Recently updated open-source projects

Dialogic Reading turns a book into a reading plan shaped by your purpose, deadline, and daily time. Each session gives one short chunk with a location, vocabulary, focus points, and one question, then waits for your response before updating progress, notes, and stage summaries. The records remain as plain Markdown files you own, so it supports active reading rather than a summary delivered to you.

Use the skill to review French text for stacked short sentences, chained present participles, empty intensifiers, anglicisms, false contrasts, and formulaic phrasing. It favors more naturally connected French syntax and can score a draft across five writing dimensions before revising it. The tool focuses on style and typography, not detailed spelling or grammar correction, factual accuracy, argument quality, or specialized literary and legal registers.

Skill ClaudeMD helps trim an existing CLAUDE.md by deciding what to keep, cut, reference, or move into path-scoped instructions, skills, nested files, and hooks. It checks commands, paths, and contradictions, reports before-and-after size, and targets a soft 200-line ceiling. It does not rewrite MEMORY.md or author a file from scratch.

Use it to review essays, posts, documentation, or professional email before publication. The Claude Code skill identifies filler, stock structures, vague verbs, and over-compressed slogans, then rewrites the text with clearer subjects and more varied rhythm. It can be installed as a plugin or copied into a skills directory, but it does not check grammar or verify factual claims.

The skill interviews you about what your GitHub profile should emphasize and how much maintenance you will accept, then selects one of nine archetypes and drafts Markdown from your actual work. It can generate consistently themed badges, stats cards, stack widgets, and install steps, helping developers avoid a cluttered collection of unrelated widgets while keeping the profile style aligned with its upkeep requirements.

Run a findings-first audit loop: explore high-risk code, verify each candidate with a concrete failure scenario, and report ranked issues before editing. After approval, make minimal fixes, compare with a test baseline, verify using the project's real build or test command, then commit and push without force-pushing.

Turn mathematical or scientific material into complete LaTeX documents, reusable snippets, or Beamer slide decks. After installing the skill, describe the theorem, proof, algorithm, table, or presentation you need, then compile the resulting .tex file in Overleaf or a local TeX distribution. The Claude web route does not require a terminal.

Give zobe.ai a design brief, existing code, a screenshot, or a URL, and it will clarify the brand direction before creating or rebuilding the interface. It produces HTML or React with Tailwind plus a portable token set for color, type, spacing, radius, and motion, with formats available for several coding agents. Optional image generation requires a paid OpenAI API key; the core design workflow does not.

Give Claude a brief, prototype, deck, or URL, and the skill guides it through scripting, a beat-by-beat motion board, design review, a roughly 15-second hook render, and the final 60–90 second film. It is a workflow rather than a standalone app and requires a skills-enabled Claude environment, Node.js 22, FFmpeg, a renderer such as Remotion or HyperFrames, and ElevenLabs access for voiceover.

Claude Coach uses training history, event goals, injuries, travel, and equipment constraints to create plans for marathons, triathlons, and other endurance events. Users can enter fitness data manually or connect Strava, then edit, move, and complete workouts in a browser-based plan that stores data locally. Workouts can be exported to calendars, Zwift, Garmin, or TrainerRoad formats. It requires Claude.ai or Claude Code with network-enabled Skills, and Strava access requires user-created API credentials.

pi-mem stores durable facts, daily logs, notes, and a scratchpad as plain Markdown, with tools for reading, writing, and keyword search. It can inject long-term memory, open tasks, and the latest daily logs into each agent turn while leaving older material available on demand. Installation targets the pi coding agent.

Praman turns a business-process description into planned, generated, and repaired Playwright tests for SAP GUI, UI5, WebGUI, and Fiori applications. For UI5-based interfaces, it queries controls through the runtime registry rather than relying only on fragile DOM selectors, while also offering typed fixtures for manual test authoring. It requires Node.js 22 and a compatible Playwright release.

This developer template demonstrates a Tauri v2 desktop application with a Next.js interface and a FastAPI backend. PyInstaller compiles the Python service into a single-file sidecar that Tauri starts and stops, while the frontend communicates with it over local HTTP, so end users do not need a separate Python installation. Developers can build platform-specific installers locally or adapt the included GitHub Actions workflow for Windows, macOS, and Linux releases.

youtube-summary uses `yt-dlp` to collect a YouTube transcript, metadata, and chapters, then writes a structured note with a TL;DR, takeaways, links, and open questions. For slide-heavy videos, an opt-in mode downloads the video, detects distinct slides with `ffmpeg`, reads their text and visuals, and embeds key images beside the prose. Notes can print in chat or save to an Obsidian vault.

cv-creator builds, improves, reviews, and tailors CVs through one Claude Code skill. It separates regional patterns for US/Canada, UK/EU, Germany, academic applications, and UAE/GCC from industry overlays such as tech, nursing, finance, sales, trades, creative, and executive work. Markdown needs no extra tools; PDF and DOCX output requires pandoc, and PDF also needs a TeX engine. Japanese, Chinese, and India-specific formats are outside v1.

Designed specifically for German rather than translated from an English humanizer, the skill checks 36 patterns, including nominal style, genitive chains, bureaucratic phrasing, and repetitive connective openings. It produces an initial rewrite, audits its own draft for remaining AI tells, and then returns a final version. A personal writing sample can be supplied to calibrate the voice.

Triangula uses an iterative evolutionary algorithm to approximate an image with triangles or other polygons. Users can work through the separate graphical application or the companion CLI, which generates an intermediate JSON result and later renders it to SVG or PNG. The number of points and optimization settings can be adjusted for different styles and detail levels. Unlike instant geometric filters, the algorithm improves over repeated iterations and may need meaningful processing time before the result reaches the desired fitness.

Mappa creates furnished tabletop RPG areas as two aligned ASCII layers for Illwinter’s Floorplan Generator: an architecture grid exported to PNG and a furniture grid composited over it. When a needed object is missing, it can generate artwork with Canva and convert it into a transparent TGA icon. The workflow requires Python, Pillow, NumPy, a legitimate Illwinter installation, and the Canva MCP server for generated objects.