Recently updated open-source projects

superhacker-skill accepts one security objective and routes it to exactly one of 14 focused reference areas, ranging from web and API security to cloud, identity, incident response, forensics, and passive clue discovery. Only the selected guide is loaded, keeping the working context narrow instead of dumping every technique at once. The authorization gate is mandatory: use is limited to systems you own or explicitly have permission to test.

Claude Code Doctor inspects the workspace layer that shapes every session, including context files, permissions, skills, MCP tools, automations, and disk usage. It produces a graded Markdown report and local HTML dashboard with red flags and concrete prescriptions. The diagnostic pass is read-only apart from the approved report destination, and cleanup actions are separated behind explicit user approval.

de-slop detects common machine-written patterns, separates fixable wording from passages that lack a real claim, and rewrites only the former under strict fidelity rules. It self-scores and iterates for a limited number of passes, then returns the revised text with change notes and unresolved flags. Hollow passages are surfaced rather than filled with fabricated opinions.

Shopify Custom App Builder focuses on single-store custom apps running on Cloudflare Workers. It guides credential setup, storage choices, App Proxy and webhook signature verification, merge-on-write synchronization, and secret-safe packaging. The scope is intentionally narrow: examples assume Workers and custom apps, while Node, Deno, and multi-store App Store development are outside the primary focus.

This Claude Code skill collects references in three sequential layers—UX patterns, visual direction, and mood—and fills a Figma Design file with screenshots, sources, and links as it runs. Claude in Chrome MCP is required; Figma MCP is optional for automatic board creation. It suits designers who want live examples to shape a new project's direction, but it is a reference-discovery workflow rather than a design generator.

Use /tldr to turn a meaningful conversation into a tagged session note and update a shared index. The companion session-recall skill watches for natural-language reminders that a topic has come back, then surfaces the matching note without another search command. Both skills use the same sessions directory, index, and optional tag registry.

Localization Editor is a macOS application for managing Localizable.strings files used by iOS and macOS projects. Open a localization folder and it detects the languages, sorts entries by key, displays translations side by side, and highlights missing values; edits are written back to the corresponding files. It can be installed with Homebrew or from release archives, although manually downloaded builds use a development certificate and may require opening them through the context menu.

Fable Prompt Skill turns a rough intention into a prompt tailored to Claude Fable 5. It asks a few focused questions, assembles the answer from Fable-specific patterns, and recommends an effort level for running it. The repository is a skill and pattern library rather than an application, so the result is a prompt you can paste into the intended model.

doc-generator lets Claude collect the required fields, confirm them, and pass a JSON payload to a local deterministic renderer. It currently supports purchase orders, invoices, requests for quotation, and test request forms, with validation and computed totals handled outside the model. Local Python setup is required, and WeasyPrint may need Pango system libraries on macOS or Linux.

This skill scaffolds an Apache-2.0 project with a license, ignore rules, README, CI, repository topics, an initial commit, and GitHub and Codeberg remotes. It can push to both hosts and follows preset CryptoJones and Nebraska conventions, so users should check those project-specific defaults before running it.

SSCI Academic Writing Skill supports English social-science papers from topic and journal selection through the introduction, literature review, methods, results, and pre-submission checks. It combines structural guidance, reusable sentence patterns, method-specific reporting conventions, and a checklist for common desk-rejection problems. It is aimed at graduate students, early-career researchers, and mentors working across management, finance, education, psychology, and related fields.

This Claude skill installs a self-contained DebugPicker.tsx component into React projects and mounts it according to Vite, Next.js, TanStack Start, or Remix conventions. A floating button or Alt+D enables hover and click inspection, producing a DEBUG PICK block with the URL, element, component, CSS path, dimensions, attributes, text, and props.

Untether bridges coding agents running on your own computer or server to a Telegram bot. From a phone, you can send text or voice tasks, stream progress, switch projects and sessions, transfer files, and respond when an agent needs input. It supports Claude Code, Codex, OpenCode, Pi, Gemini CLI, and Amp, but approval controls, plan mode, and cost reporting vary by engine.

Pre-Prod Readiness Check detects a project’s stack and fans out read-only checks across 17 production-readiness categories, including authentication, billing, external requests, secrets, databases, AI safety, performance, compliance, and release operations. It merges duplicate findings and re-checks Critical and High items against their cited locations before producing a severity-grouped report. Mechanical fixes are drafted one at a time and require approval before application.

Cost & Margin Analysis inventories paid APIs, SDKs, scrapers, hosting, storage, messaging, payments, and other recurring surfaces in a codebase, then attaches rates from repository data, saved snapshots, or provider pages after permission to fetch. It models average, minimum-payment high-cost, and legitimate power-user scenarios per plan and feature, including payment fees. The scope is variable run cost and margin, not one-time build costs or formal finance and tax work.

This skill runs a deliberately short Socratic conversation: an opener, exactly three substantive exchanges, and a hard ending with no follow-up prompt. It saves the full dialogue as a timestamped Markdown file, asks once for the speaker label and destination folder, and aims for concrete inquiry rather than debate or tidy conclusions.

Rehelios Video Skill guides a developer or coding agent through uploading or importing a video, waiting for processing, reading its playback URL, and embedding an adaptive HLS or DASH player. It covers public playback, signed tokens, domain allowlists, captions, and the REST API, CLI, or MCP paths. Rehelios charges by stored and delivered gigabytes.

resume-radar simulates an LLM resume screener with a reverse-engineered 120-point rubric, including a GitHub open-source classification that can affect the score. It returns a gap table sorted by point swing and concrete edits, while refusing to fabricate experience, pull requests, stars, or metrics. Use it to understand machine-screening signals, not to inflate a candidate’s record.