The useful distinction is not “more context.” It’s context on demand: Claude sees each…
This is a dev post classified by Jev as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
The useful distinction is not “more context.” It’s context on demand: Claude sees each Skill’s name and description first, then loads deeper instructions when a task matches. Skills are organized folders that package expertise—and they’re portable across Claude Code, the API, and http://claude.ai. At startup, only each Skill’s name and description enter the system prompt, using about 30 to 50 tokens per Skill. When a prompt matches, Claude loads the full SKILL.md. Referenced files and scripts are then progressively loaded or run as needed. That progressive disclosure lets you install many
Posted by catman (1.7k followers) 4 days ago · 4 likes · 227 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: claude.ai.
More dev work like this
- I think we’re looking for this — @vaibcode
- When a hard coding decision needs a second opinion, don’t settle for one model. — @DanKornas
- Banger paper from MIT and Sakana AI. — @dair_ai
- Nautilo agents use memory like memory competition champs. They never forget and they… — @Dan_Jeffries1
- AI agents need guardrails before they reach your tools. — @DanKornas
- 20-30 agents are only useful when you stop babysitting every one of them. — @catmanyau
- Okay, everyone wants us to give the unbiased facts. — @Teknium
- A single RTX 3090 hit 381 tok/s on Qwen3.8-27B. — @0x0SojalSec
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.