A Claude Code skill that turns the project you just built into a 20-second launch video, with music, motion and share copy, in 1 command.

Microsoft's open-source method for training agent skills like a neural network, without touching the model: small edits to a skill file, kept only if they score better on held-out tasks.

An open-source Claude Code framework that runs a whole job search: profile, portal search, fit scoring, tailored CV and cover letter, reviewer agent, interview prep and tracking.

How I configure Claude Code for NicAI: layered CLAUDE.md files, hooks, auto-memory, permissions, skills, connectors and the output conventions.

Anthropic's guidance for getting the most out of each Opus release in Claude and Claude Code, newest first: Opus 5.5 (September 2026) and Opus 4.7 (April 2026).

Every skill in my NicAI setup, grouped by purpose, 1 line each, plus what a skill is and the rules I build them by.

A Rust terminal multiplexer built for coding agents. Sessions survive a closed lid, and every pane says whether the agent is working, blocked or idle.

Stream Deck plugin showing live Claude Code token usage with auto-refresh and zero config.

Python CLI that switches Claude Code between several accounts, rotates before rate limits and runs accounts side by side.

Free Stream Deck plugin showing live Claude Code usage, session status and one-press permission approvals.

A portable agent skill that audits and rewrites AI writing tells, now backed by a deterministic detector engine that scores text 0 to 100.

A Claude Code skill that turns one YouTube link into an archival Markdown note with frontmatter, metadata, chapters and full transcript.

Nodes, edges, the fake-edge test and the diamond, from a long-form X post, checked against how Claude Code actually runs agents in parallel.

An open-source AI sales team for Claude Code: research prospects, qualify with BANT + MEDDIC, map buyers, draft outreach, and export PDF pipeline reports.

A reusable NicAI skill that raises any artifact's quality through a make, critique, score loop until a weighted panel of expert agents converges.

How power users moved from prompting to context engineering to writing loops, and the three parts every loop needs.

Claude Code skill that compiles personal data into a Wikipedia-style personal knowledge wiki.

Andrej Karpathy's observations on LLM coding failure modes, codified into four principles. Now shipped as a Claude Code plugin under the Multica org.

Claude Code skill from browser-use that turns raw footage in a folder into final.mp4, using ElevenLabs Scribe for word-level audio timestamps.