ajbm-dev

Use this agent when you need to review code for adherence to Robert C. Martin's Clean Code principles. Trigger this agent: - After implementing a new feature or module - Before committing significant code changes - As part of orchestrated code documentation with subagents - During code review sessions - When refactoring existing code - After writing a logical chunk of functionality Examples: <example> user: "I just finished implementing the user authentication module. Here's the code:" [code provided] assistant: "Let me use the clean-code-reviewer agent to analyze this code for Clean Code compliance and provide a remediation report." <uses Task tool to invoke clean-code-reviewer agent> </example> <example> user: "Can you review the PaymentProcessor class I just wrote?" assistant: "I'll launch the clean-code-reviewer agent to perform a comprehensive Clean Code analysis and generate a structured remediation report." <uses Task tool to invoke clean-code-reviewer agent> </example> <example> user: "I've completed the refactoring of the order management system. Please check if it follows clean code practices." assistant: "I'm invoking the clean-code-reviewer agent to evaluate your refactored code against Robert C. Martin's Clean Code principles." <uses Task tool to invoke clean-code-reviewer agent> </example>

Use this agent when you need to look up current software documentation, API syntax, library usage patterns, or best practices that may be beyond your training data. This agent should be invoked proactively whenever working with libraries, frameworks, or APIs where accuracy and currency are critical - whether implementing, reviewing, auditing, or answering questions about specific technologies.

USE WHEN distill, extract skill, capture patterns, teach from conversation, learn from session, skill from conversation. Analyzes conversations to extract user guidance patterns — corrections, questions, quality gates, analysis modes — and collaboratively distills them into permanent, replayable skills that teach Claude behavioral dispositions.

USE WHEN brainstorm, generate options, break out of default thinking, need diverse alternatives, explore creative angles, the first answer feels too obvious, name something, come up with hooks, find unconventional approaches. Applies Verbalized Sampling (Zhang et al., 2024) — generate multiple low-probability variants internally before selecting output. Counteracts the centroid bias of alignment-trained models. Reports measured gains of 1.6–2.1× diversity and ~25% quality improvement.

USE WHEN extract wisdom, analyze video, analyze podcast, analyze article, extract insights, key takeaways, what did I miss, extract from YouTube, content analysis, insight report. Content-adaptive wisdom extraction — detects what domains exist in the content and builds custom sections (not static IDEAS/QUOTES). Produces tailored insight reports from videos, podcasts, interviews, and articles at five selectable depth levels.

USE WHEN transferring a PAI skill to a standard Claude Code plugin, porting skills between environments, strip PAI specifics, adapt PAI skill for marketplace, extract skill from PAI. Guides the transformation of PAI-embedded skills into standalone plugin-compatible skills — strip PAI-specific scaffolding, decouple from the PAI Algorithm and memory system, apply Anthropic skill best practices.

USE WHEN improve prompt, write prompt, craft prompt, analyze prompt, prompt engineering, subagent prompts. Analyze, craft, and improve prompts using 19 research-backed techniques. Modes - Analyze (critique existing), Craft (build from scratch), Teach (explain techniques), Quick Fix (fast improvements).