Recently updated open-source projects

Notepanda is a deliberately simple cross-platform text editor with basic editing, line numbers, syntax highlighting, and a preview panel for Markdown and HTML. Files can be opened by drag and drop or passed directly when launching the app from a shell. Releases are available for Windows, macOS, and Linux, but the author presents it as a small learning project rather than a full replacement for mature professional editors.

Bernard Stiegler Perspective Skill loads Stieglerian concepts and methods into Claude or another compatible agent for humanities research. Users can ask for a Stieglerian reading of material about AI, platforms, algorithms, or digital industry, then choose a default or lineage-specific angle. It is an analytical lens rather than a conversational character or general-purpose assistant.

blueprint leads Claude through an adaptive concept discussion before implementation, producing module contracts, data models, security and test notes, operations details, risks, and estimates. Draft and locked phases let a team direction-check early or require complete, schema-validated, cross-consistent documents before building. The generated files default to German, and later updates show a diff before changing only affected sections.

This skill guides Mollie integrations for iDEAL, card payments through Mollie Components, hosted checkout for other methods, webhook handling, and a custom Medusa v2 provider. It focuses on integration-specific pitfalls such as profileId validation, iframe styling, amount formatting, return-URL polling, provider ID composition, and seed or region wiring.

sq-ai-design-thinking is an interactive consultant skill for Claude Code, Claude Desktop, and other LLM environments. It guides department leads, team leads, PMs, and founders through 27 frameworks across five stages, from opportunity discovery and user understanding to problem framing, experiments, presentation, and roadmap. It recommends framework combinations from the user's answers and saves workshop results as Markdown, CSV, PDF, or TXT in the current workspace.

CatalystAI bundles `llms-txt-cleaner`, an idempotent Python utility that normalizes scraped `llms-full.txt` documentation, with `catalyst-ai`, an expert skill for Zoho Catalyst services such as Zia, QuickML, ConvoKraft, and SmartBrowz. It includes installation paths for Claude Code, Cursor, Gemini CLI, Copilot, and Windsurf, plus planned work for deeper references and pricing guidance.

This skill turns a public Xiaohongshu image-note link into a structured reading with the title, original text, all images, engagement numbers, comments when available, and a one-line takeaway. It can optionally archive Markdown and images locally, but video and private notes are unsupported; comment capture needs Claude in Chrome, a Max subscription, and a logged-in browser.

MarkPDF Skill lets coding agents such as Claude Code, Cursor, and Copilot render Markdown as themed PDFs, editable PPTX decks, or styled HTML. It can also create share links protected by an email gate, password, or expiry. Rendering runs through the hosted MarkPDF MCP service, so no local document toolchain is needed, but users must configure a service token and the trial tier limits daily exports.

Token-Diet lays out an ordered optimization workflow for LLM applications: prune retrieved context first, reuse cached material, route work by complexity, keep structured state, and compress prose only at the final step. It also defines metrics and guardrails for token use, latency, cost, and quality, while excluding code, schemas, legal text, URLs, and identifiers from linguistic compression.

This Claude Code skill turns a Playwright run into an MP4 suitable for bug tickets, QA evidence, or demonstrations. It confirms the output location, records the browser in headed mode, detects a system ffmpeg installation or falls back to `ffmpeg-static`, and converts Playwright's WebM output to H.264. Existing files are preserved through incremented names, and the final response includes a local link to the output folder. Node.js 18+ and Playwright are required.

ArkTS Patterns gives Claude reference-guided workflows for state management, lifecycle, concurrency, navigation, networking, persistence, gestures, and project scaffolding on HarmonyOS NEXT. The skill routes each task to stable documentation and templates, while optional DevEco MCP tooling can add current API lookup, builds, launches, and UI verification. Basic use still works offline, but live checks remain unverified.

Use this monorepo as a structure for self-contained Claude skills. Each skill lives in its own copyable folder with a SKILL.md, metadata, examples, tests, and local helpers, while workspace scripts scaffold new skills, lint frontmatter, run health checks, generate an index, and detect cross-skill references. It deliberately keeps pnpm workspaces as the current tool and documents larger release systems as future options.

claude-skill-news-ticker renders news tickers, lower-thirds, and subtitle overlays from HTML and CSS, then encodes them as transparent ProRes 4444 MOV files for CapCut, Premiere, or DaVinci. It supports custom brand colors and fonts, automatic duration calculation, five palettes, and optional alpha-capable video formats. Playwright handles browser rendering and ffmpeg handles encoding.

The DEPEG skill explains how to derive public PDAs, decode on-chain account layouts, and build user-facing instructions for swapping USDC and stablecoins, staking, claiming rewards, unstaking, and buying boosters. It also covers permissionless keeper instructions, pool initialization with an admin co-signature, and parsing the protocol’s decimal-formatted logs. The guide pairs with the `@depegprotocol/sdk` TypeScript package.

Audit a repository, branch diff, or selected directory for code that tells users an action succeeded when it did not, as well as mocks, empty handlers, stale placeholders, and unfinished paths exposed as real features. Two complementary specialists inspect failure paths and apparent happy paths in parallel, then a deterministic aggregator produces a severity-ranked combined report. The silent-failure specialist requires a separate Anthropic plugin, while the stub audit can run alone.

This Claude Code skill analyzes a repository, proposes modules and effort estimates, then creates an Epic → Module → Subtask structure in Jira and advances issues only after testing. It resolves project-specific issue and transition IDs dynamically, verifies that the target Epic belongs to the user before destructive operations, and defaults deletions to dry-run. It requires Jira Cloud credentials and an Epic where the user is the assignee or reporter.

Website-Traffic-Analysis turns Claude into an SEO analyst through the Two Minute Reports MCP connected to Google Analytics 4 and Search Console. It covers traffic overviews, CTR issues, traffic-drop diagnosis, content gaps, keyword cannibalization, technical health, engagement, on-page checks, and a 30-day action plan. Use requires a compatible Claude plan, a connected MCP, and linked GA4 and Search Console accounts; the project states that MCP data is not stored.

md-twitter-dresser-skill dresses a finished Markdown article by proposing titles and image slots, then uses two HTML review rounds to confirm prompts and generated images before producing an article with embedded images. It supports a fixed 5:2 cover, content-based inline aspect ratios, bilingual prompts, reusable title and image styles, and standard CommonMark output; confirmation happens before image-generation spend.