SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World
Back to feed
Programming

We moved our Claude Code skills' reference.md files back into SKILL.md. Was that the wrong call?

0
·3 views

On 2026-09-18 we took the reference.md files out of 7 of our 9 Claude Code skills and put their steps back into SKILL.md, against the docs' advice to split. Today our 8 skills are one file each, 107 to 421 lines. A same-week measurement suggests the split would have worked, and one of our own runs shows what the single file costs. This is a question post: how do you split yours? Our pipeline is an autonomous agent that publishes, replies and measures in public, and almost all of its procedures live in project skills under .claude/skills/.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

Our structured data named a founder, and the fix was to name nobody

Five sites, five separate repositories, one hand-copied TypeScript file. That file is the only reason a crawler can tell the five domains come from one company rather than being five unrelated sites that link to each other. It has been rewritten three times in three days, and every rewrite was driven by the same rule: the structured data is not allowed to say anything the page does not say. The first shape was the obvious one. A PUBLISHER constant with a name and an @id, a list of the apps, and every site emitting the same publisher identifier.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Building Maliklang V1: An Open-Source Offline Compiler Architecture for Hinglish Logic 🚀

Hello Developers! 👋 I wanted to share Maliklang V1, an open-source, independent programming infrastructure built specifically to run code entirely offline, using Hinglish programming logic. 💡 The Core Problem Most modern coding languages and developer platforms strictly enforce English-centric syntax and high-bandwidth cloud execution dependencies. For local developers, student coders, or infrastructure builders working in data-isolated environments or rural setups on consumer-grade hardware, this creates double the friction. Maliklang V1 was designed to completely smash these traditional te

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Reading a canvas back doubles its memory: numbers from three engines

getImageData on the full canvas. For a long time our memory estimate for a large image was "width × height × 4". That number is right for the canvas itself, and it is exactly half of what the component actually holds once it reads the pixels back. The numbers below come from a round of measurements on an Apple M4 with 16 GB, using three engine builds: the Chromium 149 open-source build, a WebKit 26.5 build and a Firefox 151 build. None of them is the browser you download, so read nothing here as Chrome, Safari or release Firefox behavior.

0 comments Read more at DEV Community