agent-builder
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand…
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
$ npx -y skills add shareAI-lab/learn-claude-code --skill code-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/code-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
name: code-review description: Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
You now have expertise in conducting comprehensive code reviews. Follow this structured approach:
Check for:
# Quick security scans npm audit # Node.js pip-audit # Python cargo audit # Rust grep -r "password\|secret\|api_key" --include="*.py" --include="*.js"
Check for:
Check for:
Check for:
Check for:
## Code Review: [file/component name] ### Summary [1-2 sentence overview] ### Critical Issues 1. **[Issue]** (line X): [Description] - Impact: [What could go wrong] - Fix: [Suggested solution] ### Improvements 1. **[Suggestion]** (line X): [Description] ### Positive Notes - [What was done well] ### Verdict [ ] Ready to merge [ ] Needs minor changes [ ] Needs major revision
# Bad: SQL injection
cursor.execute(f"SELECT * FROM users WHERE id = {user_id}")
# Good:
cursor.execute("SELECT * FROM users WHERE id = ?", (user_id,))
# Bad: Command injection
os.system(f"ls {user_input}")
# Good:
subprocess.run(["ls", user_input], check=True)
# Bad: Mutable default argument
def append(item, lst=[]): # Bug: shared mutable default
# Good:
def append(item, lst=None):
lst = lst or []// Bad: Prototype pollution Object.assign(target, userInput) // Good: Object.assign(target, sanitize(userInput)) // Bad: eval usage eval(userCode) // Good: Never use eval with user input // Bad: Callback hell getData(x => process(x, y => save(y, z => done(z)))) // Good: const data = await getData(); const processed = await process(data); await save(processed);
# Show recent changes git diff HEAD~5 --stat git log --oneline -10 # Find potential issues grep -rn "TODO\|FIXME\|HACK\|XXX" . grep -rn "password\|secret\|token" . --include="*.py" # Check complexity (Python) pip install radon && radon cc . -a # Check dependencies npm outdated # Node pip list --outdated # Python
1. **Understand context**: Read PR description, linked issues 2. **Run the code**: Build, test, run locally if possible 3. **Read top-down**: Start with main entry points 4. **Check tests**: Are changes tested? Do tests pass? 5. **Security scan**: Run automated tools 6. **Manual review**: Use checklist above 7. **Write feedback**: Be specific, suggest fixes, be kind
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand…
Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate…
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.