Recently updated open-source projects

OSS Community Health helps maintainers interpret the human side of an open source project, including contributor retention, onboarding friction, concentrated workload, bus-factor risk, and burnout patterns. It favors multi-week trends and pairs each observation with a concrete next step rather than acting as another metrics dashboard. Discord, Slack, or forum signals are optional and require explicit consent, community notice, and aggregate-only analysis without individual attribution.

Sunset guides an agent through deciding whether a project is truly finished, recording what worked and what ended it, harvesting reusable code or lessons, and archiving the project with a visible marker instead of deleting it silently. It also closes lingering loops so an inactive project stops consuming attention. The archive is designed to be reversible, and the first safeguard is distinguishing a frozen project from one that is genuinely dead.

Immune Check scans an artifact before it enters a public repository, external service, release, or inbox. It looks for API keys, private keys, passwords, cookies, personal or health data, internal hostnames, home paths, build output, and oversized vendored material, selecting an available scanner or falling back to a built-in pattern pass. The skill is stack-agnostic and records which scanner ran, so a release gate can show the depth of its check.

open-source-octopus-investigation starts from a person or topic and follows GitHub stars, follows, followers, and contributions to surface projects that keyword searches may miss. The skill scopes an origin, depth, and call budget, then groups findings into themed tentacles, records visited networks, and keeps unexplored leads for later runs. It can also prepare issue reports. Crawling uses the authenticated gh CLI and GitHub APIs rather than scraping pages.

qld-re-compliance answers Queensland property-sales questions only from structured rule files linked to legislation, approved forms, or regulator guidance. It covers Form 6 appointments, commissions, marketing and pricing, offers, and seller disclosure, labels the authority tier, refuses when no rule applies, and explicitly is not legal advice.

yoyo-huitu-illustrations turns one judgment, process, state, or metaphor from a Chinese article into a 16:9 hand-drawn explainer image. It uses Xiaohei and related characters, black line work, and restrained red, orange, or blue Chinese annotations, choosing one cognitive anchor per image before exporting PNGs. It is for knowledge and methodology content, not commercial key art, slide decks, complex diagrams, or editable vector files.

la-profe creates a language self-study route from the learner’s level, goal, available time, interests, and materials. Setup builds a monthly path and a daily block; review recalculates the next block from progress; adjust makes a smaller change when the current plan is too hard, boring, or time-consuming. Plans are stored as ordinary Markdown files. The skill does not teach lessons, create flashcards, or track attendance, and is grounded in SLA study principles.

enggenie packages 14 role-based skills that move work from a vague request to a specification, phased plan, test-driven implementation, code and design review, evidence-based QA, and PR preparation. The stages leave structured artifacts for handoffs and work across Claude Code, Cursor, Copilot CLI, Gemini CLI, OpenCode, and other skill-compatible assistants.

google-chrome-skill documents macOS workflows for discovering Chrome profiles, editing bookmark JSON safely, controlling tabs and windows with AppleScript, and locating extensions. It also describes cookie extraction for authenticated internal API calls when an MCP lacks the needed action. The skill is macOS-only, and cookie handling should be treated as sensitive because it can expose logged-in browser state.

The skill studies screenshots or live references, asks preference questions, and generates two rounds of browser-ready design probes before compiling a concrete taste specification. That file records colors, typography, spacing, anti-goals, and the reasoning behind the choices. Claude can then use the same specification to build web or mobile interfaces while checking for generic AI-design defaults.

kitty-tab-note places a large colored note over a parked kitty terminal tab so a long-running build, REPL, SSH session, or coding agent has a visible return point. A keybinding opens the note, any key dismisses it, and the existing terminal content and title remain intact; color, position, and size are configurable. The script uses Python’s standard library but requires kitty 0.40 or newer with remote control enabled.

pg-extension-lab gives PostgreSQL extension authors an isolated harness for development, regression testing, benchmarking, and performance experiments. Its references cover C/PGXS and Rust/pgrx extensions, accelerator paths, microservice boundaries, matched-recall benchmarks, and Pareto-style trade-offs so a fast number is not mistaken for a fair result. Reusable templates keep hypotheses and reports tied to raw artifacts, and the package installs as a Claude Code plugin.

Sharecraft starts by clarifying the audience, single takeaway, platform, and desired action before choosing a medium. It can turn one content core into a coordinated slide deck, social card, explainer video, terminal demo, or interactive HTML page, then checks the result against shared design rules. The workflow uses local open-source tools without paid APIs, while heavier video and terminal-recording support is installed only when needed.

Use the Python command-line tools to turn numeric, alphanumeric, or tone-only FLEX pager messages into WAV audio, then decode recordings with automatic mode detection. It supports all four standard FLEX modes, while long capcodes, full fixed-frame timing, and ReFLEX uplink are not implemented.

The skill assigns each request an S, A, B, or C level based on complexity and risk, then scales the planning depth accordingly. For larger jobs it breaks down goals and constraints, audits available agents and tools, evaluates feasibility, and lays out milestones and deliverables before implementation begins. Code is held until the user approves the plan, and the supplied planning template can be adapted to a team's workflow.

news-for-beginners collects recent articles from a user-selected site or feed, organizes them into a narrative for beginners, and writes three artifacts: a source ledger, a standalone HTML news page with topic filtering, and a preview PNG. It runs as an independent Claude Code skill and keeps collection inside the selected site boundary. Network access is needed for the source, and the preview image requires Playwright with Chromium or another real browser renderer.

Breakglass helps Solana teams respond to failed transactions, suspicious drains, authority compromise, RPC degradation, and frontend incidents without rushing into risky actions. It organizes evidence, labels severity and confidence, then routes the case to focused debugging, communication, recovery-planning, or postmortem guidance. The skill never requests keys, submits transactions, moves funds, or changes authorities; humans remain responsible for every on-chain action.

FoFo Council of Personas sends one question to several adversarial roles in parallel, has them peer-rank one another, lets a Devil’s Advocate attack the emerging consensus, and asks a Chairman to synthesize the final call. Seats can use different model lineages and an optional shared web brief, while the project offers both a command-station UI and a headless Claude skill. Running it requires Gemini or compatible model endpoints and their credentials.