Anthropic Just Revealed 10 NEW Rules for Claude Skills
Anthropic updated its official skill-authoring guide: keep main files under 500 lines, limit references to one level deep, and replace prompt rules with hooks.
October 5thCreator
Anthropic updated its official skill-authoring guide: keep main files under 500 lines, limit references to one level deep, and replace prompt rules with hooks.
October 5thA decision-only model built for picking, not writing, paired with Claude Code across nineteen real automations, from spreadsheet tagging to routing which Claude model handles a prompt.
October 4thA RoboNuggets creator walks through the three-step Claude Sonnet 5.5 workflow he uses to cut, animate, and direct his own videos end to end, with no separate AI video-generation model involved.
October 2ndOne creator maps the gap between a lucky one-shot prompt and a director-grade Claude Code workflow for AI motion graphics.
September 29thA screen-recorded tour of 25 prompts, sites, and Claude Code skills, sorted easy to advanced, for anyone tired of interfaces that scream default AI design.
September 27thHow TypeSafe's System 1 model Jev cuts LLM costs by 70% by handling routing, skill picking, and high-volume classification at 4 cents per million input tokens.
September 21stA creator walks through his own Claude Code command center and the four-layer system underneath it: Skills, Memory, Routines, and Applications.
August 21stAnthropic shipped a Figma-style artboard editor into Claude Code itself, and one identical prompt with real context beat Claude Design's default template every time.
August 19thAnthropic is about to start nudging Claude's word choices into a hidden, detectable pattern. Here's when it starts, who it hits, how the method actually works, and what paraphrasing does to it.
August 17thTwo five-minute configuration changes, a custom output style and an on-demand skill, turn Opus 5's dense jargon and wall-of-text replies into plain, scannable answers.
August 14thA three-line prompt that fans Claude out into paired builder and critic sub-agents until every piece clears a stated quality bar — and the one condition that decides whether it helps or hurts.
August 5thA walkthrough reverse-engineers Higgsfield into a Claude Code skill that calls the same aggregator APIs directly, for cents instead of a monthly fee.
July 31stSame one-shot prompts, two models, three real builds — a website, an app clone, and a 3D game — scored on intelligence, cost, and time, not just vibes.
July 23rdA walkthrough of routing Claude Code through a ChatGPT subscription's GPT-5.6 Sol model, plus a two-model skill that has Claude plan while Sol builds, for roughly a quarter to a half less per task.
July 15thMobbin's new MCP connector lets Claude search 600,000+ real, shipped app screens as design references — trading the generic serif-and-purple-gradient AI look for interfaces grounded in production apps.
July 13thA creator has Claude design a visual second-brain system for his own workspace, then proves it answers questions faster and 40% cheaper than a default session.
July 6thA screen-share tour of five things people are actually doing with Anthropic's newest model, before its free access window closes.
July 2ndA 12-minute screen-recorded tour of Claude Design 2.0 — unified limits, a real editor, markup annotations, MCP connectors, and two-way sync with Claude Code.
June 24thA 14-minute tutorial on the three tiers of self-running Claude Code workflows — and why the creator of Claude Code stopped prompting it manually.
June 12thSix one-shot build tests settle where the Mythos-tier model's 2x cost premium actually pays off.
June 10thAn 8-minute walkthrough of the Hermes Agent desktop app — installation, skills, Telegram setup, cron limits, and a candid verdict against Claude Code and Codex.
June 3rdA 15-minute walkthrough of the free 31-skill plugin that wires Claude into your small business ops stack.
June 2ndAn 11-minute screen-share demo arguing that Dynamic Workflows and UltraCode are the real Opus 4.8 story, and showing what 96 parallel sub-agents actually look like.
May 28thA 26-minute walkthrough of eight purpose-built micro-apps that turn a Claude Code agent setup from a chat window into a visual command center.
May 25th