PopKit operations plugin - quality assurance, deployment, and debugging workflows
npx claudepluginhub jrc1883/popkit-ai --plugin popkit-opsanthropic | security | performance | ux | architect | docs | all [--fix, --json]
quarterly | yearly | stale | duplicates | health | ip-leak [--verbose, --fix]
run | analyze | report - Benchmark PopKit value vs baseline
code | routing [--trace, --verbose]
init | setup | validate | execute | rollback [--target, --dry-run, --yes, --json]
scan | list | fix | report [--dry-run, --severity, --fix]
Expert debugging specialist for complex issues. Use when facing hard-to-reproduce bugs, performance anomalies, or mysterious system behaviors that require deep investigation and systematic troubleshooting.
Elite performance engineering specialist that analyzes, diagnoses, and optimizes web application performance across all metrics. Use for performance audits, bottleneck identification, and optimization strategies.
Comprehensive security specialist for vulnerability assessment, threat analysis, and defensive security implementation. Use when auditing code, analyzing security risks, or implementing security measures.
Comprehensive testing specialist for writing, fixing, and optimizing test suites. Use when implementing tests, debugging test failures, or improving test coverage.
Ensures safe, reliable deployments through comprehensive validation and verification. Use for pre-deployment checks, smoke testing, and deployment verification.
DevOps automation specialist for CI/CD pipelines, containerization, infrastructure as code, monitoring, environment management, and build optimization. Use when setting up, modifying, or troubleshooting deployment infrastructure, CI/CD workflows, Docker configurations, or cloud resources.
Expert in rapid recovery procedures and safe rollback operations. Use when deployments fail, production issues arise, or emergency recovery is needed.
Validates PopKit compliance with Claude Code patterns using concrete standards and automated checks
Validates PopKit code quality using concrete metrics for DRY, coupling, cohesion, and architectural patterns
Evaluates PopKit efficiency using concrete metrics for context usage, token consumption, and lazy loading validation
Validates PopKit security posture using concrete vulnerability patterns, automated secret scanning, and OWASP-aligned checklists
Evaluates PopKit user experience using concrete heuristics for command naming, error messages, and interaction patterns
Orchestrates benchmark execution comparing PopKit vs baseline Claude Code
Confidence-based code review that filters issues to 80+ threshold, eliminating false positives and noise. Reviews implementation against plan or requirements for bugs, quality issues, and project conventions. Use after completing major features, before merging to main, or after each task in multi-step workflows. Do NOT use for quick fixes, single-line changes, or when you need immediate feedback - the thorough review adds overhead best reserved for significant changes.
Run an advisory outside-voice review through the opposite model family. Uses Codex when working in Claude Code, and Claude Code when working in Codex, unless explicitly overridden. Produces a normalized review artifact, prints the advisory report, and can optionally publish it as a PR comment keyed to the current head SHA.
Execute deployment to target environment - supports dry-run mode, captures deployment metrics and logs, handles rollback on failure. Use after pop-deploy-validate confirms readiness. Do NOT use without validating first.
Use when you need to manage project deployments - analyzes project structure to detect deployment targets (Docker, npm, Vercel, etc.), creates .claude/popkit/deploy.json config, and sets up deployment infrastructure. Do NOT use for actual deployment execution - use /popkit-ops:deploy execute for that.
Emergency rollback to previous deployment version - supports automatic and manual rollback triggers, validates rollback success, and creates incident report. Use when a deployment fails or needs to be reverted.
Use after pop-deploy-init to generate deployment infrastructure files - creates Dockerfiles, docker-compose configs, Kubernetes manifests, CI/CD pipeline workflows, and platform-specific configs based on deploy.json targets. Do NOT use for actual deployment execution - use /popkit-ops:deploy execute for that.
Pre-deployment validation - checks build, tests, security, dependencies, and deployment config against target environment. Generates a deployment readiness report with go/no-go recommendation. Use before any deployment execution.
Four-phase debugging: root cause → patterns → hypothesis → implement. For complex bugs, test failures, multi-component issues. NOT for obvious syntax errors.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research