Cloudflare has published an MIT-licensed coding-agent skill called security-audit that, according to its repository README surfaced on GitHub Trending, turns a coding agent into a security auditor. The skill runs a six-phase workflow — reconnaissance, coverage-led hunting, candidate validation, structured output, independent record verification and target-neutral reporting — with isolated agents and adversarial validation in which the checker is never the finder. Findings are written to a schema-validated JSON file and checked by zero-dependency Node validators, and Cloudflare says the skill is the single-repo starting point from which its fleet-wide vulnerability discovery harness grew. Installation is via the Skills CLI, and running target code requires a model with tool use and parallel sub-agents plus an OS-enforced sandbox.
The vercel-labs/skills project appeared on GitHub Trending as a command-line tool for what it calls the open agent skills ecosystem, invoked via npx skills. Its documentation says npx skills add can install skills from GitHub shorthand, full GitHub, GitLab or Azure Repos URLs, any git URL or a local path, while npx skills use generates a prompt without installing and can optionally launch a supported coding agent interactively with --agent. The listed targets include OpenCode, Claude Code, Codex and Cursor, and the project claims support for "75 more" agents, a count that comes from the project itself and was not independently verified. The docs also note anonymous usage telemetry that can be disabled with DISABLE_TELEMETRY or DO_NOT_TRACK, and the project is released under the MIT license.
What problem it solves
AI agents need product-specific instructions to use NVIDIA software reliably across physical AI, robotics, simulation, CUDA-X libraries, RAG, and platform workflows. The catalog centralizes these skills while keeping them maintained in their respective product repositories and synchronized through an automated pipeline.
Key features
Agent-discoverable skill catalog — The NVI…
What problem it solves
AI coding agents often take the shortest path, skipping specifications, tests, security reviews, and other practices needed for reliable software. This project packages structured workflows, verification gates, and engineering practices so agents apply the same discipline consistently throughout development.
Key features
Lifecycle commands — Nine slash commands map the devel…
What problem it solves
Coding agents need visual and spoken evidence from videos before they can answer questions about them. Watch transforms a URL or local video into frames, transcripts, and timestamped visual evidence that an agent can inspect.
Key features
Process URLs and local videos — Accept a remote video URL or a local file and turn it into timestamped frames and a transcript for the age…
What problem it solves
AI coding tools need structured design guidance to produce interfaces with coherent visual systems and usable implementation details. This project packages such guidance into self-contained markdown skill folders that can be installed for different agents.
Key features
Landing page design — The landing-page-design skill covers intake questions, page structure, conversion cop…
What problem it solves
LLM responses and technical documents often contain jargon, hedging, fragmented sentences, and unnecessary formatting that can make instructions difficult to understand. This project applies structured writing rules so agents produce clear, direct technical content in either a plain default register or a stricter ASD-STE100-oriented mode.
Key features
Plain and strict writin…