Recently updated open-source projects

AI Tutor structures learning around retrieval practice, spaced review, interleaving, elaborative questions, and adaptive difficulty rather than immediate answer delivery. Its learn, practice, review, quiz, and explain modes prompt the learner to recall first and offer only the hint needed to continue. It is plain Markdown that can be adapted to several LLM platforms; where file uploads are supported, the learning-science reference files can be added as well.

meeting-minutes-skill sends meeting audio to Alibaba Cloud OSS and Tongyi Tingwu for transcription and speaker separation, optionally extracts text from presentation files, and produces formal Chinese minutes with action items and review notes before exporting a Word document. It keeps the transcript as the factual source and warns against inventing names, budgets, or promises. OSS and Tingwu credentials are required.

Senior SAAD takes a project idea through a multi-phase design process: advisors challenge the scope, then the skill shapes architecture, data and API maps, security planning, UX direction, key screens, and an implementation prompt package. It pauses for confirmation before visual design and coordinates installed UI and engineering skills. The output is planning material for Claude Code, not a finished application.

github-search-skill searches GitHub across repository, code, REST, GraphQL, and CLI angles to uncover useful projects that star rankings may hide. It includes a dead-end guide, code-search examples, and a batch shell helper with deduplication and rate-limit handling. The workflow uses GitHub’s official API rather than scraping and requires an authenticated gh CLI plus jq.

ByteDa Skill turns a short design brief into assets such as posters, long images, social graphics, presentations, comics, or H5 pages. It calls the ByteDa MCP service through a self-contained Python standard-library CLI, so the host client does not need a separate MCP setup. A ByteDa API key is required.

llm-wiki-distiller separates notes, clippings, articles, chats, books, screenshots, and code into a preserved raw layer and a distilled wiki layer with source links. It offers quick, distill, review, search, and integrate modes, then checks for contradictions, stale pages, broken links, and orphans. The Markdown and Git-friendly output can feed articles, newsletters, decks, or agent context.

web-animation-engine combines a Claude skill with a compact React and SVG runtime for animated explainers, diagrams, dashboards, and motion graphics. Stage owns the playhead, Sprite controls each beat's time window, and SVG and HTML layers handle different visual elements. React 18 and Babel load from a CDN, so there is no npm install or build step; the result is runnable HTML rather than an exported video.

claude-telegram-bot-skill automates @BotFather through a logged-in Telegram Web session to create one independently revocable push bot per project. A Python standard-library helper then sends notifications from cron or scripts, reusing the same chat ID while storing a separate token for each bot. The workflow reads tokens from the DOM, cancels destructive dialogs, and avoids common Telegram Markdown parsing failures.

grok-skill lets Codex or Claude send research queries to an OpenAI-compatible Grok endpoint and receive structured JSON containing both an answer and its sources. It is aimed at time-sensitive checks such as software versions, release dates, documentation, installation details, and troubleshooting. Configuration can be supplied through local overrides or environment variables. The included one-click installer targets Windows PowerShell, and the skill still requires you to provide a working 2api or other compatible Grok endpoint.

skill-create-video-meta-ai drives Meta AI through a logged-in browser using Playwright MCP, producing roughly five-second clips from prompts. For a longer story, continue in the same chat so the next scene preserves the style, then stitch clips with ffmpeg. No separate video API key is needed, but Claude Code, the browser connection, and a Meta AI account are required.

Key Message Review examines prescription-drug marketing messages for empty claims, weak strategic grounding, and common compliance risks, then rewrites them around a concrete patient, a memorable point, and a clinician action. It offers quick, standard, and deep modes plus an optional before-and-after card. It is not a substitute for medical or regulatory sign-off and should not invent efficacy data.

MNB Claude Skills bundles ten independent workflows for Indian legal documents, GST invoicing, startup compliance, pitch decks, outreach, content, interviews, data cleaning, and technical handoffs. The skills require no API keys and can be used separately. Legal, tax, and compliance outputs are preparation aids and should be reviewed by a lawyer, CA, or CS for high-stakes use.

slidewright creates animated presentations on a fixed 1920×1080 HTML, CSS, and JavaScript stage, either from scratch or from extracted PPTX content. Each self-contained HTML deck includes inline text editing plus comment and annotation modes that export feedback as structured Markdown. Helper scripts also cover PDF export and Vercel deployment.

jiaoben helps creators and content teams turn an idea into a shootable script for talking-head videos, vlogs, or live content. Its workflow emphasizes the opening hook, platform-aware retention structure, and spoken pacing rather than generic prose. It targets Douyin, WeChat Channels, Bilibili, and Xiaohongshu video workflows.

codex-collab gives Claude and Codex one append-only Markdown journal so neither agent needs to relay the other’s context by hand. Both read the index and the current day at startup, then record what they did, verified, touched, and leave open after each round. Claude is the default lead for planning and implementation while Codex supplies an independent review, but both are peers in the journal. Delegation requires a Codex MCP server.

agent-token-usage-skill maps a natural-language question to the underlying atu CLI, then summarizes local session-log usage across Codex, Claude Code, Pi, Grok, opencode, and openclaw. It reads files already on your machine, makes no network call, and needs no API key. The skill installs across platforms, although the bundled CLI installer differs between macOS or Linux and Windows.

This skill turns a short description into an editable Google Sheet for CRM, orders, or general records. It proposes columns, keeps dropdown values on a separate Lists tab, and applies section colors and practical formatting. With the Chrome extension connected it edits a live sheet; otherwise it can generate an XLSX or CSV fallback.

claude-skill-llms-txt validates, repairs, or generates llms.txt, llms-full.txt, context files, and per-page Markdown using the llmstxt.org and Mintlify formats. It checks the root H1, blockquote summary, H2 link lists, Optional section, non-fetchable targets, and stray headings, while also guiding discovery headers and serving across stacks. A dependency-free Python validator and Claude Code hook are included.