Recently updated open-source projects

Upstream Sync avoids blindly merging an original repository into a customized fork. It fetches upstream diffs, compares each file with local modifications, chooses whether to apply, adapt, partially apply, or skip the change, edits files directly, records the last synchronized commit, and reports every decision so future runs remain incremental.

Use Copy That Sells to create or diagnose conversion copy for print and outdoor ads, headlines, landing pages, emails, product descriptions, manifestos, and sales letters. It follows a structured brief-to-self-edit workflow, draws on direct-response and advertising craft, and removes common AI phrasing in English and Spanish. The skill refuses to invent proof, figures, testimonials, or claims, and it is not intended for long-form articles, internal reports, or naming work.

FiveM Resource Builder scaffolds resources such as shops, garages, jobs, and HUDs for FiveM or RedM while putting security-sensitive logic on the server. Generated events validate types and ranges, prices stay server-controlled, money and item actions get rate limits and anti-duplication guards, and world actions use proximity checks. It supports ESX, QBCore, QBox, ox, and related ecosystems, with escaped NUI output and optional luacheck CI. The result is a secure starting point, not a finished game feature.

venture-compass is a Claude Code co-pilot for solo AI-built micro-ventures. It keeps state in VENTURE.md, watches kill dates, live metrics, and landscape freshness, and convenes independent adversarial lenses when a gate is due. The stages cover whether to take on an idea, success and kill criteria, checkpoint verdicts, and a constrained pivot, returning GO, PIVOT, KILL, or SCALE with a default bias toward killing on time. Project-local metric collectors run only after their source is explicitly marked verified.

Solution Ladder makes an agent consider several architectural responses to a refactor or wiring problem: a local patch, a per-consumer escape hatch, a safer right default, and an outside-the-ladder wildcard. Separate blind subagents develop the options without knowing one another, then a blind judge ranks them against the current codebase and flags both insufficiency and overreach. The skill works in Claude Code, Codex CLI, and OpenCode; no level is universally correct.

Spectron was a testing framework for Electron applications that combined ChromeDriver with WebdriverIO and provided an Application API for launch and browser-style interaction tests. Its version map ties specific Spectron releases to Electron versions, which matters when maintaining older suites. The project has been officially deprecated since February 1, 2022, so it is mainly relevant to legacy maintenance and migration rather than new test development.

Trim Diff Noise classifies each branch diff hunk as definite noise, necessary, or borderline before changing anything. It reverts only approved definite noise, asks about borderline cases, verifies each revert with the project's test and lint commands, and leaves all reverts unstaged for review; its default verification assumes Ruby with RSpec and RuboCop.

App Store Connect Agent Skill maps plain-language requests to a bundled CLI for Apple’s official App Store Connect API. It manages listings, localizations, review replies, reports, media, TestFlight, builds, submissions, and releases from local agents such as Claude Code, Codex, or Cursor. It requires Node.js 22.12 or later, network access, and App Store Connect API credentials; it does not build or sign apps, and website-only tasks remain outside its scope.

visual-plan helps teams turn a text plan into a self-contained interactive HTML document for collaborative review instead of a wall of terminal Markdown. It supports diagrams, file trees, annotated code and diffs, anchored comments, and open-question decisions; reviewers can print or export PDF and send section-specific feedback back for iteration. No separate build step is required, and the page can be deployed to Cloudflare.

Build a Chokepoint Brief by anchoring demand, mapping a supply chain down to its physical dependencies, testing whether a bottleneck is truly irreplaceable, and listing catalysts and thesis-killers. The method can generalize beyond semiconductors, but it is an unofficial educational reconstruction from public material, not financial advice or a recommendation to buy named companies.

Stock Industry Chain takes a company, ticker, or theme and organizes upstream and downstream companies for Chinese, Hong Kong, or US markets into a shareable HTML map. Clickable nodes open company cards and TradingView charts, while a second view can sort individual stocks by market measures. Claude performs the research and the page builder inlines the resulting JSON, so company relationships, tickers, and market data should be checked independently; the project is not investment advice.

Use Elevate to review a web, macOS, or iOS codebase across performance, functionality, stability, reliability, security, usability, and visual polish. Its bounded report ties recommendations to concrete files and verification steps, then identifies one change to ship first. The skill produces an improvement plan only and does not edit the codebase.

Pear is a hosted MCP integration for Claude Code and OpenClaw that connects to iCloud Calendar, Reminders, Contacts, and Mail. It exposes scheduling, contact lookup, reminder management, and mail operations through natural-language requests, with support for macOS, Linux, and Windows. Setup requires a Pear account, an Apple app-specific password, and an API key; the project says connected data is proxied in real time rather than stored on Pear’s servers.

Run the CLI against a project to detect its stack, match suitable MCP servers from a curated registry, and check pinned versions, package integrity, install hooks, and multiple advisory feeds. It can also validate stored pins offline. The tool is an install-time gate—not a sandbox, runtime monitor, or guarantee that a third-party server is benign.

Recon maps a codebase, hunts for defects and refactoring opportunities with read-only subagents, and sends selected work to implementers in isolated worktrees. Each phase has a human gate; fixes and behavior-preserving optimizations must meet the test baseline and verifier checks before being cherry-picked. Its pentest mode is limited to authorized, non-destructive targets.

certora-prover-skill helps Claude Code write Certora Verification Language specifications for Solidity and EVM contracts, including rules, invariants, ghosts, hooks, and method summaries, then run certoraRun and diagnose counterexamples, vacuity, soundness, and timeouts. It keeps the distinction from testing explicit: a result covers every state allowed by the model, not every behavior omitted from the specification. The skill is an unofficial community package and requires the Certora Prover environment.

Roam turns a natural-language world brief into a single HTML experience that can be explored in the browser. One track builds dependency-free CSS-3D corridors for scroll-through stories; another uses Three.js for first-person rooms with WASD, mouse look, GLB furniture, and tileable textures loaded through an import map. The skill avoids a build step, but the project is an early prototype and the room track still depends on browser-loaded Three.js assets.

AIEngineerCV turns an old CV, LinkedIn export, GitHub profile, or free text into a role-targeted resume for AI-engineering jobs. Its web app, CLI, and Claude plugin all populate one validated Profile before the shared generation rules create, score, and export Markdown, HTML, or PDF. An LLM key is optional: deterministic generation and scoring still work without one. There is no backend or telemetry, and provider calls go directly from the user’s machine without the project storing keys or source data.