All Skills

Quality gates, eval checkpoints, and recovery controls for continuous autonomous agent loops. Patterns for safe loop operation with stall detection and intervention hooks.

Autonomous agent loop architectures from simple to complex: sequential pipelines, infinite agentic loops with quality gates, continuous PR loops with CI gates, de-sloppify cleanup passes, and RFC-driven multi-agent DAG orchestration with merge queues.

Systematic prompt improvement pipeline: structured prompt analysis, A/B testing patterns, metric-driven iteration, and prompt versioning for production LLM applications.

MCP server construction with Node/TypeScript SDK: tool registration with Zod validation, resource and prompt handlers, stdio vs Streamable HTTP transport selection, and transport-independent server architecture.

Solves the subagent context problem via 4-phase iterative retrieval: dispatch with minimal context, evaluate gaps, retrieve targeted context, and re-dispatch. Prevents context overflow and starvation in multi-agent workflows.

Production deployment workflows: rolling/blue-green/canary strategies, CI/CD pipeline patterns, Docker multi-stage builds, health checks, readiness probes, rollback strategies, and environment-specific configuration management.

Head-to-head coding agent comparison tool: YAML task definitions with judge criteria, git worktree isolation per agent run, pass rate/cost/time/consistency metrics, and reproducible benchmarking across Claude Code, Aider, Codex, and other agents.

Playwright E2E testing patterns: Page Object Model, test configuration, CI/CD integration with artifact capture (screenshots, videos, traces), flaky test quarantine, and critical user flow coverage strategies.

Eval-driven development framework: define pass/fail criteria before implementation, capability/regression/consistency eval types, pass@k reliability metrics, grader patterns, and continuous eval integration during development.

Test-driven development enforcement: write-tests-first methodology, RED/GREEN/REFACTOR cycle, 80%+ coverage requirement across unit/integration/E2E, user journey definitions, test pyramid structure, and coverage verification gates.

Docker and Docker Compose patterns: multi-service orchestration for local development, bind mounts with anonymous volume isolation, container networking, multi-stage Dockerfile optimization, container security hardening, and volume backup strategies.

Pre-PR verification pipeline: sequential build check, type check, lint, test with coverage, security scan, and diff review. Hard stop on build failure. Report all type errors before proceeding.

Audit skill and command libraries for quality: quick scan mode for changed skills, full stocktake with sequential subagent batch evaluation, quality scoring, and gap analysis.

Backend architecture patterns: repository/service/controller layers, database query optimization, Redis caching, background jobs, middleware chains, and structured error handling.

PostgreSQL quick reference: B-tree/GIN/BRIN index selection, data type cheat sheet, Row Level Security patterns, connection pooling, and Supabase-specific best practices.

REST API design patterns: resource naming, HTTP methods, status codes, pagination, cursor-based filtering, error response envelopes, versioning strategies, and rate limiting configuration.

OWASP Top 10 security checklist with code patterns for secrets management, input validation, SQL injection prevention, XSS, CSRF, rate limiting, and pre-deployment security verification.

Zero-downtime database migration patterns: forward-only production migrations, concurrent index creation, nullable column additions, separate schema vs data migrations, rollback planning.

SHA-256 content-hash caching for expensive file processing. Path-independent keys auto-invalidate on content change. Frozen dataclass cache entries with file-based O(1) storage.

Scans agent harness configurations for security vulnerabilities, misconfigurations, injection risks, secrets leaks, and permission escalation vectors.

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, patterns to catch blind spots where the same model writes and reviews code.