Recently updated open-source projects

gsheets-apps-script-skill helps teams turn a Google Sheet or CSV into working Google Apps Script and HTML Service code. It formats and validates sheets, adds lookup or aggregation formulas, builds a validated data-entry form, and handles common traps such as empty sheets, text dates, and deployment file names. The generated code still needs to be deployed in the user's Google environment.

Code Inspector is a Go CLI and library for finding worthwhile refactoring targets across many programming languages. It combines complexity, git churn, duplication, maintainability, and dependency-graph metrics, then reports file- and function-level details plus ranked hotspots. The repository also includes a Claude Code skill for first-pass code-health analysis. Non-Go language support requires cgo and a C compiler.

unigui-framework-skill distills 116 official uniGUI 1.60.0 documents into mental models, decision heuristics, VCL-to-uniGUI mappings, anti-patterns, and a deployment decision tree. It helps Delphi developers reason about the shift from desktop-style code to stateful web applications, and supports architecture design, code review, migration, performance work, and Standalone, Service, ISAPI, or HyperServer choices. The material is Delphi-focused, may lag newer releases, and has limited coverage of mobile controls and advanced APIs.

Paste in an existing draft and the skill scans for stock AI vocabulary, formulaic phrases, and structural habits such as excessive em dashes or repeated three-part lists. It returns a diagnosis, a cleaner rewrite, and an explanation of the most important edits while trying to preserve the writer's voice. English coverage is the most developed, Spanish has a starter map, and the tool is neither a from-scratch generator nor a fact checker.

Clever Comebacks turns a mean message into one concise reply. Choose soft, medium, heavy, or trainwreck intensity, and the skill applies a reframe-first method instead of adding filler or escalating by default. It refuses slurs, bigoted attacks, violence threats, doxxing, attacks on third parties, and anything longer than one sentence. It is a free Claude Code skill with no separate API key or signup.

scraper offers an article mode for clean text and metadata and a soup mode for CSS-selected fields. It respects robots.txt, handles retry and exponential backoff, writes JSONL incrementally, resumes successful URLs after interruption, and can seed work from a sitemap. The tool identifies HTML, PDF, and JSON responses and can optionally use ScraperAPI for proxying or JavaScript rendering. It is intended for auditable collection rather than unbounded crawling.

ai-footprint reads local Claude Code and OpenAI Codex transcripts, removes duplicated resumed messages, and estimates water use, energy, and CO2e with model- and datacenter-specific factors. It reports combined totals, ranges, per-agent shares, and offset-cost scenarios without sending data away or requiring a paid API. The skill is read-only and portable across Claude Code and Codex. Its numbers are modeled estimates, not direct measurements from a provider’s meter or invoice.

claude-dependency-mapper turns static imports into two complementary views: an Obsidian vault for people to inspect architecture and change impact, and a compact PROJECT_MAP.md that Claude can read once to navigate code. A hook refreshes the views after source edits; small projects stay with direct exploration, while larger ones get the map to reduce repeated searches. Resolution is static-import and regex based, so unusual constructs may be incomplete.

Automatically route a hard task into either a creative track that amplifies, builds, playtests, and judges the artifact, or an audit track that gathers independent findings, reaches consensus, implements fixes, and verifies them adversarially. The Claude Code skill loops until explicit completion criteria are met and a fresh pass finds no material next steps, escalating with preserved state when blocked or over budget.

github-repo-audit runs five specialist agents over an existing repository’s public surface, covering competitive framing, user language, positioning, README hierarchy, and search or AI discoverability. It synthesizes the findings into severity-ranked issues and proposed fixes, then waits for approval before editing files or GitHub metadata. The skill is for maintainers with a working product, not for code quality or security scanning.

Provide the company, industry, and service details to generate a ready-to-use client onboarding system. The output includes welcome messages, a structured intake form, kickoff agenda, access and asset checklist, a week-by-week 30-day plan, and a CRM workflow specification. It can run as a Claude Code skill or through a Python command-line generator that uses only the standard library.

biz-health-check looks up a Korean business registration number across public records and returns facts, sources, and lookup times side by side. Providers cover tax status, national-pension workplaces, published tax-debt lists, corporate basics, procurement sanctions, and regional permit status. It intentionally avoids scores or interpretation, downgrades unavailable providers instead of crashing, and requires a data.go.kr key for some services. Local permit matching also needs a region and may not provide the registration number itself.

Zenith Audience adapts Elias Mamã's Audience method into a Claude Code plugin that connects trend research, idea development, scripting, pre-publication checks, metrics review, and weekly planning into a daily content workflow. It uses specialized agents and slash commands and includes HTML script templates.

fk_marketing’s achete-pas skill separates a real need from a product story before comparing new items. It considers doing nothing, repairing, borrowing, or buying used first, then examines specifications, observed prices, total cost, and footprint only if a new purchase remains justified. The current implementation assumes France and French sources, runs on claude.ai rather than Claude Code, and requires manual re-upload when updated.

This community skill gives Claude a structured workflow for planning, building, debugging, reviewing, and preparing Flutter apps for release. It favors feature-first Clean Architecture and includes guidance for responsive UI, REST and Laravel APIs, Firebase, state management, local storage, plus templates, checklists, and a feature scaffolding script. It is guidance rather than an app framework, and roadmap areas such as Supabase, in-app purchases, animation, and a full testing workflow are not yet included.

Upload a PDF, DOCX, or text CV and the Claude Cowork skill produces a single-page LaTeX package with main.tex, company logos, and an Overleaf setup guide. The template avoids letter-spaced section headings to preserve ATS parsing while keeping a distinctive layout and clickable employer links. It requires XeLaTeX; longer resumes and non-Latin scripts may need manual adjustment, and published ATS scores come from one scanner.

RGS Skill helps Dutch sole traders, BV owners, bookkeepers, and bookkeeping-tool builders map ledger entries to the national Referentie GrootboekSchema. The same mapping can support annual accounts, tax filings, statistics, and SBR reporting, with guidance for entity and sector subsets and tools such as MoneyBird. Its scope is Dutch-GAAP and SME bookkeeping: it does not supply IFRS mapping or consolidation logic for multinational groups.

repo-onboard gathers repository, manifest, entry-point, test, and CI signals, then forms an evidence-linked view of the project's purpose, stack, and current state. It persists that understanding for reuse, asks the user to confirm or correct it, and only then asks what to do, without editing the repository during onboarding.