agent-toolkit

Evaluate existing architecture fitness. Identify gaps, suggest improvements only when scale justifies them. Safe refactoring if user wants changes. Keywords: assess, audit, evaluate architecture, tech debt, refactor, modernize, fitness, anti-patterns, scale

Comprehensive quality grading. Checks prompt compliance, code quality, security, test coverage, architecture fitness. Produces a percentage score. Not lenient. Keywords: evaluate, grade, check, verify, validate, scorecard, quality, percentage, score, how good

Quality gate before every commit. Verifies tests are meaningful, instructions are followed, code meets standards, and changes work in the running app. Keywords: commit, push, pre-commit, quality, check, verify, ready, standards, before commit, gate

Review code, test coverage, runtime, accessibility, dependencies, UI quality. Keywords: review, test, coverage, quality, a11y, smoke test, validate, audit

Design system architecture with trade-offs. Keywords: architecture, design, database, API, frontend, backend, security, scaling, decisions, tech stack, patterns

Systematic debugging when something is broken. Diagnose by layer, hypothesis-driven, reproduce with test, then fix. Keywords: debug, broken, not working, bug, crash, fix, error, failing, blank page, 0 results, silent failure

Get familiar with any codebase. Deep-dive tech stack, architecture, features, conventions, issues. Multi-repo support. Keywords: explore, understand, onboard, what is this, how does it work, codebase, repo, project, analyze

Build features with TDD. Skeleton first, then feature slabs. Fix, refactor, demo modes. Keywords: implement, build, code, TDD, skeleton, slab, fix, debug, refactor, demo

Gather, scope, and validate project requirements. Keywords: requirements, features, scope, user stories, what to build, planning, intake, MVP, priority

Generate install scripts, Docker config, and README for any project. One-command setup, platform agnostic. Keywords: install, setup, deploy, docker, readme, run, start, build

Project dashboard, progress, what's done, what's next. Keywords: status, progress, dashboard, where am I, what's done, what's left, what's next, overview

Audit toolkit health, freshness, security, standards. Keywords: updater, audit, outdated, stale, security, OWASP, refresh, check links, standards, compliance

Verify changes actually work and output is useful. Session health check, output quality, user confirmation. Keywords: verify, test, check, does it work, QA, validate, is it right, output quality