SKILLS

Adversarial skill files - folders of instructions agents load dynamically - exploit a mainstream enterprise coding agent in 95.5 to 96.1 percent of runs, while the agent recognizes danger 1.99 percent of the time. The skill folder is now a measured attack surface, and the defense is admission engineering, not better prompts.

A GitHub-trending library of Anthropic cybersecurity skills points at the next agent security layer: framework-mapped playbooks that need provenance, tests, and abuse boundaries before they become trusted runtime tools.

The andrej-karpathy-skills repo exploded because every coding agent needs behavioral rails. The useful move is not copying it blindly, but turning the rules into repo-specific operating constraints.

Skills turn a general coding agent into a trained teammate by packaging runbooks, scripts, examples, and domain-specific judgment into reusable instructions.

Commercial underwriters drown in PDF submissions. Here is how to build a Claude Agent SDK triage bot with skills, hooks, and a clean audit trail.

A curated directory of 312 Claude Code skills, plus Pro tools for authors who want analytics, version pinning, and a real submission flow.

Two quality-of-life tools we built this week for Claude Code daily drivers: a SKILL.md linter and a VS Code status bar that shows live LLM spend.

From Claude Opus 4.7 and GPT-5.5 to Andrej-karpathy-skills and EvoMap - the AI dev tools actually shipping the last 30 days, with commands, links, and pricing.

Four Claude-Design-adjacent repos entered the trending week with a combined 8,300+ stars. Huashu-design, open-codesign, awesome-claude-design, cc-design. Here is what is actually happening, and why the pattern matters.

Reusable markdown files with instructions and workflows.

/simplify, /batch, /debug, /fast, and other built-in skills.

Pass arguments to skills with string substitution support.

Hide skills from Claude's auto-selection until manually triggered.

Configure model, tools, MCP, skills, memory, and scoping.

Skills are how you stop copy-pasting the same workflow into Claude Code every session. What they are, how to write one, and where to find hundreds ready to use. Fact-checked against Anthropic's docs.

Claude Code skills can now reflect on sessions, extract corrections, and update themselves with confidence levels. Your agent gets smarter every time you use it.

Skills turn Claude Code sessions into persistent memory. Successes and failures get captured, progressively disclosed, and shared across teams. Your agent remembers.

A comprehensive look at Claude Skills-modular, persistent task modules that shatter AI's memory constraints and enable progressive, composable, code-capable workflows for developers and organizations.