What are Claude Skills?
— Akshay ๐ (@akshay_pachaar) 29 mars 2026
๐๐๐๐จ๐๐.๐บ๐ฑ was never meant to hold entire workflows.
But that's exactly where they end up. General rules, coding conventions, 20-step security review processes, deployment checklists. All in one file that loads into every single session, eatingโฆ https://t.co/fCLQezp4lG pic.twitter.com/VPLfFEYrTR
What are Claude Skills? ๐๐๐๐จ๐๐.๐บ๐ฑ was never meant to hold entire workflows. But that's exactly where they end up. General rules, coding conventions, 20-step security review processes, deployment checklists. All in one file that loads into every single session, eating context even when Claude is just renaming a variable. ๐ฆ๐ธ๐ถ๐น๐น๐ fix this by turning workflows into self-contained packages that Claude loads only when the task demands it. Here's the idea. A skill is a folder inside .๐ฐ๐น๐ฎ๐๐ฑ๐ฒ/๐๐ธ๐ถ๐น๐น๐/. Each folder contains a ๐ฆ๐๐๐๐.๐บ๐ฑ file with two things: a ๐ฑ๐ฒ๐๐ฐ๐ฟ๐ถ๐ฝ๐๐ถ๐ผ๐ป that tells Claude when to activate it, and the workflow instructions that tell Claude what to do. The description is the trigger. Claude reads all available skill descriptions, watches the conversation, and when your request matches, it pulls in that skill automatically. You don't paste the steps. You don't type a command. Claude recognizes the intent and invokes the right skill on its own. You can also trigger any skill explicitly with a slash command like /๐๐ฒ๐ฐ๐๐ฟ๐ถ๐๐-๐ฟ๐ฒ๐๐ถ๐ฒ๐ when you want manual control. I recorded a deep dive on skills when they were first released, and everything in it is even more relevant today. The video below walks through exactly how this works. But auto-invocation is just the surface. The real power is what skills can carry with them. Skills are full packages, not just instruction files. A ๐ฆ๐๐๐๐.๐บ๐ฑ can reference supporting files that live right next to it using the @ symbol. A detailed security standards document. A release notes template. A compliance checklist. Whatever the workflow needs, the skill bundles it together. Inside ๐ฆ๐๐๐๐.๐บ๐ฑ, YAML frontmatter defines the name, description, and which tools the skill is allowed to use. The ๐ฎ๐น๐น๐ผ๐๐ฒ๐ฑ-๐๐ผ๐ผ๐น๐ field is worth paying attention to. A security review skill only needs ๐ฅ๐ฒ๐ฎ๐ฑ, ๐๐ฟ๐ฒ๐ฝ, and ๐๐น๐ผ๐ฏ. It has no business writing files. Restricting tool access makes the skill safer and far more predictable. Skills live at two levels. Project skills go in .๐ฐ๐น๐ฎ๐๐ฑ๐ฒ/๐๐ธ๐ถ๐น๐น๐/ and get committed to git so the whole team shares them. Personal skills go in ~/.๐ฐ๐น๐ฎ๐๐ฑ๐ฒ/๐๐ธ๐ถ๐น๐น๐/ and follow you across every project. A ๐๐๐๐จ๐๐.๐บ๐ฑ with a 20-step security process baked in is dead weight in 90% of your sessions. A ๐๐ฒ๐ฐ๐๐ฟ๐ถ๐๐-๐ฟ๐ฒ๐๐ถ๐ฒ๐ skill that activates only when security is on the table is precision. ๐๐๐๐จ๐๐.๐บ๐ฑ tells Claude what rules to follow. Skills tell Claude what workflows to execute. The article below is a complete guide to ๐๐๐๐จ๐๐.๐บ๐ฑ, hooks, skills, agents, and permissions, and how to set them up properly. Akshay ๐ (@akshay_pachaar) x.com/i/article/203496196714โฆ โ https://nitter.net/akshay_pachaar/status/2035341800739877091#m
โ View original post on X โ @akshay_pachaar, 2026-03-29 10:13 UTC
