Recently updated open-source projects

loveorder uses roughly 40 themed questions and six rounds of reflection to shape an ideal partner profile around identity, daily life, connection, attraction, growth, and boundaries. After the user confirms the profile, it creates an HTML “letter to the universe” with a send animation, receipt stamp, and save or PDF export options, with pronoun tracks for he, she, or an open choice.

Magyar-eladó researches public Hungarian marketplace listings, estimates quick-sale, market, and patient prices, recommends suitable platforms, and writes platform-specific listings with photo folders and a posting checklist. Optional browser assistance stops before final submission by default; Facebook is never DOM-automated, while an explicit auto-submit flag is available at the user's own risk.

Browse a verified catalog of Telegram Premium Emoji IDs with previews, search, sections, and fallback characters. The accompanying Claude Code skill can choose icons for a bot style and generate aiogram code, while the Telegram bot accepts new emoji descriptions and pushes catalog updates to GitHub Pages. Running the update bot requires Telegram and GitHub credentials.

rviewer converts a textbook chapter, PDF, screenshot, Obsidian note, or pasted text into a fresh diagnostic quiz. Learners answer in a local browser with per-question timing, hints, and immediate feedback, then receive an HTML mastery report based on accuracy, speed, streaks, and subtopics. SQLite keeps session history so progress can be reviewed over time.

harness-check audits multi-agent frameworks assembled from prompts, Markdown, and scripts. It checks four dimensions: system architecture, trigger reliability, execution reliability, and declared-versus-wired behavior, covering 24 failure patterns involving discovery, registries, symlinks, script seams, locks, and state handling. Findings must be verified against real files, then appear in a behavior-focused report with severity, fix risk, and a split between safe fixes and decisions that need the owner’s call.

HTML to Presentation converts an index.html into a self-contained 16:9 deck with keyboard navigation, deep-linked slides, an overview grid, speaker notes, a dark-mode toggle, and print layout. Its extractor and linter have no dependencies, while the Playwright harness screenshots light and dark slides and exercises keyboard navigation end to end. Playwright is an extra requirement for the visual checks.

layout-map-illustrator separates visual restyling from factual labeling: it detects site pads, builds a blank positional anchor, asks an image model for watercolor or cartoon styling with text removed, then overlays names and numbers at exact coordinates. The labels remain reliable even when the art changes. Standalone use requires a Google API key plus google-genai and Pillow.

agentic-commerce-news scans the previous seven days of public X posts, industry media, and VC or platform announcements for agentic-commerce startups, launches, funding, partnerships, and influential opinions. It filters for credible endorsement, classifies items across a nine-layer commerce stack, and writes sourced cards, an overview table, and weekly takeaways. Quality rules reject stale, duplicated, or purely sponsored items and require dates from source pages. It needs a WebSearch-capable agent; persistent scheduling is optional and environment-specific.

product-view keeps Claude in a product-language lens that describes what a customer, player, reader, or developer experiences. Its explain, reframe, and plan modes cover existing flows, bugs, and new functionality, with view on and view off for persistence. It deliberately stays out of algorithmic, performance, infrastructure, and code-style questions where technical language is the more useful level.

Ganhuo Textbook Downloader parses natural-language requests for Chinese school or university textbooks, using province, city, grade, subject, volume, and edition clues to rank public PDF candidates. Cover or page OCR can add matching signals, and split PDF parts are reassembled automatically. It returns local paths, upstream locations, source URLs, and ranking reasons, but does not claim official edition status.

Transcrever Reel downloads audio from an Instagram Reel and transcribes it locally with yt-dlp, ffmpeg, and Whisper. It returns readable paragraphs plus timestamped segments and can detect Portuguese, English, and other languages. Audio stays on the computer, but macOS may need a logged-in browser session, and the first run installs tools and downloads a speech model.

Quetzalcoatl helps a team decide why an AI project matters and whether it is feasible before execution. It compares alternatives, cross-checks decisions with Claude and GPT, records decisions and risks in resumable project documents and dashboards, and keeps sending, payment, deployment, and deletion behind a human approval gate.

Ganhuo Travel Lock helps plan family trips, graduation travel, and city routes by comparing tickets, hotels, transport, and budgets. It records the source and query conditions, presents trade-offs, and keeps a status table for locked, suggested, pending, or backup choices. It is a decision aid rather than a ticket bot or payment robot, and it does not promise the lowest price.

This agent skill helps consultants and business teams turn a company name into an AI opportunity map. It guides a web-search-capable agent through company and industry research, pain-point analysis, scenario discovery, prioritization, and implementation planning, with quick, standard, and deep report modes. The repository includes industry examples, analysis frameworks, and report templates. Research quality depends on the connected agent and its search and reasoning capabilities, and the supporting framework script requires Python 3.8 or later.

agentrank-verify queries an x402 counterparty’s AgentRank before settling payment. The 0–1000 score is derived from real on-chain USDC settlements and weighted by payer reputation, and the check works through MCP, A2A, or a plain HTTP GET. It helps identify counterparties with verifiable settlement history, but a reputation score is a pre-payment signal rather than a guarantee of safety or delivery.

Powerhouse Clarity Coach leads an entrepreneur through five phases covering values, vision, scheduling, business validation, and mindset blocks. It turns the conversation into a full-picture analysis, an Eisenhower goal matrix, a personalized reflection question, and reusable weekly and milestone templates. The skill is intended for personal development and does not replace therapy, medical, legal, or financial advice.

Bloom's Quiz Builder guides teachers from an uploaded reading or chapter to a validated question set spanning all six Bloom's Taxonomy levels. It identifies testable themes, collects preferences such as grade level and question type, and asks for approval as questions are built. The finished set can be exported as JSON for editing, review, or import into a learning management system.

skill-stocktake reviews an installed Claude skill library in one context and assigns Keep, Improve, Update, Retire, or Merge recommendations based on quality, overlap, freshness, and optional usage history. It supports full and changed-only audits, then asks for confirmation one item at a time before consolidation; usage counts require the bundled Claude Code hook.