Recently updated open-source projects

The SendFlow API Skill teaches Claude Code to work with SendAPI's 44 WhatsApp-automation endpoints across campaigns, groups, messages, accounts, templates, blocking, verification, and media. It includes an OpenAPI 3 specification, real response examples, and Node.js and Python helper clients with authentication and rate-limit handling. The service is aggressively rate-limited and requires a user-created API key.

wayamzpost turns an Amazon seller's daily topic into researched copy, six to nine rendered cards, and a platform-ready Markdown post in Chinese or English. It supports platform-specific limits for Xiaohongshu, LinkedIn, X, and Instagram, plus source-health checks. Some gated sources are fetched through Chrome, while automatic publishing is disabled and enabling the adapter requires considering platform terms and account risk.

Use eight agent skills to investigate wallets, tokens, transactions, market data, smart-money activity, and MEV across Dune, Solscan, Nansen, Solana RPC providers, pump.fun, Dexscreener, and CoinMarketCap. The workflows prefer parsed and batched endpoints, estimate or gate costly calls, and include resumable asynchronous Python examples for larger jobs. Most paid data providers require your own API keys.

Repo Docs System builds a Chinese knowledge base around a codebase, including an AGENTS.md context map, an architecture overview, design documents, product specifications, execution plans, and a documentation coverage score. It is intended for both human maintainers and AI agents that need a reliable project map. Repeated runs update and extend the existing documentation rather than deleting prior content.

Analyze whether a company could plausibly compound toward a tenfold return using current market facts, 25 structured modules, and separate five- and ten-year scenarios rather than one target price. The method covers business quality, financials, competition, risks, valuation, passive-portfolio opportunity cost, Kelly sizing, and assumptions to revisit later, with special handling for crypto-linked equities. It supports several public and pre-IPO markets and is not investment advice.

Work with Chef Infra Server and Chef Automate without repeatedly looking up knife syntax. The skill covers node and cookbook operations, bootstrapping, remote execution, monitoring, and failure diagnosis, but it expects Chef Workstation, a configured knife profile, and network access to the target Chef environment.

cursor-chats-bridge connects Claude Code to Cursor's local chat database in read-only mode on Windows. An MCP server exposes workspace and chat listing, active-chat retrieval, search, and journal queries, while a scheduled poller records new messages every five minutes for later recap. It never writes to Cursor's database, but it only sees live messages from the currently open chat and does not backfill older history.

memory-map bundles three skills that preserve project progress, decisions, and pending work after a conversation ends, recall relevant context in later sessions, and propose cleanup when stored memory becomes stale or cluttered. It uses a local Markdown file in Claude Code, the persistent memory interface on claude.ai, and can be installed in other tools that support the Agent Skills format.

Meme Library ingests single images or batches, uses a vision model to create semantic filenames and metadata, and organizes them into collections with distinct vibe fingerprints. An agent can then choose the best collection and image for a conversation without loading the whole library. It returns a local path only, so delivery through WeChat, Telegram, Slack, or another channel needs a separate sender integration.

SceneLens prepares public video URLs or local files for Claude by extracting frames at scene changes, running OCR on each frame, and attaching a timestamped transcript. It first tries native captions, then falls back to Groq or OpenAI Whisper and automatically splits audio that exceeds the API size limit before merging timestamps. Accuracy is best for videos under ten minutes, output is capped at 100 frames, and authenticated private platforms are not supported.

OpenOrder helps an AI agent maintain a local investment-research wiki instead of leaving insights in chat history. It reads an index before answering, ingests pasted articles or earnings material into immutable raw files, updates company and industry pages, logs every write, and can lint for contradictions or stale gaps. The same Markdown-based wiki works across Claude Code, Cursor, Codex, and other supported agents.

Seedance Forge is a reference library for drafting Seedance 2.0 video prompts, not an automatic prompt generator. It searches 2,366 authored community prompts by keyword, author, or length, returns source links, and helps extract three structural patterns from the results. The package has no third-party dependencies and works in Claude Code and Codex CLI, but its conventions are specific to Seedance and do not target Sora, Runway, Veo, Kling, or image generation.

SubManager is a cross-platform Python utility that follows GitHub users who follow your account and unfollows users who later leave. Two blacklist files let you exclude selected accounts from either side of the automation. After configuring a username and personal access token, the script can run manually or on a schedule through cron on macOS and Linux or Task Scheduler on Windows. It is intended for users who want recurring relationship maintenance rather than manual list updates.

claude-tabletop inspects a project's files to choose a relevant incident or continuity scenario, then creates a facilitator runbook and an interactive HTML version. The runbook supports a timer, staged inject reveals, decision logging, and JSON state export. A companion skill turns that export into an After-Action Report with a timeline, gaps, and severity-tagged actions. It covers nine domains, including security, SRE, privacy, data/ML, and AI safety.

Use this skill when Claude Code needs reliable, Mac-specific guidance for SwiftUI and AppKit work instead of defaulting to iOS patterns or stale APIs. Its references cover windows, menus, sandboxing, signing, notarization, testing, and macOS 15 and 26 features, with triggers in English, Vietnamese, and Simplified Chinese; iOS and other Apple platforms are outside its scope.

Research Backlog fetches unstarted issues for a Linear team and assigns a separate research agent to each ticket. The agents investigate the technical domain, official documentation, prior art, best practices, and likely gotchas, then post structured comments back to Linear. It finishes with a summary table and requires a Linear API key plus `jq`.

past-paper-topic-analyzer reads a chosen window of exam PDFs end to end, clusters topics inductively, and exports a three-sheet Excel workbook with coverage, every question grouped by topic, and a year-by-topic frequency heatmap. It counts an essay once, records cross-topic material separately, and preserves enough question detail to defend the tally. The workflow depends on accessible public PDFs and an explicit board, level, section, and year scope.

job-hunt-skill turns a job description and an experience bank into a one-page tailored CV, a cover letter, a short outreach message, application answers, a submission tracker, and feedback rules across eight phases. The master CV remains untouched, metrics must be confirmed, and the final Submit action stays with the applicant. It began with UK AI startup roles, so senior, non-technical, or other-market searches need adaptation.