jayanaka98
Re:Agent skills should be compiled, not just read
on Monday August 17, 2026 @11:58AM (#49333121)
So true. A lot of skills out there already mix methodology and orchestration together. SIGIL’s AG-IR compilation helps extract the methodology and keep that separation clean.
Re:Agent skills should be compiled, not just read
on Monday August 17, 2026 @11:52AM (#49333021)
Ha ha, true. We already had the solution for compliance years ago with LangGraph, byLLM, etc. I think we went with SKILL.md because of the ease of authoring and use. SKILL.md or AGENT.md is genuinely easier to use, with a low barrier to entry for building custom workflows, though not very compliant. SIGIL seeks to address this dilemma by compiling agent skills.
Re:Show HN: Sigil – compile a SKILL.md the model MUST run, not "might"
on Friday July 24, 2026 @11:37AM (#49037235)
Sigil compiles a plain-markdown skill into a program the model runs inside. It's not a runtime that reads skills, it's a compiler: SKILL.md in, standalone agent harness out.
It's written in Jac (https://www.jaseci.org), that's where the graph runtime, the typed "by llm" slots and the concurrency come from. Docs: https://sigilagent.com. Happy to go deep on the IR design.
Show HN: Sigil – compile a SKILL.md the model MUST run, not "might"
Re:Ford rehires 350 engineers after AI fails to preserve expertise or ...
on Thursday June 25, 2026 @11:28AM (#48674883)
The reason AI fails in Industry is that SKILL.md or other knowledge-injection methods do not guarantee compliance. AI just thinks it "knows better".