agentleFS
Sign inStart free
VoTruongDanhVoTruongDanh/Skills-Agent/.cursor/skills/explain/SKILL.md

explain

Skill4 starsChanged 33 days agoMITView on GitHub

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.

We split this skill into the rules it gives an agent

13 rules. 0 are common, 6 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 97 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    START: Read .ai-memory.md from project root.

    line 10
  2. Very specific:

    END: Update .ai-memory.md using Memory Compaction Rules with: what was explained, key insights, misconceptions clarified, and follow-ups.

    line 11
  3. Very specific:

    If explaining backend/API logic → read .kiro/skills/agents/agents/backend-specialist.md and apply its knowledge

    line 17
  4. Very specific:

    If explaining UI/component behavior → read .kiro/skills/agents/agents/frontend-specialist.md and apply its knowledge

    line 18
  5. Very specific:

    If explaining database schema/queries → read .kiro/skills/agents/agents/database-architect.md and apply its knowledge

    line 19
  6. Very specific:

    If explaining security mechanisms → read .kiro/skills/agents/agents/security-auditor.md and apply its knowledge

    line 20
  7. Very specific:

    Default → read .kiro/skills/agents/agents/documentation-writer.md for clear, structured explanation

    line 21
  8. Distinctive:

    If any answer is unclear, ASK before proceeding.

    line 28
  9. Distinctive:

    Read the target code thoroughly — understand intent, not just syntax.

    line 32
  10. Distinctive:

    Use analogies or diagrams if the concept is complex.

    line 39
  11. Distinctive:

    If the code is unclear or has issues, mention them without derailing the explanation.

    line 66
  12. Distinctive:

    Avoid proposing wide changes mid-explanation.

    line 67
  13. Distinctive:

    Always read and update the memory file.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 97 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

  1. Which file, function, or code block should be explained?
  2. What level of detail? (high-level overview vs line-by-line walkthrough)
  3. What is the user's familiarity level with this area? If any answer is unclear, ASK before proceeding.

Workflow

  1. Read Memory — Load .ai-memory.md for project context, tech stack, and architecture.
  2. Read the target code thoroughly — understand intent, not just syntax.
  3. Identify the explanation scope: single function, module, data flow, or architecture.
  4. 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.
  5. Highlight non-obvious logic, hidden side effects, and design trade-offs.
  6. Use analogies or diagrams if the concept is complex.
  7. Suggest follow-up topics if relevant (e.g., "you may also want to understand X").
  8. Quality Gate — Read .kiro/skills/_scripts/checklist.md for cross-cutting checks.
  9. 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

  • Target code identified and read
  • Explanation level matches user need
  • Logic explained clearly, not just syntax described
  • Non-obvious details highlighted
  • Design decisions explained
  • Follow-up suggestions provided
  • Memory file updated
  • Clean code chuẩn (Standard clean code applied)
  • Cập nhật đầy đủ tất cả các file liên quan (All related files fully updated)

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free