Analyzes completed development work to identify automation, delegation, systematization, and learning opportunities. Use after features, bug fixes, or code reviews.
From compound-analyzernpx claudepluginhub aviflombaum/claude-code-in-avinyc --plugin compound-analyzerThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Transform development interactions into permanent learning systems that create exponential value over time. Identify how today's work can become tomorrow's accelerator.
Identify subtasks where specialized agents could provide superior efficiency:
Spot recurring manual processes ripe for systematic automation:
Find knowledge that must be captured for compound benefits:
Highlight insights preventing future issues or accelerating similar work:
Suggest independent workstreams for simultaneous execution:
COMPOUND ENGINEERING OPPORTUNITIES:
SUGGESTION: [Specific, actionable recommendation with clear scope] COMPOUND BENEFIT: [Long-term compounding value, quantified where possible] IMPLEMENTATION: [Approach, complexity (Simple/Moderate/Complex), timing] CONFIDENCE: [High/Medium/Low] - [Reasoning based on observed patterns]