Recently updated open-source projects

Load this skill into any agent that accepts Markdown context to draft or revise titles, abstracts, introductions, methods, experiments, figures, and closing sections. Its guidance is distilled from 63 embodied-AI papers across CoRL, RSS, ICRA, IROS, and Science Robotics. It focuses on writing craft, not experiment design, claim validation, research direction, translation, or LaTeX builds.

SAP-RPT-1-OSS Predictor helps prepare SAP extracts and run classification or regression with SAP’s open-source tabular foundation model using in-context learning. It includes local prediction and batch-processing helpers, with an optional playground API path. A Hugging Face account is required, and a 24–80 GB GPU is recommended for the intended workloads.

x-shot-skill captures the actual X article card instead of re-rendering a mockup. Playwright handles ordinary pages in an isolated browser, while opencli can temporarily use your logged-in Chrome for gated tweets; both paths produce precise 2× retina PNGs and stitch long cards automatically. It needs Node, Playwright, and Chrome, with Python’s standard library only for the fallback image stitcher.

kamar-taj bundles three Claude Code skills. wong reads the day’s sessions and produces a study guide, Slack standup, and explanations of unfamiliar Git commands. dormammu repeatedly attacks a solution with edge cases until it sees the check pass. agamotto brings in a separate AI critic to challenge a plan. wong uses Python; its optional PDF and Drive workflow also needs Node, Chrome, and rclone.

After installing the skill, its specialist agents, and the `bzrk` CLI, you can ask for error searches, trace analysis, metric exploration, service health checks, or production incident triage in natural language. The main skill routes each request to a focused log, trace, metric, cluster, or incident agent so detailed query output does not overwhelm the primary conversation.

yoda-skill adds a /yoda mode that compresses Claude’s replies with OSV inversion and zero filler, with padawan, knight, master, and grandmaster levels. Technical terms, code blocks, and error strings stay unchanged, and the mode turns off automatically for security warnings and destructive-action confirmations. It saves words by deliberately trading away normal sentence order.

shopify-theme-builder interviews for brand, markets, languages, template scope, and feature constraints before generating an Online Store 2.0 theme that merchants can control from the theme editor. It uses JSON templates, modular sections, design tokens, and reorderable blocks without hard-coding copy, colors, fonts, or images, and supports bilingual and RTL storefronts. Companion orchestration and UI-UX skills are expected, with optional Shopify CLI or Python validation.

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.

Dev_Wrapped turns git history or a GitHub account into a Spotify-Wrapped-style annual recap: one self-contained HTML file, hand-designed themes, and a final share card. It can also embed a live profile or repository card in a README, with optional Playwright export for PNG stories. Local mode reads only local git history, so the code data stays on the machine unless you choose a remote source.

animeblip-showrunner-skill drives Animeblip from a story brief through screenplay, characters and recurring elements, scene images, scene videos, and a final cut. It can run end to end or pause between stages for review and targeted fixes, and it supports shorts, films, and episodic series. The skill itself uses the fixed Anime6 style; other styles must be changed in the web editor. An Animeblip API key and hosted service are required.

AWRSHIFT gives coding agents a single adaptive flow for identifying a task, researching it, defining success metrics, comparing hypotheses, fact-checking a plan, and testing inside an experiments folder. The user chooses what happens at every phase transition. Main project files remain read-only until a GO decision and an explicit file-by-file implementation preview are approved.

Describe the customer, item, and payment in natural language, and the skill can create records, apply Portuguese VAT or exemption details, prepare a draft, issue the fiscal document, and download its PDF through FIZ. Issuing reports the document to Portugal's tax authority and cannot be undone, so the skill asks for separate confirmation. A FIZ account and API key are required, and non-trivial tax cases should be reviewed with an accountant.

facebook-leads targets industrial abrasive products by searching public Facebook content or analyzing private text you paste. It classifies buying, selling, competitor, and demand signals, scores lead quality, and exports a styled XLSX with tags, links, filters, and frozen panes. Append mode deduplicates by company name and URL, while public-search mode depends on an external search tool and a configurable result limit.

bdev-copyguard audits a URL or local codebase across hotlinking, bots, AI crawlers, canary fingerprints, watermarking, source exposure, framing, ownership evidence, and open data endpoints. It returns a prioritized score and hardening plan while separating real server-side access control from measures that only raise the cost of copying. The skill explicitly rejects right-click disabling as security: rendered content can still be saved, while protected data must stay behind authenticated server endpoints.

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.

AgentLint audits the context a coding agent reads, including AGENTS.md, CLAUDE.md, Cursor rules, and Copilot instructions, alongside repository conditions such as documented build commands, CI, tests, and oversized files. It runs as a standalone CLI in any Git repository, with an optional Claude Code command for teams that want the checks inside their agent workflow.

Once installed, the skill gives Claude Code or Claude Desktop working knowledge of Digital Samba's REST API, embedded SDK, JWT authentication, and common integration patterns. It can assist with room management, embedded calls, webhook handlers, and troubleshooting while drawing on included examples. The repository is guidance for a coding agent, not the conferencing service itself, and users still need a Digital Samba account and Developer Key.

paper-to-storyboard extracts a paper’s structure, tables, and figures, then helps Claude shape the material into a seven-to-nine-part narrative rendered as a static HTML, CSS, and JavaScript site. It is aimed at science communication and visual presentation rather than ordinary PDF conversion. Multi-column layouts and complex figure backgrounds may need manual cleanup, while optional cover generation requires an OpenAI API key.