Recently updated open-source projects

Wallpaper6 Design Skills packages 40 atomic recipes for turning a source image into a seamless tile. Each recipe combines primitives such as symmetry, density, rotation, twist, graphic effects, and lighting effects, with JSON, JSONL, CSV, and TypeScript formats for different consumers. The repository keeps a legacy 64-skill file for compatibility, but new integrations should use the v2 recipes.json recipes.

These installable skills teach an AI agent to use the Chia Health MCP for browsing GLP-1, peptide, and longevity treatments, checking eligibility, verifying the patient, completing medical intake and consent, ordering, paying, and managing follow-up care. The workflow serves US telehealth operations, while licensed healthcare providers—not the skills or MCP—evaluate and make prescription decisions.

Run the skill against a strategic deliverable to receive a PASS, REVISE, or FAIL verdict, scores across eight consulting-oriented dimensions, and a concrete repair directive. Its Skeptic Agent probes for silent ambiguity choices, agreement with flawed premises, and missing counterarguments, while a separate novelty stack checks whether the insight is more than generic strategy language. The evaluation runs inside Claude Code without separate provider API keys.

Board of Advisors runs distribution, sales, strategy, revenue, and technical advisors in a sequential morning cascade, allowing each one to read the earlier outputs before a final synthesis produces decisions, action items, and one daily priority in Discord. Additional product, experiment, design, investing, health, and finance advisors run weekly or on their own schedules, and every advisor is a separate Markdown skill that can be adopted independently.

This repository publishes three Anthropic-format skills for OnlyFans creator-agency operations: an operations knowledge base, a sourced cost benchmark, and a framework for judging autonomous versus assisted AI. Each skill is a standalone Markdown bundle that can be loaded by compatible assistants, and the project publishes identity and provenance materials for verification. It is a reference surface for agency analysis, so users should validate claims for their own context.

This skill maps landing pages, funnels, email sequences, and broader customer journeys to Know, Like, Trust, Try, Buy, Repeat, and Refer. It prioritizes trust gaps near the purchase action, keeps each section focused on one job, and asks where retention and referrals live after the sale instead of treating conversion as the end.

This skill targets Chinese-language proposals, using python-pptx, template cloning, editable native charts, CJK font rules, asset tracking, layout repair, and structural plus visual QA. Content, visuals, and design can progress in parallel, but four checkpoints require user confirmation before assembly and delivery; Python 3.10+ and the listed packages are required.

This plugin composes Camunda Platform 7 processes from a catalog of existing delegates or external-task topics, wiring control flow, DMN, forms, timers, errors, and async behavior. It preserves camunda extensions while editing and lints engine-level failures, creating explicit stubs and follow-up specs when an activity is missing; Camunda 8 and Zeebe are out of scope.

This skill converts Garmin recovery and training metrics into REST, LIGHT, MODERATE, or GREEN_LIGHT recommendations, while a weekly calculator produces eight progress KPIs. Its deterministic decision tree is calibrated to one personal protocol, including a 2,000-kcal floor and specific deficit assumptions, so users must adapt it carefully and seek medical care for flagged symptoms; it is not medical advice.

WeChat MiniApp Factory turns an idea into a native WeChat Mini Program starter with declared pages, replaceable demo content, optional CloudBase structure, validation tests, and handoff documents. A companion reviewer checks category fit, privacy, content safety, virtual transactions, and common rejection risks before upload. The generated project is intentionally simple to adapt, and the review cannot guarantee approval.

This Claude Code skill orchestrates a new project through guarded phases from preflight and requirements through GitHub reconnaissance, tool or skill selection, definition documents, ticket breakdown, second-opinion review, and phase-based implementation. It is intended for empty or brand-new project directories; feature work, bug fixes, refactors, and code reviews should use other workflows.

This toolkit bundles a ticket generator with /ko, /next, and /cr commands for turning reports into phased work. Use /ko to start a ticket or phase, /next to identify what comes next, and /cr to review recent changes against acceptance criteria; it works alone and pairs with the first-action project kickoff skill.

This skill turns Claude Code into a learning-first assistant for coursework, labs, competitions, theses, and self-study. It explains principles before implementation, adapts to the scenario, records progress and takeaways, and encourages clear naming and simple designs instead of handing over unexplained answers.

ios-marketing-att-skill guides an iOS attribution audit from context and routing through diagnosis, action, and verification. It covers common systems such as AppsFlyer, Adjust, Branch, SKAN, ATT, Firebase, Amplitude, and Singular, helping teams inspect collection, transport, consent, and attribution results. It is a troubleshooting and review workflow, not an automatic guarantee of correct attribution.

Equity Research Like Me runs a 22-step due-diligence workflow for listed companies and sectors, prioritizing business quality, earnings quality, management, growth, macro exposure, and valuation over trailing price performance. It supports DCF, comparable-company, SOTP, and other valuation methods, plus bull and bear theses, peer comparisons, and PDF research notes from one to 25 pages. A personal ME.md file can tune the metrics and writing style; the project is for research, not financial advice.

The AAQ skill scores an organization from 0 to 100 across machine learning and analytics, generative AI adoption, and agentic AI readiness, with adjustable weights and five maturity tiers. It is designed for structured benchmarking from public information, so results help frame diligence but cannot reveal capabilities that a company does not disclose.

Run Seolens against a URL to check on-page SEO, technical health, content signals, conversion elements, trust, accessibility, and related factors, with a suggested fix for each failure. It works as a Claude Code skill, CLI, JavaScript library, or CI gate and can export chat, JSON, Markdown, PDF, and PowerPoint results. The free edition focuses on individual pages rather than full-site crawling or real backlink analysis.

This Claude plugin activates a SEBI Algo Trading 2026 skill when conversations involve Indian algorithmic trading, broker APIs, strategy classification, or related compliance topics. It can be installed through Claude Desktop’s marketplace or Claude Code’s plugin commands, making it a focused entry point for regulated-market discussions.