Recently updated open-source projects

set-the-mood changes a Claude Code session’s tone through three combined behaviors: terse phrasing, vivid plain-language analogies, and one-question-at-a-time interrogation of plans against project context and architecture decisions. It can update CONTEXT.md and offer an ADR as decisions settle, while keeping full explanations for security warnings, irreversible actions, and tricky sequences. The mood starts at the beginning of a chat and stays active until reset.

AI SEO Maxer helps audit and improve a website’s chances of appearing in Google AI Overviews, AI Mode, and assistant citations. Its workflows check indexability, snippet eligibility, content quality, search intent, technical foundations, first-hand value, and agent access, then produce prioritized fixes or citation-oriented rewrites. A separate mythbusting mode tests GEO and AEO advice against Google’s published guidance instead of treating every trend as a required tactic.

This Claude skill guides a six-phase design-system setup: brand decisions, color scales, typography, token integration, Figma Variables, and documentation. It uses Supa Palette, Typescale, Figma MCP, and a Next.js/Tailwind project, with Figma Desktop and local fonts needed for the visual stages. Users still supply the rationale behind their design decisions.

Describe your role and the decision you are facing, and Reading Compass draws on its distilled library across entrepreneurship, product, growth, management, and business to combine multiple perspectives. It adapts takeaways, action items, decision frameworks, and cautions for six reader types and four usage modes. The planned 100-book library is still incomplete, with notable gaps in finance, legal topics, and fundraising.

ATS Resume Builder deconstructs a target job posting, maps its requirements to the candidate's real background, and rewrites bullets with an action, metric, and result structure. Each run produces an ATS-clean resume, a recruiter-readable version, a keyword-gap report, and tailoring notes. The skill follows Canadian conventions such as city-and-province formatting, Canadian English, and omitting photos, birth dates, and marital status, so its guidance is calibrated primarily for that market.

Code-Warden adds verifiable controls around delegated coding work: declared scope, secret and file-size checks, runtime hooks, a Git pre-commit backstop, CI reports, and audit receipts. Teams can adopt the layers independently and use baselines for existing codebases. It is not a sandbox, and Codex exposes fewer hook surfaces than Claude Code.

City Food Guide builds a static bilingual restaurant site from one JSON file and a set of photos. Visitors can filter and search venues, mark visits, browse a map, and generate share cards, while creators can export a PDF and map data or offer email-gated downloads. The result has no backend and can be deployed to common static hosts.

ClaudePowerPointSkill teaches Claude Code a disciplined Windows workflow for building PowerPoint decks through COM automation. It emphasizes backup-before-editing, named shapes, rebuilds instead of patch accumulation, typography budgets, and rendering every change to a PNG before trusting the result. PowerPoint and the powerpoint-mcp server are required; optional image or video generation adds Gemini or Remotion dependencies.

cyberseguranca gives Claude Code a routed Portuguese reference set for threat modeling, compliance, supply-chain security, incident response, and AI or agent risks. It includes operational checklists, response playbooks, and copy-ready templates, with especially concrete guidance for Cloudflare Workers, Supabase, Astro, and related services. The principles can transfer elsewhere, but many examples reflect that assumed stack and business context.

Second Draft revises prose by diagnosing five causes of an AI-like voice: missing stakes, performed emphasis, excessive symmetry, hidden actors, and abstraction. Its four-pass method uses frequency budgets instead of banned-word lists and changes rules by register, so technical references do not receive essay-style edits. Six falsifiable yes-or-no checks keep the revision tied to concrete consequences rather than a self-assigned score.

GHL Claude Skill lets Claude Code operate GoHighLevel through API v2, covering contacts, opportunities, custom fields, tags, lookups, and spreadsheet imports with in-memory deduplication. It handles the service’s browser User-Agent requirement, E.164 phone normalization, padded spreadsheet rows, trusted names, and one opportunity per funnel. Credentials stay in environment variables, and the skill distinguishes API-supported objects from UI-only features.

The TypeScript Narrows combines a Claude skill with an ESLint plugin to promote one consistent approach to type safety, async code, error handling, naming, immutability, and control flow. The skill covers guidance that cannot always be expressed as lint rules, while the plugin enforces the automatable subset in editors and CI. Either artifact can be used alone, but they are designed to complement each other.

s5cmd Skill teaches Claude Code to use s5cmd v2.3.0 for bulk S3-compatible transfers instead of slow command loops. It covers object copy, sync, deletion, streaming, metadata, presigned URLs, and bucket operations, with notes on quoting wildcards and previewing deletions. The reference includes MinIO, R2, and other endpoints, but the s5cmd binary must be installed separately.

mule-headless-dev provides cross-platform scripts for building, deploying, hot-redeploying, restarting, and testing Mule 4 applications on a real standalone runtime without Anypoint Studio. The same scripts can be used as a Claude Code skill or directly from Windows, macOS, and Linux. Mule 4.9+ requires JDK 17 and Maven 3.9+, while enterprise runtime and connector downloads require the appropriate MuleSoft repository credentials in Maven settings.

OpenLog gives each project module an architecture note, a reverse-chronological development log, and a short current-breakpoint file, with an index for all modules. Startup and wrap-up rules keep context compact so a new Claude Code or Codex session can resume without re-exploring the project. The repository notes that Codex should receive a physical copy of the skill because symlink tracking is unreliable.

Add, list, complete, and review reminders through a natural-language command, with records stored in a local JSON file. A SessionStart hook shows overdue, due-today, and upcoming items when Claude Code opens, while completed reminders remain available in history. It uses Bash and Python 3 without external dependencies.

LoopCoding interviews the user and inspects the actual repository, installed skills, agents, connectors, hooks, workflows, and test commands before writing a LOOP.md. That specification defines the goal, machine-checkable done conditions, per-iteration checks, guardrails, escalation rules, and progress memory. A /loop runner or sub-agent then executes it until the checks pass. The approach is most useful when a task needs repeated changes and verification rather than prompt-by-prompt supervision.

Shizheng aggregates CCTV’s Xinwen Lianbo and domestic-news sources into a daily current-affairs brief. It supports date and source selection, full or brief output, local deduplication, configurable limits, and Markdown archiving without sending the full text through the model. It needs Node.js 18+ but no API key; source availability, freshness, and the rights to republish content remain outside the skill’s control.