Recently updated open-source projects

This skill drives the logged-in X web interface through a dedicated Chrome profile that loads only Kimi WebBridge, closes stale X tabs, and keeps the main browser untouched. Draft mode is the default; sending requires --send, while login, captchas, two-factor prompts, and password entry remain user responsibilities.

This skill routes research through nine scenarios or a generic mode, covering question framing, source collection, conflict tracking, four critique passes, citation validation, and gap logging. It produces a research-vault with query, plan, sources, findings, conflicts, gap-log, critique, and report files, while separating facts, inferences, and recommendations.

Use the five Claude Code commands to turn existing heritage documents, photos, and notes into a place brief, significance assessment, condition snapshot, prioritized recommendations, or a full assessment. The workflow follows the Burra Charter principle that cultural significance must guide later interventions, so recommendations cannot skip that step. Every output is a reviewable draft, not a substitute for a qualified practitioner, engineer, or statutory advice.

This skill helps Vietnamese web developers move from understanding English to using it in real-time work situations. It offers plans, lessons, short drills, writing review, mock interviews, inline correction, and progress tracking built around reusable phrases rather than isolated vocabulary. Examples cover PHP/Laravel, React/Next.js, and Node.js/TypeScript, with progress kept in one file between sessions.

Use unsloppify to lint Markdown prose with a fast CLI, then let its Claude Code skill handle patterns that need language judgment. The CLI can report or safely fix punctuation and banned phrases, scan directories in text or JSON formats, and run in pre-commit or GitHub Actions. The skill covers broader structures such as binary contrasts and false agency; exit codes distinguish clean files, findings, and invocation errors.

AI Skill Hub is a collection of small AI skills for reducing repetitive operational work and making execution easier to see. Its Standup Agent can combine changes from Jira, GitHub, Slack, and meeting tools into structured updates while surfacing blockers and stale work; the collection is intended for quick, lightweight integrations.

Content Repurposing Engine turns an article, essay, podcast transcript, or report into platform-specific deliverables. It extracts the central claim, hook, proof, and takeaway, flags thin or technical material, and can produce a LinkedIn post, X thread, newsletter blurb, or short-video hook with a format-specific visual idea. A selector lets you request only the outputs you need, while tone presets keep the voice consistent.

This Claude skill writes Spanish-language X posts and threads, offering variants and rationale, and can plan weekly calendars in Markdown or Excel. It can research a reference account and score drafts with signals from xai-org/x-algorithm; browser-based posting requires an authenticated Chrome session.

Meridian stores milestones, phases, plans, decisions, and checkpoints in a local SQLite state machine so Claude Code can resume deterministically after a session reset. It executes plans in scoped subagents, supports parallel waves, and applies regression checks, requirement coverage, stub detection, repair strategies, and two-stage review. Optional integrations can sync a kanban board or dispatch work to remote agents. Setup requires Python 3.11+, uv, Git, and Claude Code with skills support.

russian-text-quality scans code and locale files for Russian plural-structure errors, case-agreement problems, terminology drift, mixed-language content, and transliterated identifiers. It activates only when meaningful Cyrillic content is present and explains findings in English for reviewers who do not speak Russian. It is not a prose or spelling checker, and some heuristic checks may produce false positives.

This Claude skill covers Belgian accounting workflows in French and Dutch, including PCMN/MAR journal entries, balance sheets, income statements, BE GAAP, annual accounts, ASBL/VZW reporting, and sole-trader cases. It is an educational productivity aid, not professional accounting, tax, or legal advice, and draft figures still need verification.

Prepare print-safe output for oversized PDFs and high-resolution images. The Python utility scales PDF pages onto Letter or A4, tiles images across a fixed or automatically chosen sheet grid, and produces a preview PNG showing page gaps and layout before printing. It centers artwork instead of cropping mismatched grids; Python 3.10+, PyMuPDF, and Pillow are required, while printer setup remains external.

This community skill gives Claude a consolidated Bulma 1.0.4 reference covering components, forms, grids, themes, dark mode, Sass customization, and common page patterns. It is designed to prevent outdated class names and incorrect assumptions about Bulma's CSS-only behavior, and includes community extensions plus commands for checking and updating the bundled knowledge.

Use this Claude skill to structure EU and cross-border VAT questions in French, Dutch, English, or German. It helps qualify B2B and B2C transactions, assess place of supply, OSS/IOSS, VIES, SaaS, Brexit and Northern Ireland cases, and prepare invoice considerations. It deliberately avoids storing volatile rates, thresholds, and dates, requiring web verification for current figures; its output is general analysis, not tax advice.

Claude Figma Skills brings design review and comment-driven editing into Figma. Claude can leave feedback on specific elements, read requested changes, apply adjustments, and support token or handoff synchronization. It requires Claude Code and Figma Desktop; most write operations depend on the third-party figma-console MCP, while some comment and screenshot workflows also need a Figma personal access token.

Tvastar scans an existing frontend stack, installed component libraries, and color tokens before proposing a design system and page plan. After user approval, it can generate code and run checks for visual consistency, framework mistakes, motion, performance, and WCAG accessibility. It targets environments such as Next.js, React, and Tailwind, and requires Claude Code with Python 3.10 or newer.

army-to-civilian helps service members translate U.S. Army experience for civilian resumes, LinkedIn profiles, cover letters, and interview answers. It first adapts the framing to the target audience and document type, then checks acronyms, tone, and common veteran self-translation mistakes before producing the draft. Its rank and MOS mappings are Army-specific, so other branches need adaptation.

DailyForge turns the last 24 hours of Git activity across multiple Unity repositories into a narrative report for Discord. It enriches commits with Unity-specific context and supports whole-project, personal-commit, or anonymous team scopes without commit counts or rankings. Configure the provider, repositories, recipients, and webhook, and notify affected developers in writing before processing their data.