Skip to content

ECC Skills

The skills-ecc pack imports skills from the ECC community collection (github.com/affaan-m/ECC). These skills cover agent architecture, agentic engineering patterns, backend and frontend frameworks, testing, and autonomous operations. Check the public package source for its current inventory.

Terminal window
# Install the full ECC pack
dz install @dzhechkov/skills-ecc
# Or import fresh skills directly from the ECC repo
dz import-ecc
Skill Description
agent-architecture-audit Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes.
agent-eval Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics.
agentic-engineering Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
autonomous-loops Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
continuous-agent-loop Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
enterprise-agent-ops Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.
Skill Description
architecture-decision-records Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale.
benchmark-optimization-loop Use when making something faster — tries many variants, runs recursive optimization, benchmarks latency/throughput/cost, and selects the best implementation by measured tests.
Skill Description
ai-regression-testing Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots.
browser-qa Automate visual testing and UI interaction verification using browser automation after deploying features.
canary-watch Monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions.
django-tdd Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage analysis, and testing Django REST Framework APIs.
e2e-testing Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
Skill Description
backend-patterns Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
fastapi-patterns FastAPI best practices covering project structure, Pydantic v2 schemas, dependency injection, async handlers, authentication, authorization, and testing with httpx and pytest.
docker-patterns Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.
Skill Description
flutter-dart-code-review Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, and clean architecture.
Skill Description
data-scraper-agent Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports. Scrapes on a schedule, enriches with a free LLM, and stores in Notion/Sheets/Supabase. Runs 100% free on GitHub Actions.
Skill Description
brand-voice Build a source-derived writing style profile from real posts, essays, launch notes, and docs, then reuse that profile across content, outreach, and social workflows.
git-workflow Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices.

All ECC skills are imported from github.com/affaan-m/ECC and canonicalized into the DZ Harness format. Original skill authors retain attribution. Check the ECC repository for upstream updates and contribution guidelines.