Recently updated open-source projects

Use a reasoning-first workflow to generate a desktop UI, set design direction, critique an existing screen, remove generic generated patterns, or envision a future interaction model. The skill combines transferable principles from multiple designers, derives an original token system, checks output with a deterministic slop linter, and records project decisions for later sessions. It targets desktop application shells; a separate sibling project covers browser-based interfaces.

web-legal-audit performs an external review of a website URL across GDPR-related obligations, Spanish e-commerce rules, AEPD cookie guidance, WCAG 2.2, the European Accessibility Act, HTTP security headers, and advertising claims. It produces a structured DOCX report and a remediation plan with sample policy text and code snippets. Estimated penalties are based on public precedents and the project explicitly treats the output as guidance, not legal advice.

Tutor de Skills teaches beginners to create Claude skills through an interactive five-level progression. The tutor adapts the pace, builds a working skill alongside the learner, and shifts from demonstration to shared work and independent practice instead of delivering a lecture. It also includes branded HTML teaching material for instructors, plus references covering the levels, a guided case, and visual identity.

rpcwright teaches an agent to change an Ethereum execution-layer JSON-RPC method across the client, execution-apis, test generation, and Hive rpc-compat. It covers build plumbing, OpenRPC semantics, local fixture generation, and cross-client replay, including traps such as a green run that executed no tests. Guidance is verified for go-ethereum and Nethermind, and best-effort for other clients.

Superior Skills adds agent workflows for strategy authoring, backtesting, opportunity scanning, structured trade theses, and deployment through Superior Trade and Hyperliquid. The skills work with OpenClaw, Claude Code, Codex, and other compatible clients, but require the platform API and a trading account. The repository warns that its backtests cover a specific historical window and do not guarantee future performance.

cooking-master turns a dish name, a list of ingredients, or an imported recipe into a tailored cooking plan. It asks about people, equipment, time, taste, restrictions, and pantry contents, then returns shopping guidance, timed steps, cues for judging progress, and common failure fixes. It can coordinate several dishes around available burners and remember a kitchen profile. The skill depends on Claude and may search online when its recipe library has no match.

share-html is a collection of standalone HTML templates for reports and interactive briefs. The editorial style includes a sticky table of contents, searchable tables, Kanban boards, charts, and progress checklists, while the handdrawn style uses Traditional Chinese headings, Rough.js borders, notes, and whiteboard blocks. Because data is embedded, rendered files can open from file:// or on mobile without a server.

Hookfrisk inspects agent hooks changed by a diff and looks for untrusted tool output, filenames, or trigger text being piped into a shell, along with patterns such as curl piped to bash. It refuses the done state while an auto-running hook can execute input unsafely, helping catch command-injection and remote-code-execution paths before release. It is intended for Claude Code and compatible coding agents.

Ao is an unofficial desktop client for Microsoft To Do on Windows, macOS, and Linux. It emphasizes fast keyboard operation with extensive local shortcuts, configurable global shortcuts, direct list navigation, quick task creation, and search. Theme choices, compact mode, scalable UI, and an always-available window make it useful for people who prefer a dedicated task app, but it is a community project rather than an official Microsoft client.

BlueNexus Agent Builder interviews you about an agent’s audience, workflow, guardrails, connectors, knowledge, and dashboard before driving the BlueNexus studio through Claude in Chrome. It configures the agent and publishes it end to end, with room to refine the dashboard from reference screenshots. Automated building requires a logged-in BlueNexus account and Claude in Chrome; without browser control, the skill serves as a step-by-step guide.

This portable knowledge pack lets Claude, Codex, Cursor, and other coding agents work with Qapla’ shipment, label, tracking, quote, pickup-point, and webhook APIs without repeatedly fetching documentation. It includes examples and dependency-free reference clients for public v1.3 and the stable core of v2. It is documentation tooling rather than an official SDK, so live Qapla’ docs remain authoritative when details differ.

Coverbean turns a post description into a title, image prompt, and platform-sized cover or thumbnail for Xiaohongshu, WeChat, Douyin, TikTok, and YouTube. It renders the image through apimodels.app’s gpt-image-2-all and crops it to the required aspect ratio, with optional ffmpeg support. Setup needs an API key and Node.js 18 or newer, and image generation is paid.

Neovate Code turns natural-language requests in the terminal into code changes, bug fixes, refactors, reviews, and tests. After choosing a model provider, you can inspect proposed edits and approve tool calls before they run. It supports both interactive and headless use, with provider credentials configured through environment variables or its login flow.

Gatefrisk reviews HTTP routes touched by a change, classifies them as read-only or mutating, and blocks completion when a route can write data, move money, or trigger a job without authentication. It is designed to catch temporary trigger endpoints and similar authorization gaps before release. The skill supports Claude Code, Codex, Cursor, Gemini CLI, and OpenCode.

Quests is a desktop app for generating, running, and refining full-stack applications on your own computer with a model provider you choose. It supports multiple projects, built-in version restoration, reusable templates, model comparisons, and exportable applications that can run elsewhere. The app is available for macOS, Windows, and Linux, but it requires an API key for at least one supported AI provider.

Use this skill to turn AI-sounding Italian into natural prose without flattening the author's facts, argument, register, or voice. It applies an Italian-specific editorial workflow covering syntax, punctuation, cohesion, rhetoric, clichés, and common generative habits, and it can also answer usage questions. The skill knows when informal keyboard conventions should be left alone; its instructional content is in Italian.

Tockler automatically records computer usage and working time from active window titles and idle state. Its timeline, calendar, charts, and daily, weekly, and monthly summaries show which applications were used and how time was distributed. The free desktop application runs on Windows, macOS, and Linux, making it useful for retrospective time analysis without manually starting timers.

Harness Starter Kit helps an agent inspect a repository and add the smallest useful set of instructions, constraints, feedback loops, memory, checks, and evaluation records. Its prompt-first commands cover doctor, adopt, review, update, and refresh, while preserving existing architecture. The kit documents operating context; it does not by itself prove better agent outcomes.