AI Eng System

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

Design CI/CD pipelines, quality gates, and iterate on failing PR checks until green. Use when setting up pipelines or fixing CI on a branch.

Build a personalized learning roadmap with milestones and practice checkpoints

Read the auto-memory graph (~/.claude/projects/*/memory/*.md), find cross-session patterns, and write a digest. The skill never mutates memory — output goes to a fresh file the user reads. The cron-driven version is the daily-brief-sdk dream-digest workflow, which writes to a separate dedicated directory.

Continuous iteration loop pattern for well-defined tasks with clear completion criteria. Use when getting tests to pass, implementing features with automatic verification, bug fixing with clear success conditions, or running automated development overnight. Provides prompt templates, safety guidelines, and integration patterns for ai-eng-system workflows.

Multi-phase research orchestration for thorough codebase, documentation, and external knowledge investigation. Invoked by /ai-eng/research command. Use when conducting deep analysis, exploring codebases, investigating patterns, or synthesizing findings from multiple sources.

Build a static-first knowledge architecture using file-backed domain maps, rules, hypotheses, and durable references. Use for knowledge architecture, learning systems, decision context, and long-lived team memory without runtime memory tooling.

Prepare PRs for review: clean noisy history, improve descriptions, add reviewer guidance without changing behavior. Use when a PR is hard to review.

Publish npm packages via GitHub Actions with OIDC trusted publishing and provenance. Use when setting up automated npm publishes, debugging ENEEDAUTH/E404 errors, configuring provenance attestations, or setting up a new package for publication.

OWASP Top 10 prevention, auth patterns, secrets management, dependency auditing, boundary validation. Use when handling user input, auth, or external integrations.

Multi-axis code review with optional strict maintainability mode. Use before merging any change—human, agent, or automation output.

Recursively initialize AGENTS.md in monorepo subdirectories with smart detection. Creates hierarchical agent context files with proper linking to root CLAUDE.md and parent AGENTS.md. Use for setting up multi-package projects, microservices, or any project with important subdirectories that need AI agent guidance.

Write a structured specification before code: objectives, structure, code style, testing strategy, boundaries. Use when starting a new project or feature.

Red-Green-Refactor workflow: write tests before implementation, maintain coverage. Use when implementing logic, fixing bugs, or changing behavior.

Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.

Ground every framework decision in official documentation. Use when you want authoritative, source-cited code for any framework or library.

Deliver changes in thin vertical slices. Use when implementing a feature or refactor that touches more than one file.

Evaluate learning progress, identify blockers, and adjust the learning plan

Normalize mixed inputs like code, docs, PDFs, screenshots, diagrams, audio, and transcripts into a structured corpus. Use when the task depends on combining multiple artifact types before analysis or retrieval.

Decompose specs into small, verifiable tasks with acceptance criteria and dependency ordering. Use when you have a spec and need implementable units.

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior does not match expectations, or any unexpected error appears.

Chrome DevTools for live runtime data: DOM inspection, console logs, network traces, performance profiling. Use when building or debugging anything in a browser.

Run an extremely strict performance review for runtime efficiency, memory usage, bundle size, database query patterns, and scalability limits. Use for a thermo-nuclear performance review, thermonuclear performance audit, or especially harsh performance review.

Run an extremely strict architecture and system design review for coupling, boundary violations, dependency direction, layering, and structural decay. Use for a thermo-nuclear architecture review, thermonuclear system design audit, or especially harsh architecture review.