Recently updated open-source projects

Connect an owned or authorized iPhone to a Mac and capture decrypted Bluetooth HCI and local Wi-Fi packet streams through libimobiledevice and rvictl. The workflow pairs tshark recipes with a decoder for PTP-IP and selected Sony private opcodes, helping reconstruct device-command timelines without jailbreaking or a hardware sniffer. It cannot break application-layer encryption, decrypt internet TLS payloads, or extract keys from apps or firmware.

lecture-builder combines a knowledge document, question document, and optional solution document into two printable DOCX handouts. The student edition leaves answer space after each problem, while the teacher edition adds answers and explanations. The engine copies source images, Word formulas, and tables at the XML level instead of retyping them, then applies fixed A4 layout, numbering, contents, and page elements. A small configuration file maps knowledge sections to questions; without a solution file, only the student edition is produced.

kapus-secuaudit checks a codebase or an owner-operated URL for dependency risks, exposed secrets, missing RLS or auth, injection paths, unsafe configuration, and deployment mistakes. It returns a 0–100 score plus P0–P3 findings with locations, impact, and concrete fixes. In fix mode, it shows a file-by-file change plan and waits for approval before editing. The skill is deliberately defensive: it avoids exploitation, brute force, denial-of-service, and audits of sites the user does not control.

Add a floating toolbar to a React 18+ prototype so designers, PMs, and stakeholders can switch component alternatives in place. The toolbar highlights the component under each option, keeps selections and layout state in local storage, and shows only versions whose wrapped component is in the viewport. It has no new npm dependencies; the page-side toolbar is local-only by default, while production use relies on the companion extension or an explicit override.

This skill turns saved articles or RSS items into a produced Spotify episode: it writes a segmented script, renders Qwen3-TTS with a reference voice, pads chapter silences, creates cover and description assets, and uploads through the authenticated save-to-spotify CLI. It targets Apple Silicon with Python and ffmpeg, supports scheduled runs, and can optionally publish an R2 web feed.

Curator triages session context before a compressor decides what to shorten or discard. It scores information by recoverability, constraint criticality, and dependency risk, then routes it as pinned, structurally preserved, summarizable, or discardable. Use it to keep prohibitions, exact configuration values, and decision rationale visible across long agent sessions while continuing to use a separate compression tool for lower-risk content.

Build a structured voice profile from your own writing samples, including tone, sentence patterns, formatting habits, and phrases to avoid. ResoNote then scouts topical angles and creates separate drafts for platforms such as X, LinkedIn, Bluesky, Threads, Instagram, TikTok, and Mastodon. Posts remain in a human review queue before publishing, and engagement data can refine the profile; direct publishing may require third-party APIs.

The skill checks line counts in MEMORY.md and oversized files in a custom file-based auto-memory setup, with read-only diagnosis as the default. Trimming or splitting requires explicit approval and includes backup, verification, and audit logging; it is designed mainly for a specific macOS setup, not Claude Code’s built-in memory features.

claude-leandata-skill gives Claude structured guidance for LeanData FlowBuilder routing, account matching, tagging, Audit Log diagnosis, and the differences between real-time and CCIO batch behavior. It can map fallback edges, explain administrator settings, and support certification preparation while grounding field names in a reference set built from official documentation. The skill targets Claude Cowork, and its recommendations still need checking against the organization’s actual configuration and platform version.

introduce-ts inspects an existing JavaScript project to identify its bundler, framework, Babel use, and package manager, then creates a matching tsconfig and adjusts the build setup. It migrates one leaf utility first and runs type checking plus a build as a smoke test before explaining the next steps. The skill deliberately avoids converting every file at once, enabling strict mode immediately, or combining conflicting loaders. Projects already using TypeScript are skipped.

sketch-inspector converts Sketch documents into cleaned JSON, deduplicated image assets, and a LayoutIR describing flex, grid, absolute, or leaf structure. For large designs it splits the result into section files with a manifest, allowing an agent to implement manageable pieces before replacing markers in the main layout. The toolkit is designed for Claude Code, Cursor, and other agents and pairs with the official Sketch MCP server for HTML, CSS, React, or Vue work.

Review organizes a medical course folder by matching the syllabus, teaching calendar, and lecture slides chapter by chapter, then produces exhaustive Markdown and HTML notes with optional Anki cards and a Mermaid map. Numerical values and procedural steps stay verbatim, while missing or conflicting material is marked rather than filled in. Its cross-checking workflow has been used for surgery, preventive medicine, and anesthesiology; the local install needs the listed PDF, Office, and spreadsheet parsers.

This skill calculates sPEG = forward P/E ÷ (growth × Scarcity Multiplier), using five factors to examine irreplaceability, replication time, supply concentration, throughput control, and downstream dependency. It helps analysts interpret sPEG bands; the included Micron example is personal analysis, not investment, tax, legal, or accounting advice.

Give expert-review-panel a paper, business plan, codebase, product document, competition entry, or creative work before it is submitted. The skill runs independent role-based reviews, cross-examination, and a chair verdict, then returns a P0/P1/P2 issue list with location, evidence, reasoning, and a concrete fix direction. It is designed to surface rejection-level problems rather than offer a polite general critique.

youtube-learn turns a YouTube link into structured notes for lectures, podcasts, interviews, and tutorials. It fetches captions with yt-dlp, falls back to Whisper when needed, reads the full transcript, and writes a TL;DR, key takeaways, topic-by-topic explanation, notable quotes, and audience guidance. Tutorials are organized like reference material, and the result is saved as Markdown.

claude-skills-deploy bootstraps a repository with Coolify app configuration, Doppler service tokens, and a GitHub Actions workflow that builds an image once, checks staging, and promotes the same tag to production. Its `validate` and `plan` commands are read-only, while `seed` and provisioning are explicit operations. Using it requires a configured Coolify host, Doppler account, GitHub CLI, SSH access, and local credentials.

magdil-rosh prevents an agent from shipping only the happy path. Before building, it loads the checklist relevant to the request, asks up to three questions at the forks that change the design, and reports what is covered, deferred, or still open. The WalterCare edition adds project-specific checks for its environments, data layer, compliance, and locales; trivial lookups and one-line edits are intentionally skipped.

skill-steward manages a Claude Code skill collection through three layers: a read-only loader that finds the right pack, a coordinator that audits and moves skills, and a synchronizer for cc-switch drift and repairs. Packs are discovered from the filesystem instead of hard-coded domains, and the system uses a small set of Markdown files without external services or databases. It suits installations where a large global skill directory is becoming difficult to navigate.