From ai-firstify
Analyzes, re-engineers, or bootstraps projects to align with AI-first design principles across 7 dimensions. Includes audit, active restructuring, and guided new project setup.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-firstify:ai-firstifyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze and re-engineer projects to align with AI-first design principles.
Analyze and re-engineer projects to align with AI-first design principles.
Use this skill when asked to:
Perform a comprehensive read-only analysis across 7 dimensions. Output a scored report with recommendations. Do NOT modify any files.
Read references/mode-audit.md for the full audit procedure and dimension checklist.
First, perform the full audit (Mode 1). Then actively fix issues in 7 phases: foundation, de-agentification, skill extraction, complexity reduction, context hygiene, safety hardening, workflow optimization.
Read references/mode-reengineer.md for the full re-engineering procedure.
Guide the user through setting up a new AI-first project from scratch. Interactive: ask discovery questions, recommend architecture, scaffold, and test.
Read references/mode-bootstrap.md for the full bootstrap procedure.
Domain knowledge (load on demand per dimension):
Load the relevant reference file for the dimension you are currently analyzing. Do not load all references at once. Use progressive disclosure.
npx claudepluginhub techwolf-ai/ai-first-toolkit --plugin ai-firstifyDiagnoses AI project workspaces as new 'Pure Engine' or existing 'Evolution', conducts Spanish requirements interviews, proposes expert skill squads, and generates tareas.md and plan_implementacion.md roadmaps. Use at project start.
Analyzes project requirements and recommends optimal Anthropic architectures using Skills, Agents, Prompts, and SDK primitives for scalable AI systems.
Scaffolds greenfield project architecture and AI agent harness via interview-driven decisions. Outputs markdown spec with code structure exemplar, tests, guardrails, CLAUDE.md setup, and unified plan. Invoke via /scaffold for new projects.