Recently updated open-source projects

Upload or point to a DDEX ERN XML file to detect its version, validate it against official schemas, and check fields such as ISRCs, UPC or EAN codes, territories, and required metadata. The result includes a release summary, error locations, and concrete fix suggestions. It is designed as a proof of concept for pre-delivery checks by labels and distribution teams.

Web Experience Auditor splits a website or web-app audit across specialized subagents for scope, browser capture, layout, UX, KPIs, structured data, research, and synthesis. Its knowledge gate checks installed versions before making version-specific recommendations and can fall back to static fetching when browser capture is unavailable. Full runs need a Claude Agent SDK environment and optional browser tooling.

econometrics-phd-level-skill organizes a Korean lecture series into topic-specific references and runnable Stata scripts covering OLS, inference, specification, IV and GMM, difference-in-differences, regression discontinuity, panel fixed effects, MLE, Logit, and Probit. A keyword router loads only the relevant references for each question, keeping the active context smaller. The material is derived from a third-party course rather than redistributing its original recordings.

Playing to Win applies Roger Martin and A.G. Lafley’s choice cascade to an idea, offer, codebase, or market move. It gathers context, labels claims as fact, inference, assumption, or speculation, tests the winning aspiration, where-to-play and how-to-win choices, and ends with one of five verdicts. Each run writes an offline interactive HTML page plus Markdown, with assumptions highlighted for follow-up validation.

Hormozi Offer Audit reviews an existing landing page, pricing tier, or lead magnet against the Value Equation and related offer frameworks. It identifies the weakest lever, produces a scored assessment, and ranks three concrete changes with before-and-after examples. The skill is designed for improving an offer that already exists; it does not create a new sales offer from a blank page.

Use human-copy as a final editing gate for English content before publication. Its seven passes target flagged vocabulary, stock structures, indirect copulas, repetitive rhythm, vague claims, em dashes, and leftover formatting, then return a findings table, rewrite, change summary, and second scan. It can be embedded in Claude Code, Claude.ai, Gemini, Codex, or a plain chat, with a detect-only mode when you do not want a rewrite.

BetterThink gives Claude Code, Codex, and Gemini CLI six guardrails for coding work: clarify scope, finish and verify one slice before the next, delegate mechanical tasks, keep instruction files lean, load supplementary docs only when needed, and check UI at three viewport widths. It is a portable skill prompt, not a separate test runner.

Ask an AI coding agent to create or manage Yandex Cloud resources and receive commands grounded in service-specific yc CLI references. Coverage includes compute, networking, managed databases, Kubernetes, serverless, storage, load balancing, IAM, observability, and other major services across multiple agent clients.

Operate Yandex Direct from Claude Code by listing or changing campaigns, ads, and keywords, adjusting bid-related resources, and requesting performance reports. The scripts support production and sandbox environments, agency accounts, and asynchronous report polling, and they require a Yandex OAuth token with Direct API access.

Pull web analytics from Yandex Metrica through Claude Code, including counter details, goals, preset or custom reports, and multipart raw-log exports. The included scripts cover the management, reporting, and Logs APIs and require a Yandex OAuth token together with curl, jq, and Python.

grayscale converts one image, many images, a directory, a ZIP archive, or any mix of them through a Claude skill or a plain Python command. It adds a -Grayscale suffix, preserves alpha channels for PNG, WebP, GIF, and TIFF, and keeps folder structure when rebuilding an archive while removing macOS junk and non-image files. Pillow is the only library dependency, with options for recursive folders and a custom output directory.

claude-gender-decoder checks job advertisements for gender-coded wording with a deterministic Python scorer based on published research, then adds contextual review to reduce false positives and catch phrasing the word list misses. It reports a coding verdict and can suggest a more balanced rewrite, with JSON output available. The project notes that its English-only, binary framing is directional: it does not cover every form of bias or replace a full inclusivity audit.

Give the skill a country and health domain to map health-system context, digital systems, indicators, gaps, and stakeholder questions from open institutional and academic sources. It renders a linked HTML profile and compact JSON, keeps contradictions visible, and records missing evidence instead of filling gaps. This is a starting brief, not a clinical tool or final assessment, and needs country-informed expert confirmation.

Content Dashboard archives posts from platforms such as Xiaohongshu, Douyin, WeChat, Taobao, and Xianyu into a local system. A Claude skill extracts titles, copy, screenshots, metrics, tags, comments, and history, storing Markdown for later agent use and a single offline HTML board for human browsing and sharing. The board shows trends and platform or rating breakdowns, applies configurable performance labels, and keeps a separate library for reference posts.

Claude Photoshop Skill turns plain-language design requests into layered Photoshop PSD files. Claude writes a small ExtendScript, runs it through Photoshop, renders a preview, and can rebuild after changes to text, color, or placement. It supports common social, presentation, web, print, and card formats, but remains an early prototype: a Mac with Adobe Photoshop, Claude Cowork, code execution, and macOS control access is required, while print PDF output is experimental.

xml-mapper transforms CSV, spreadsheets, JSON, database rows, API payloads, or free-form text into XML that conforms to a target DTD. Its standard-library validator reports each error with a location and explanation. When element-versus-attribute choices, content ordering, enumerated values, or required fields are ambiguous, the skill asks targeted questions instead of silently guessing. No third-party XML package is required.

Gemini as Tool lets Claude Code call Gemini 3.x Pro or Flash as a second opinion, builder, or judge through a Google AI Pro OAuth subscription. Its Python harness supports the Gemini CLI and Antigravity backends, including isolated parallel calls, without an API key. Users still need a signed-in CLI or agy installation, and OAuth credentials stay in the OS keyring.

This opt-in plugin has Claude Code append a short plain-language spoken summary to conversational replies, then sends only that summary to a persistent edge-tts daemon for playback. You can change voices, mute output, or interrupt speech without reading code, tables, or file dumps aloud. It requires Windows 10 or 11, Python 3.10+, and edge-tts; playback is not currently supported on macOS or Linux.