ralph-long
Run the Ralph loop for a multi-iteration deep run in WSL (default 100) using the pt-study-sop worktree.
Run the Ralph loop for a multi-iteration deep run in WSL (default 100) using the pt-study-sop worktree.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Vercel ๋ฐฐํฌ, Preview/Production ํ๊ฒฝ ๊ด๋ฆฌ, Edge Functions, ํ๊ฒฝ ๋ณ์ ์ค์ , CI/CD ํ์ดํ๋ผ์ธ ํตํฉ ์ ๋ฌธ ์คํฌ.
Manages Agent hierarchy (POโManagerโDeveloper). Required for all code modifications except minor fixes. Optimizes performance through parallel execution.
Performs release-level QA checks for JU-DO-KON!, identifying risk, regressions, and readiness gaps.
Use when you have a spec or requirements for a multi-step task, before touching code
Avalia quality gates entre fases do SDLC. Verifica artefatos obrigatorios, criterios de qualidade, e aprovacoes necessarias antes de permitir transicao. Use quando: transicao entre fases, verificacao manual de gate, auditoria de qualidade.
Rollback the latest to the previous deployment. Requires authentication. Use for Agentuity cloud platform operations
Execute Phase 5 comprehensive verification before PR. Use when (1) implementation is complete, (2) before creating Pull Request, (3) user requests quality check, (4) pre-commit validation needed, (5) Constitution compliance verification required.
Use when working with Ansible Core 2.19 for automation, configuration management, playbooks, modules, or infrastructure as code
Complete management for Jokers Hockey website - deployment, build checks, database migrations (Drizzle ORM), and PM2 process management. Use for any Jokers site operation.
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
็ผๆ็ซ็นๅๅธไธๅๆป๏ผๅๅปบjobใๆฅ่ฏข่ฟๅบฆใ้่ฏ/ๅๆถใ็ๆฌๅๆข๏ผใๅฝ็จๆท่ฆๅ้กต/ๅ จ็ซๅๅธใๆฅ็ๅๅธ็ถๆๆๅๆปๆถ่ฐ็จใ
One lifecycle for Lambda repos: choose a bd task, start work, land the PR, and watch GitHub via Dumbwaiter MCP until it merges.
CI/CD integration and automation frameworks for continuous AI security testing
Context-fresh development workflow with spec-driven phases. Prevents context rot by enforcing fresh contexts per task.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
่จญๅฎ Auto-Dev workflow๏ผๅฏฆ็พ Human-in-the-Loop ่ชๅๅ้็ผ
Use when you have a written implementation plan to execute - implements inline with subagent review gates for spec compliance and code quality
Perform and apply code reviews (UACRP + application protocol) and coordinate artifacts via mpcr.
GitHub Actions ใฎใฏใผใฏใใญใผๅฎ่กใจใฉใผใ่ชฟๆปใใๅๅ ใ็นๅฎใใฆ่งฃๆฑบ็ญใๆๆกใใใใActions ใจใฉใผใใใฏใผใฏใใญใผๅคฑๆใใCI ใ่ฝใกใใใใใซใๅคฑๆใใใในใๅคฑๆใใActions ใ่ชฟในใฆใใCI ใฎใจใฉใผใ่ฆใฆใใชใฉใง่ตทๅใๅคฑๆใใใธใงใใฎใญใฐใๅๆใใๅ ทไฝ็ใชไฟฎๆญฃๆนๆณใๆ็คบใ