Recently updated open-source projects

This skill creates architecture diagrams, flowcharts, CI/CD pipelines, dependency maps, or edits to an existing `.excalidraw` file without flooding the main conversation with diagram JSON. Isolated agents generate the drawing, then local scripts validate and render PNG or SVG output, with optional animated SVG export. It requires Claude Code, Node.js 20 or newer, and npm.

Tamara Payments is an offline documentation skill for integrating Tamara checkout, order states, signed webhooks, capture, refunds, and supported commerce plugins across GCC markets. It guides the server-side flow from checkout to approval, authorisation, fulfilment capture, and refunds, while separating API, notification, and public credentials. The bundled mirror is dated and should be checked against the current sandbox and documentation before launch.

This skill gives Claude Code, Codex CLI, or Gemini CLI the cluster-specific knowledge needed to work on Garnatxa over SSH: submit and monitor SLURM jobs, diagnose failures, tune resource requests, run bioinformatics workflows, and manage storage or tape archives. It requires an existing Garnatxa account, VPN access, and working SSH setup, while destructive or unusually large operations are designed to require confirmation.

Laravel Vue Starter is an opinionated foundation for admin panels and single-page applications. It combines Laravel 13 and Vue 3 with registration, password recovery, email verification, role-based authorization, user CRUD, reusable components, dark mode, and localization. The repository also includes project-specific skills for several coding agents so generated changes follow its conventions. It requires PHP 8.3 or newer.

VergingAI Agent Skills is a modular collection for media and AI-service tasks, including face swap, background removal, video enhancement, image generation, vision, chat, speech-to-text, and text-to-speech. Skills can be installed together or individually. Some tools accept local files or remote URLs, download inputs automatically, and show progress while using verging.ai services from an AI coding agent.

SEO Master gives file-based AI agents a structured workflow for technical audits, keyword and competitor research, local SEO, backlinks, and AEO/GEO readiness. It produces prioritized findings, developer briefs, and 30/60/90-day plans instead of an unranked checklist. Apify is the default data layer and requires APIFY_API_TOKEN; when data is unavailable, the skill falls back to browsing, uploaded files, or advisory analysis rather than inventing metrics.

Connect an MCP-compatible agent to the AdMapix API to search creatives by keyword, app, advertiser, category, or ad copy, then filter by format, country, region, and date. Results are raw JSON records with media URLs and metrics that can be sorted by relevance, first seen, estimated impressions, or active days. Presentation and strategy analysis are outside the project, and an AdMapix API key is required.

PII Scrub scans a target directory before a push, share, chat, or public release, using generic patterns plus user-defined patterns for personal schools, phones, or emails. It groups matches by severity and reports file, line, and context without rewriting or sending anything. Results are not logged, and the user decides what to remove or whitelist.

Greenfish Compose Multiplatform Skill collects practical conventions for Kotlin Multiplatform apps using Compose, Material 3, Koin, and one-way MVI state per screen. It encourages one class per file, named UI tokens instead of magic numbers, no mock data in production, and adaptive navigation that changes with width. The detailed rationale lives in the skill file.

Interview Outline turns a guest’s profile, company, field, public material, and recording schedule into a nine-section interview guide with follow-up questions. It also plans a main video title and short clips built around conflict, quotable lines, and methods. At least one link to the guest’s prior public output is required; engagement data must be supplied separately when unavailable.

pubmed-reference-resolver extracts References sections from PDF, DOCX, or TXT files, resolves citations against PubMed, and writes a PubMed-compatible CSV, numbered abstract text, integrated audit report, and journal-mismatch JSON sidecar. It handles common citation styles, PDF line-number noise, an offline MDPI fast path, unresolved-reference preservation, composite-key deduplication, and possible fabricated-citation detection. Python 3.11+, Anthropic, and NCBI credentials are required.

This Claude Code collection uses a router-to-executor architecture: project-compass identifies the current stage and directs work to a state-machine SOP builder, ACTOR reading coach, Socratic discussion partner, skill auditor, or postmortem writer. Teams can install the full set or reuse the routing pattern with their own executors.

Mand! teaches a Claude Code agent to answer fully first, then shorten its reply whenever the user says “korter,” “shorter,” “again,” or a similar cue. Repeated turns strip the response down to one word, and the skill can be installed locally or as a plugin.

Floor Plan Vectorizer detects walls and enclosed rooms in a raster architectural plan, then creates an interactive SVG with clickable room paths, stable IDs, and optional area labels. A known dimension or pixel scale enables square-meter or square-foot schedules; without a scale, rooms remain clickable but areas are omitted. Runtime needs numpy and opencv-python.

Audit a Shopify store through an MCP connection or public extraction. The connected mode reads real products, collections, navigation, apps, orders, and metafields, while public mode inspects visible markup, scripts, metadata, and structured data. The six-dimension review covers catalog, collections, navigation, SEO, app load, and conversion signals; public mode is less complete.

Use this skill across Shopify theme development, Remix apps, Storefront and Admin GraphQL, CLI environments, Hydrogen, and checkout UI extensions. It routes by task and consults live Shopify documentation through Context7 for version-sensitive questions. Shopify access and app credentials remain part of the setup; Context7 MCP is recommended for live documentation.

venture-analyst takes a startup or SaaS idea through problem discovery, competitor intelligence, validation experiments, and a Bull/Bear/Judge verdict. It gathers public signals, extracts pricing and gap clues, and proposes three prioritized tests such as a fake door or concierge MVP. No API keys or paid accounts are required, but the result is a starting point for real validation.

This pack covers four naming jobs: map competitor naming clusters, generate and score candidates across brand and domain factors, audit an existing name, and document a repeatable naming system. The suggested flow uses competitor mapping before generation, while an existing brand can move from audit to guide. Domain, social, and trademark checks are part of the candidate output.