---
title: "Comment by Skillselion on \"Agentic AI Deep Dive — Memory: How Agents Remember\" | Hashnode"
description: "The onboarding-doc vs SOP analogy for CLAUDE.md vs SKILL.md is the cleanest version of that distinction I have seen. One thing worth adding to the procedural-me"
url: "https://hashnode.com/posts/agentic-ai-deep-dive-memory-how-agents-remember/6a0ca1e488372774117cec88/comment/6a856ad1694713b903d2485f"
---

[Discussion](https://hashnode.com/posts/agentic-ai-deep-dive-memory-how-agents-remember/6a0ca1e488372774117cec88)

Comment [Agentic AI Deep Dive — Memory: How Agents Remember](https://hashnode.com/posts/agentic-ai-deep-dive-memory-how-agents-remember/6a0ca1e488372774117cec88)

[Skillselion](https://hashnode.com/@skillselion)

[Aug 19](https://hashnode.com/posts/agentic-ai-deep-dive-memory-how-agents-remember/6a0ca1e488372774117cec88/comment/6a856ad1694713b903d2485f)

The onboarding-doc vs SOP analogy for CLAUDE.md vs SKILL.md is the cleanest version of that distinction I have seen. One thing worth adding to the procedural-memory section: retrieval for SKILL.md is keyed on the description field, not the body. The agent decides whether to load a skill from that one description alone, so a skill with a great process and a vague description simply never fires. You can watch this at scale by browsing real SKILL.md files sorted by install count (disclosure, I run Skillselion: [skillselion.com/skills](https://skillselion.com/skills?utm_source=hashnode&utm_medium=comment&utm_campaign=sweep-aug-19) ): the heavily-installed ones almost all spend the description on trigger conditions, "use when X", rather than summarizing the body. Which fits your consistency point: procedural memory only makes an agent consistent if the trigger fires reliably.