# Developer-Experience

- [Scaling Claude Code Skills Across an Engineering Org](https://sdd.sh/2026/04/scaling-claude-code-skills-across-an-engineering-org.md): You gave Claude Code to 40 engineers. Now everyone's writing their own prompts, their own workflows, their own shortcuts. Here's how one team turned that chaos into a shared skill marketplace — and what they learned building it.
- [Claude Code /powerup and /insights: Fixing the 80% Problem](https://sdd.sh/2026/04/claude-code-/powerup-and-/insights-fixing-the-80-problem.md): Most developers use a fraction of what Claude Code can do. Two new commands shipped in v2.1.90 — /powerup and /insights — attack this problem from opposite ends: one teaches you what's possible, the other shows you where your actual workflow breaks down.
- [Parallel AI Agents: The Tools That Let You Run Ten Claudes at Once](https://sdd.sh/2026/03/parallel-ai-agents-the-tools-that-let-you-run-ten-claudes-at-once.md): One Claude Code session is powerful. Ten running in parallel is a different paradigm entirely. Here's the emerging ecosystem of multiplexers, orchestrators, and dashboards — and how to pick the right one.
- [Your AI Agent Is Drowning in Tokens — Here's How to Fix It](https://sdd.sh/2026/03/your-ai-agent-is-drowning-in-tokens-heres-how-to-fix-it.md): A single `cargo test` can dump 4,800 tokens into your context window when only 11 matter. Multiply that across an agentic session and you're paying for noise that actively degrades your agent's reasoning. The fix exists — and it's not a bigger context window.
- [Claude Code March 2026: Voice Mode Isn't the Story](https://sdd.sh/2026/03/claude-code-march-2026-voice-mode-isnt-the-story.md): Voice mode grabbed the headlines. The 64k default output tokens, /loop, MCP elicitation, and --channels are the updates that will actually change how you use Claude Code day to day.