Recently updated open-source projects

Build or extend Flask REST APIs with Controller, Service, Validation/DTO, and Model layers. Specialized agents review the plan and code, run migrations and pytest, and keep API documentation aligned with Marshmallow schemas through generated OpenAPI output. Its opinionated Python and Flask stack suits teams that want consistent conventions across new endpoints and existing services.

These Claude Code skills gather material from repositories, Git history, or pull requests, turn it into stakeholder-friendly HTML, and publish it through the Uselink CLI. They cover repository overviews, PR digests, changelogs, API documentation, onboarding guides, reports, and planning specs. Publishing requires a Uselink account, an API key, and a configured CLI.

claude-skills bundles eight Claude Code skills for turning repository and development artifacts into shareable Uselink pages. Each skill gathers project data, renders HTML, and publishes through the Uselink CLI, so stakeholders can read without repository access. Setup requires a Uselink account, API key, and installed CLI.

edm-review checks transactional email templates against structure, visual styling, client compatibility, and accessibility checklists, then groups issues by real-user risk or polish. Non-engineers can select which fixes to apply and receive a diff or full file with plain-language explanations. Project conventions cover Mailgun variables, the icon system, a forced light-mode policy, and optional Branch deep links.

Decision Translation helps professionals adapt dense judgment to the way a real decision-maker receives information. It diagnoses the decision system, creates a concise decision version plus a fuller reference version, scans where the message may stall after delivery, and suggests ways to unblock it. Variants cover spoken updates, cross-cultural communication, crisis messages, and boards, while also watching the sender’s attention load.

linux-wayland-chinese-input-method walks Linux and GNOME Wayland users through installing fcitx5 with Rime and the rime-ice dictionary, including the `IM_MODULE` values that avoid Qt input failures. It also covers switching schemes and basic candidate-panel theming, and can be installed as a Claude skill for guided setup. The instructions target Linux desktops rather than macOS.

This tool fetches the day’s limit-up stocks and analyzes each one across news catalysts, capital participation, limit-up quality, sector resonance, and consecutive-board position. It produces scored Markdown attribution reports with a driver summary and next-day outlook; the project is for research only and does not provide investment advice.

claude-skill-module-design turns a development task into a blueprint of modules, stages, and atomic operations, with a target end product at each level. Its nine-step method starts with premortem and inversion, places the Config/Client/Storage triad, and finishes with checklists and a failure-to-measure mapping. It suits work that needs an explicit structure and contract before implementation.

marketing-skills is an English translation of Vlad Yasko’s collection of 35 Claude Code skills. The bundle spans SEO, conversion optimization, copywriting, paid ads, content strategy, email, pricing, referrals, product marketing, and related utilities, with single-skill or full-bundle installation. It is useful when an English-language marketing workflow needs modular skills rather than one large prompt.

yulya-reels-skill applies Yulya Filipenko’s documented Reels formula to an idea and returns three hook options, a timed script, production notes, caption copy, and CTA variants. The structure moves from a short hook through setup and proof, a numbered framework, and a soft CTA, with visual and editing guidance kept separate. It is suited to creators who want a ready starting draft rather than an unstructured idea list.

agentic-delivery-skill supports approved-scope execution from kickoff through evaluation, launch, support, handoff, and closeout. It selects templates for project plans, milestones, decisions, risks, change requests, acceptance packets, monitoring, runbooks, and escalation, then keeps outputs aligned with the engagement’s scope and approval gates. It can feed verified delivery facts back into proposal, contract, invoice, and email workflows, and is designed for bounded agentic pilots rather than open-ended delivery.

Nigerian-Prince-Scam-Detector analyzes emails, SMS, direct messages, screenshots, voice transcripts, `.eml` files, URLs, phone numbers, and crypto wallet addresses for scam indicators. It combines header forensics, domain and wallet checks, scam-database references, and location-aware plausibility checks, then saves a Markdown report while explaining the con in a distinctive narrator voice. It asks only for a city and country, not a street address.

agentic-invoice-skill selects and drafts invoices, pro formas, deposits, milestone bills, change orders, retainers, credits, refunds, receipts, and closeout documents from contract and billing facts. Its Python tools render branded Markdown and PDFs, while placeholders remain visible until client, tax, payment, and accounting details are verified. It is suited to agentic development engagements with milestone-based billing.

simetrik-design-studio groups five Claude Code skills around Simetrik’s product design language. The `simetrik-ui` hub coordinates product design, UX research, UX writing, onboarding, and data-visualization work, while companion skills handle the specialist tasks. It includes the product glossary, navigation patterns, design-system rules, and brand-specific exclusions, so it is tailored to Simetrik rather than a generic design kit.

agentic-proposal-skill turns verified discovery into buyer-facing one-page pilots, proposals, SOWs, roadmaps, evaluation plans, risk and control plans, change orders, and approval summaries. It chooses the document by buyer stage and decision need, while keeping scope, assumptions, risks, acceptance criteria, and approval gates visible. Templates remain drafts until pricing, timeline, and other client facts are verified.

agentic-security-review-skill creates bounded review artifacts for permissions, data exposure, credentials, tools, retrieval sources, external actions, launch blockers, rollback, and incidents. It selects checklists and memos by the change or launch event, then keeps controls, logs, approvals, and escalation paths explicit. The output is a practical review draft, not a substitute for the technical or client signoff needed for a real launch.

agentic-discovery-skill structures early work for agentic development through intake questionnaires, discovery scripts, interviews, workflow maps, readiness checks, risk reviews, success criteria, evaluation worksheets, and proposal handoff briefs. It focuses on bounded scope, approvals, logging, monitoring, documentation, and support, helping a team clarify unknowns before a proposal is written. Python tools can render the selected artifact as a branded PDF.

agentic-case-study-skill turns verified delivery outcomes into client interviews, anonymized or named case studies, testimonials, technical notes, sales one-pagers, website stories, and other proof assets. It selects formats by evidence, approval status, and channel, then can render branded Markdown and PDFs. Sensitive details and attribution stay bounded, and placeholders must be replaced with client-approved facts before external use.