docs(skills): improve skill loading process diagram clarity (#81)

Split the "Skill" participant into two distinct entities to better
illustrate the three-level loading architecture:
- Skill Instructions (Level 2): SKILL.md body
- Skill Resources (Level 3): Bundled files (templates, scripts, etc.)

Also fixed inaccurate "bash: read" notation - Claude uses the Read
tool, not bash commands.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
lzw-git-all
2026-04-25 13:37:59 +08:00
committed by GitHub
parent c5f1c75def
commit 8e1f60f47e
+8 -7
View File
@@ -66,19 +66,20 @@ This means you can install many Skills without context penalty—Claude only kno
```mermaid
sequenceDiagram
participant User
participant Claude as Claude
participant System as System
participant Skill as Skill
participant Claude
participant System
participant SkillInst as Skill Instructions
participant SkillRes as Skill Resources
User->>Claude: "Review this code for security issues"
Claude->>System: Check available skills (metadata)
System-->>Claude: Skill descriptions loaded at startup
Claude->>Claude: Match request to skill description
Claude->>Skill: bash: read code-review/SKILL.md
Skill-->>Claude: Instructions loaded into context
Claude->>SkillInst: Read code-review/SKILL.md
SkillInst-->>Claude: Level 2: Instructions loaded
Claude->>Claude: Determine: Need templates?
Claude->>Skill: bash: read templates/checklist.md
Skill-->>Claude: Template loaded
Claude->>SkillRes: Read templates/checklist.md
SkillRes-->>Claude: Level 3: Template loaded
Claude->>Claude: Execute skill instructions
Claude->>User: Comprehensive code review
```