Recently updated open-source projects

Provide an image path and a natural-language target, and the skill iteratively crops and rechecks the region before returning a bounding box, center point, confidence, and saved evidence. It can report that no target was found instead of inventing a coordinate; screenshot capture and UI interaction remain the caller’s responsibility.

The skill starts from the git diff, detects the project's test framework and configuration, and reads existing tests to learn naming, fixtures, assertions, and file placement. It then adds coverage for happy paths, errors, boundaries, and authorization failures before running the suite. It does not assume a stack and needs no API credentials.

Vision Roadmap reads the codebase and documentation, asks structured questions about horizon, priorities, and constraints, then groups the product direction into a narrative roadmap. It can also create matching Linear issues through the GraphQL API. Teams without a Linear key can skip ticket creation and keep the roadmap document only.

Claude Sync tracks installed skills and commands on each machine, including versions and content hashes, then uses pull, push, status, and consolidation workflows to surface drift. It also provides a Git-backed message file for machine-to-machine coordination. MCP configuration, plugin installation, and automatic conflict resolution remain outside its current scope.

From any project folder, you can draft a single post, thread, reply, or image attachment in natural language. Claude shows the exact text and character count, asks for confirmation, then posts through the X API and returns the URL. Credentials live once in a global user file rather than each repository, and dry-run mode previews the payload without sending it.

The skill categorizes dated sessions, release notes, audits, and demo runs, then merges them into typed archive files and a smaller memory index. It leaves feedback, reusable references, user profiles, and active knowledge alone by default. Before writing or deleting anything, it presents a plan for confirmation and removes only true duplicates.

Clicks lets an agent record a signed task receipt after work is completed and look up another agent's reputation before delegating to it. The records are tied to ERC-8004 identities on Base. Using it requires a minted agentId, an agent wallet with a small amount of ETH for gas, and a private-key environment variable.

Use this Codex skill to inspect component APIs and real repository usage, then create or update Storybook stories, documentation pages, controls, and interaction scenarios for React, Vue, or Svelte. It can limit maintenance to components affected by a git diff, scaffold preview decorators from app providers, and audit Storybook coverage across a repository. The project is deliberately focused on Storybook work rather than general frontend design.

Name a fictional character and the skill researches available information, builds a reusable persona, and conducts dialogue in that character's voice with visible source-quality indicators. Personas can be cached for 90 days, responses can follow the user's language, and pause, resume, status, and exit commands keep the session controllable. Built-in safeguards address harmful character requests.

This methodology begins with tangible ideas such as sand, silicon, switches, and binary, then builds step by step toward the internet and AI. Its six-stage arc—Ground, Build, Participate, Reframe, Mirror, and Connect—is designed for learners with little technical experience or understandable distrust of institutions. The repository includes a Claude skill, DOL framework mapping, evaluation materials, and nonpartisan guardrails for civic education.

Enter a GitHub username to turn public repositories, languages, commit patterns, and README details into a shareable satire piece in one of several tech-persona parody styles. Roaster Kit works as a Claude skill, slash command, or standalone CLI and supports multiple output formats. Its rules restrict material to public data, prohibit identity-based jokes, and soften third-party or learner roasts when consent is absent.

Trigger a brief reflective mode when an answer seems technically correct but misses the larger point. Phrases such as “zoom out” or “what am I missing?” prompt Claude to examine the whole situation, which can help with strategic decisions, stuck thinking, and pre-commit plan reviews. It works as a Claude Code skill or as copied instructions for another LLM.

Scan common storage consumers such as AI coding tools, package-manager caches, Docker, Xcode data, browser test runtimes, and macOS app containers. Findings are labeled SAFE, ASK, or KEEP before you choose a conservative, aggressive, or custom cleanup plan, followed by a before-and-after disk-space report.

Define the use case, budget, country, and constraints before mapping the market, shortlisting candidates, searching for recurring owner-reported defects, and testing the recommendation for bias. The final verdict is explicitly scoped rather than naming a universal winner. It depends on web research and works best with the suggested search and X-access command-line tools.

Book Compiler turns a topic, reading list, or source collection into a local Markdown book through research, outlining, drafting, review, and assembly stages that can be paused and resumed. Chapters label book summaries, web material, and AI-generated passages, while locale profiles adapt terminology. Outline-only, single-chapter, self-review, and public-domain modes provide useful control, and the prompt-based skill can run across several LLM environments.

Scan AI-generated text or code across factual integrity, confidence, logic, code reliability, and high-risk domains, then return a trust score with categorized concerns. It is useful for identifying what needs verification, but it is not a substitute for checking original sources.

Personal Intelligence Skill guides you through combining direct RSS feeds and Google News queries into a focused daily feed, then filtering, scoring, deduplicating, and archiving the results. The reference architecture runs on GitHub Actions and publishes a static site to Cloudflare Pages, with optional OpenAI TTS audio briefs. It suits people who want direct control over sources and relevance without maintaining a backend.

Build day-by-day itineraries, track a trip budget, generate climate- and activity-aware packing lists, and consult bundled phrase, culture, and scam references. The supporting Python scripts run offline with no third-party dependencies and keep trip data local, while the conversational workflow requires Claude Code.