Aria Research Kit (ARK) skills for building applications with Project Aria smart glasses. Covers data processing (VRS, MPS, calibration) and real-time webapp development (WebSocket streaming, 3D visualization, voice pipeline).
★not rated 14 7d agoA
tokens not measured
originalApache-2.0
skraft SDLC pipeline — agents, skills and instructions for outside-in TDD, Clean Architecture and the RESEARCH→DESIGN→DISTILL→DELIVER engineering pipeline.
Zero-to-hero VoiceLink ↔ Dograh telephony integration. Drops the proven, non-breaking VoiceLink provider overlay onto any stock Dograh (source checkout or Docker image), wires the single inbound+outbound WSS URL, configures the telephony card, and verifies the whole thing end-to-end.
★not rated 14 1mo agoA
tokens not measured
originalMIT
Give Claude access to Elsevier APIs (Scopus, ScienceDirect, and more). Search scholarly literature, retrieve abstracts and full-text articles, look up journals, authors, citations, and altmetrics.
★not rated 14 5mo agoA
tokens not measured
originalMIT
Your UI, on its showreel — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and before/after composites in one command each. Self-contained Chromium motor, deterministic placement, self-validated output; no MCP, cheap on tokens.
★not rated 14
changed 1mo agoA
tokens not measured
originalMIT
Comprehensive AutoCAD .NET API reference, patterns, and gotchas for plugin development. Covers AutoCAD 2025 and 2026 (both net8.0) with full API index auto-generated from official SDK documentation.
★not rated 14 7mo agoA
tokens not measured
originalMIT
Drive CarSim 2024 from Claude Code: edit parameters, run the headless solver, and run CarSim MATLAB/Simulink co-simulation (.m and .slx). MATLAB execution is delegated to the official MATLAB MCP.
Make AI-drafted text read like a person wrote it, for the channel it ships in. De-AI pass, channel fit, voice profiles, and a two-gate audit before delivery.
★not rated 14
changed 2mo agoA
tokens not measured
originalMIT
Comprehensive security scanner for codebases — finds hardcoded secrets, injection flaws, auth issues, misconfigurations, AI-specific vulnerabilities, and more. Covers OWASP Top 10, Mobile Top 10, and LLM Top 10.
★not rated 14 7mo agoA
tokens not measured
originalMIT
A shipping pipeline for Claude Code: orchestrate a locked plan or a list of fixes with fresh-context agents or Orca/herdr/cmux worker panes, polish and explain the diff, ship it to a plain-language PR, run an incremental agent review-fix loop until clean, and clean up after merge.
Multi-provider AI media skills. Image, video, and edit generation across Google (Nano Banana Pro / Gemini 3 Pro Image, Veo 3.1), OpenAI (GPT Image 2.6 Sunburst default for finals / Flare for drafts), and xAI (Grok Imagine 2.0 image + grok-imagine-video-1.5), with capability-aware auto-pick and a /gemskills:setup…
★not rated 14
changed yesterdayA
tokens not measured
Status-line indicator showing whether the headroom MCP context-compression is being used this session — idle until headroomcompress runs, then active with the tokens AND money it saved (priced against the session model), decaying back to idle after a quiet period. Tracks an all-time money-saved total across sessions.
★not rated 14
changed 1mo agoA
tokens not measured
Read Claude's replies aloud — free system voices out of the box, premium voices (Speechify, ElevenLabs, OpenAI) with your own API key. Chunked playback starts speaking in seconds, even on long replies.
★not rated 14▲
+1 1mo agoA
tokens not measured
originalMIT