Recently updated open-source projects

When a user or support agent describes a problem with missing details, this Claude skill asks focused follow-up questions and fills a standardized 10-field template. It captures reproduction steps, environment details, expected versus actual behavior, and a suggested priority, then returns a report ready to paste into an issue tracker.

This skill writes optimized DuneSQL, runs and polls queries through Dune’s MCP tools, and supports common wallet, token, DEX, NFT, and protocol analysis tasks. It estimates credits before execution and download, warns or blocks at configured thresholds, and can rotate free keys before asking to use a paid key.

Use this Claude Code skill for straightforward Word-document work on Windows, especially when Cyrillic or other non-ASCII text causes encoding failures. A Python script extracts paragraphs and tables as UTF-8, while a Node script builds DOCX files from a JSON specification with headings, lists, images, and tables. It deliberately omits tracked changes, comments, footnotes, and in-place find-and-replace, and requires Python plus the global docx package.

This skill accesses Nansen’s Smart Money, Profiler, Token God Mode, Portfolio, Prediction Markets, and Hyperliquid endpoints across 37 chains. It tracks remaining credits, rotates keys, and guards against expensive options such as premium labels or agent endpoints, making it useful for budget-aware wallet and token research.

This skill covers quotes, market caps, OHLCV history, global metrics, Fear & Greed, exchanges, DEX data, airdrops, and trends through CoinMarketCap Pro. It uses stable CMC IDs, batches requests, estimates credit usage from returned data points, and encourages caching; a CMC API key is required, and historical coverage depends on the plan.

This skill uses DexScreener’s free, unauthenticated API to search tokens and retrieve current price, volume, liquidity, market cap, price changes, and trading pairs. It can batch up to 30 tokens per call and inspect trending snapshots, but the API has no historical data, WebSocket stream, or paginated search.

The skill streams token launches, trades, KOL activity, and PumpSwap migrations, while also documenting bonding-curve math and historical analysis. It includes Lightning and Local trading examples, requires a single shared WebSocket connection, and needs a Solana RPC plus a hot-wallet private key for trading; Lightning adds a managed service fee.

The skill handles standard Solana JSON-RPC calls for accounts, blocks, transactions, tokens, and fees across providers such as Helius and QuickNode. It also covers provider extensions, favors parsed APIs and JSON-RPC batches, and supports primary/fallback endpoints; users must supply a Solana RPC URL.

The skill covers more than 50 Solscan Pro v2 endpoints for wallet, token, NFT, transaction, and DeFi activity. It switches batch work to asynchronous Python scripts, favors multi and CSV export endpoints over repeated calls, and monitors live CU and rate-limit headers; a Solscan Pro API key is required.

e2e-agent coordinates a coding agent and a test agent through JSON files instead of a message broker or shared memory. Its initialization command scaffolds task queues, a Docker Compose app and database, test scripts, and a report reader. The test agent runs plain-language scenarios, returns feedback on failure, and routes completed or exhausted tasks to separate folders.

This Claude skill role-plays a professional bartender at an elite Louisville club between 1910 and 1915. It answers questions about period cocktails, spirits, service, and club culture using research drawn from historical bartending manuals. The persona deliberately stays within its pre-Prohibition time frame, making it useful for historically themed research or conversation.

Use JARVIS-Starter to bootstrap a new Claude Code project or adopt an existing repository through gap analysis. It adds project-scoped hooks and a `.jarvis/` workspace that maintain wiki context, recommend models, recall past decisions, track focus, and watch for hardcoded secrets or `.env` leaks without replacing existing documentation. The assistant is aimed at users who prefer plain-language development, and each added behavior remains optional.

Use PRCSS to scaffold an end-to-end product design project, plan a single phase, or generate one design-method card. After a four-question kickoff, it produces structured Markdown based on a seven-phase workflow, ready to paste into a wiki, kanban board, document, or Figma without locking the team to a specific tracker.

Drop source files into a folder and convert PDFs, Word documents, spreadsheets, PowerPoint decks, ebooks, notebooks, archives, YouTube transcripts, and web pages into Markdown for downstream AI tools. The skill uses MarkItDown locally, caches unchanged files, and spends no LLM tokens or API calls. Image-only scanned PDFs are not OCRed and return a warning.

Doc Harness records project rules, current work, file locations, and past phases in a maintained set of Markdown documents so a new agent can resume from files alone. Its Claude Code version provides commands to initialize, check, sync, flush, recall, and resume projects, while Kimi CLI installation is also supported; the documentation system requires no database or external memory service.

After you provide a published page and confirm its primary query, the skill reads the source and top three search competitors, drafts a 30–50 word opener, and cycles it through fourteen judges focused on facts, intent, entities, differentiation, voice, and format. It returns the converged block with an edit log and is intended for substantive published pages seeking AI citations, not drafts, short articles, or conversion-first pages.

The coach calibrates learners across 12 CEFR sub-levels, rewrites real articles to the chosen difficulty, and adjusts future sessions from comprehension feedback. It archives reading logs, vocabulary, inline IPA, and generated audio in Obsidian, then deliberately reuses the learner’s latest weak structure; Claude Code, Obsidian, and edge-tts are required.

The skill analyzes a named game mechanic through three construction layers—rules, experience, and system relationships—and three evaluation dimensions: innovation, feedback loops, and coupling. It produces a 500–1,000-word Markdown and HTML report, with optional web-source extraction for traceable analysis.