From aradotso-trending-skills-37
Transforms AI-generated code into structured Markdown learning guides explaining what code does, why it was written that way, and what alternatives exist. Useful for developers who want to understand and learn from code instead of blindly copying it.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aradotso-trending-skills-37:antivibe-code-learningThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```markdown
---
name: antivibe-code-learning
description: Transform AI-generated code into educational deep dives with AntiVibe, a Claude Code skill that explains what code does, why it was written that way, and how to learn from it.
triggers:
- "deep dive into this code"
- "explain what AI wrote"
- "learn from this code"
- "understand what AI wrote"
- "generate a learning guide"
- "antivibe this code"
- "explain the design decisions here"
- "turn this into a learning resource"
---
# AntiVibe Code Learning
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
AntiVibe is a Claude Code skill that fights vibe-coding by turning AI-generated code into structured, educational deep dives. Instead of copy-pasting code you don't understand, AntiVibe generates Markdown learning guides explaining **what** code does, **why** it was written that way, **when** to use these patterns, and **what alternatives** exist.
---
## Installation
```bash
# Clone and install as a global Claude Code skill
git clone https://github.com/mohi-devhub/antivibe.git
cp -r antivibe ~/.claude/skills/antivibe
For project-scoped installation:
cp -r antivibe .claude/skills/antivibe
To enable auto-trigger hooks (automatic deep dives after task completion):
cp antivibe/hooks/hooks.json .claude/hooks.json
antivibe/
├── SKILL.md # Main skill definition
├── hooks/
│ └── hooks.json # SubagentStop / Stop hooks
├── scripts/
│ ├── capture-phase.sh # Detect implementation phases
│ ├── analyze-code.sh # Parse code structure
│ ├── find-resources.sh # Find external resources
│ └── generate-deep-dive.sh # Generate markdown output
├── agents/
│ └── explainer.md # Subagent for detailed analysis
├── templates/
│ └── deep-dive.md # Output template
└── reference/
├── language-patterns.md # Framework-specific patterns
└── resource-curation.md # Curated learning resources
AntiVibe responds to natural language triggers inside Claude Code sessions:
| Trigger | Action |
|---|---|
/antivibe | Start an interactive deep dive |
"deep dive" | Analyze recently written code |
"learn from this code" | Generate a full learning guide |
"explain what AI wrote" | Explain specific files |
"understand what AI wrote" | Focus on design decisions |
Output is saved to:
deep-dive/<topic>-<date>.md
After triggering a deep dive on an auth system, AntiVibe generates:
# Deep Dive: Authentication System
## Overview
This auth system uses JWT tokens with refresh token rotation...
## Code Walkthrough
### auth/service.ts
- **Purpose**: Token generation and validation
- **Key Components**:
- `generateTokens()`: Creates access/refresh token pair
- `verifyToken()`: Validates JWT signatures against secret
## Concepts Explained
### JWT (JSON Web Tokens)
- **What**: Stateless, signed tokens encoding user claims
- **Why**: Server avoids session storage; tokens are self-contained
- **When**: APIs, SPAs, microservices needing stateless auth
- **Alternatives**: Sessions + cookies, Paseto tokens, opaque tokens
## Learning Resources
- [JWT.io](https://jwt.io) — Interactive decoder and official docs
- [Auth0 Best Practices](https://auth0.com/blog) — Real-world patterns
## Next Steps
1. Study refresh token rotation to prevent reuse attacks
2. Read OWASP JWT Security Cheat Sheet
3. Explore token revocation strategies
Edit scripts/generate-deep-dive.sh:
#!/usr/bin/env bash
OUTPUT_DIR="learning-notes" # Default is "deep-dive"
DATE=$(date +%Y-%m-%d)
TOPIC="${1:-general}"
mkdir -p "$OUTPUT_DIR"
OUTPUT_FILE="$OUTPUT_DIR/${TOPIC}-${DATE}.md"
# Render the deep-dive template with analyzed content
cat > "$OUTPUT_FILE" << EOF
# Deep Dive: $TOPIC
...
EOF
echo "Saved to: $OUTPUT_FILE"
hooks/hooks.json wires AntiVibe into Claude Code's event system:
{
"hooks": [
{
"event": "SubagentStop",
"command": "bash ~/.claude/skills/antivibe/scripts/capture-phase.sh"
},
{
"event": "Stop",
"command": "bash ~/.claude/skills/antivibe/scripts/generate-deep-dive.sh session-summary"
}
]
}
capture-phase.shDetects which implementation phase just completed (e.g., "auth", "database", "API layer") and tags the context for the final deep dive.
#!/usr/bin/env bash
# Reads recent git diff or file changes to detect phase
CHANGED_FILES=$(git diff --name-only HEAD~1 HEAD 2>/dev/null || echo "")
echo "Phase context: $CHANGED_FILES" >> /tmp/antivibe-phase.log
analyze-code.shParses code structure — functions, classes, imports — and feeds them to the explainer agent.
#!/usr/bin/env bash
TARGET="${1:-.}"
# List all source files modified recently
find "$TARGET" -name "*.ts" -o -name "*.py" -o -name "*.go" \
| xargs grep -l "export\|def \|func " 2>/dev/null
find-resources.shMaps detected concepts (JWT, React hooks, goroutines, etc.) to curated resources in reference/resource-curation.md.
#!/usr/bin/env bash
CONCEPT="$1"
grep -A 3 "### $CONCEPT" \
~/.claude/skills/antivibe/reference/resource-curation.md
Edit reference/language-patterns.md to add framework-specific explanations:
## Go
### Goroutines
- **Pattern**: `go func() { ... }()`
- **Why**: Lightweight concurrency without OS threads
- **Gotchas**: Always handle done channels to avoid leaks
- **Resources**: [Go Tour Concurrency](https://tour.golang.org/concurrency/1)
### Error Wrapping
- **Pattern**: `fmt.Errorf("context: %w", err)`
- **Why**: Preserves error chain for `errors.Is` / `errors.As`
Edit reference/resource-curation.md:
## Authentication
### JWT
- [jwt.io](https://jwt.io) — Decoder + library list
- [OWASP JWT Cheat Sheet](https://cheatsheetseries.owasp.org) — Security patterns
### OAuth2
- [OAuth2 Simplified](https://aaronparecki.com/oauth-2-simplified/) — Plain-language guide
Edit templates/deep-dive.md to match your team's style:
# Deep Dive: {{TOPIC}}
Generated: {{DATE}}
## TL;DR
{{SUMMARY}}
## Code Walkthrough
{{WALKTHROUGH}}
## Concepts
{{CONCEPTS}}
## Resources
{{RESOURCES}}
## What to Study Next
{{NEXT_STEPS}}
AntiVibe's pattern library covers:
| Language | Frameworks |
|---|---|
| TypeScript/JavaScript | React, Node.js, Express, Next.js |
| Python | Django, FastAPI, Flask |
| Go | Standard library, Gin, Echo |
| Rust | Standard library, Actix-web |
| Java | Spring Boot |
Add more in reference/language-patterns.md.
When generating deep dives, always follow these rules:
Deep dive not generating?
ls ~/.claude/skills/antivibe/SKILL.mdchmod +x ~/.claude/skills/antivibe/scripts/*.shHooks not firing?
.claude/hooks.json (project root), not the skill folderSubagentStop, Stop)Output directory missing?
mkdir -p deep-diveResources not found for a concept?
resource-curation.mdecho "### YourConcept" >> reference/resource-curation.mdInstall: cp -r antivibe ~/.claude/skills/antivibe
Trigger: "deep dive" | "explain what AI wrote" | /antivibe
Output: deep-dive/<topic>-<date>.md
Extend: reference/language-patterns.md
reference/resource-curation.md
Template: templates/deep-dive.md
Hooks: hooks/hooks.json → .claude/hooks.json
npx claudepluginhub aradotso/trending-skillsNarrates decisions, tradeoffs, and reasoning in plain language while building, helping users learn by working alongside Claude. Activates on requests for teaching or mentoring.
Explains complex code with high-level overviews, step-by-step walkthroughs, diagrams, and audience-adapted language for onboarding and knowledge sharing.
Offers interactive learning exercises after new files, schema changes, refactors, or design decisions to build expertise in AI-assisted coding.