository includes a Claude skill, DOL framework mapping, evaluation materials, and nonpartisan guardrails for civic education.