| name | explain |
| description | Explain code, walk through logic, and help understand architecture or behavior. Use when the user asks what code does, how something works, or wants a walkthrough. Triggers: explain, what does this do, how does this work, giải thích, giải thích code, code này làm gì. |
| encoding | UTF-8 |
| agents | ["documentation-writer","backend-specialist","frontend-specialist"] |
| related-skills | ["debug","enhance","status"] |
Memory Protocol
START: Read .ai-memory.md from project root. Check tech stack, architecture notes, past explanations, and domain context.
END: Update .ai-memory.md using Memory Compaction Rules with: what was explained, key insights, misconceptions clarified, and follow-ups.
Goal
Help the user deeply understand code, logic, architecture, or behavior — at the level of detail they need.
Agent Routing
- If explaining backend/API logic → read
.kiro/skills/agents/agents/backend-specialist.md and apply its knowledge
- If explaining UI/component behavior → read
.kiro/skills/agents/agents/frontend-specialist.md and apply its knowledge
- If explaining database schema/queries → read
.kiro/skills/agents/agents/database-architect.md and apply its knowledge
- If explaining security mechanisms → read
.kiro/skills/agents/agents/security-auditor.md and apply its knowledge
- Default → read
.kiro/skills/agents/agents/documentation-writer.md for clear, structured explanation
Socratic Gate
Before explaining, verify:
- Which file, function, or code block should be explained?
- What level of detail? (high-level overview vs line-by-line walkthrough)
- What is the user's familiarity level with this area?
If any answer is unclear, ASK before proceeding.
Workflow
- Read Memory — Load
.ai-memory.md for project context, tech stack, and architecture.
- Read the target code thoroughly — understand intent, not just syntax.
- Identify the explanation scope: single function, module, data flow, or architecture.
- Explain at the requested level:
- High-level: Purpose, inputs/outputs, how it fits in the system.
- Detailed: Step-by-step logic, control flow, edge cases, design decisions.
- Line-by-line: What each line does and why.
- Highlight non-obvious logic, hidden side effects, and design trade-offs.
- Use analogies or diagrams if the concept is complex.
- Suggest follow-up topics if relevant (e.g., "you may also want to understand X").
- Quality Gate — Read
.kiro/skills/_scripts/checklist.md for cross-cutting checks.
- Update Memory — Save explanation context and insights to
.ai-memory.md.
Output format
- What it does: One-sentence summary
- How it works: Step-by-step explanation at the requested level
- Key design decisions: Why it was built this way
- Non-obvious details: Edge cases, side effects, gotchas
- Related context: Connected files/modules worth understanding
Checklist
Rules
- Explain the WHY, not just the WHAT — developers can read syntax themselves.
- Match explanation depth to the user's familiarity level.
- If the code is unclear or has issues, mention them without derailing the explanation.
- Avoid proposing wide changes mid-explanation; if improvement requires broader edits, ASK before switching to implementation.
- Always read and update the memory file.
- Code encoding: All code snippets and files referenced or produced must be UTF-8 encoded. When providing example files, ensure they use UTF-8 and indicate
encoding: "UTF-8" in front-matter where applicable.
Related Skills
/debug → read .kiro/skills/debug/SKILL.md — If explanation reveals bugs/enhance → read .kiro/skills/enhance/SKILL.md — If explanation reveals improvement opportunities/status → read .kiro/skills/status/SKILL.md — For project-wide understanding
