ralph-json-start-loop
Runs the Ralph autonomous loop. Executes stories from prds/*.json using git worktrees.
ralph-json-create-issues
Converts a PRD or plan markdown file into prd.json format for ralph-json-start-loop to execute autonomously. Use when user wants to convert a PRD or plan to JSON stories.
create-script
Codify discovered processes into standalone, reusable Python scripts. Use when the user has figured out a process (API integration, data pipeline, automation task) and wants to turn it into a reusable script, or when the user says "/create-script".
execute-layer
Handles one layer of task execution. Groups ready tasks into batches, spawns batch agents, and processes merge queue after each batch.
data-engineer
Data pipeline specialist for ETL design, data quality, CDC patterns, and batch/stream processingUse when "data pipeline, etl, cdc, data quality, batch processing, stream processing, data transformation, data warehouse, data lake, data validation, data-engineering, etl, cdc, batch, streaming, data-quality, dbt, airflow, dagster, data-pipeline, ml-memory" mentioned.
development-ai-tools
Master the AI tools that supercharge software development. From code completion to full application generation, write better code faster and automate the tedious parts. Use when "AI coding, code assistant, Copilot, Cursor, code generation, AI developer tools, development, coding, ai-assistant, productivity, code-generation" mentioned.
migration-specialist
Migration specialist for zero-downtime schema changes, data migrations, and backward-compatible evolutionUse when "migration, schema change, database migration, zero downtime, backward compatible, rollback, blue green, data migration, migration, schema, database, zero-downtime, backward-compatible, rollback, blue-green, feature-flag, ml-memory" mentioned.
trigger-dev
Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when "trigger.dev, trigger dev, background task, ai background job, long running task, integration task, scheduled task, trigger-dev, background-jobs, ai-workflows, typescript, integrations, async, tasks, serverless" mentioned.
temporal-craftsman
Workflow orchestration expert using Temporal.io for durable executionUse when "temporal workflow, durable execution, saga pattern, workflow orchestration, long running process, activity retry, workflow versioning, temporal, workflows, durable-execution, saga, orchestration, activities, long-running, ml-memory" mentioned.
pg-boss
pg-boss expert for PostgreSQL-backed job queues with exactly-once delivery, perfect for applications already using Postgres (Supabase, Neon, etc.). Use when "pg-boss, postgres queue, postgresql job, supabase background job, neon job queue, postgres scheduling, database job queue, pg-boss, postgresql, job-queue, background-jobs, supabase, neon, exactly-once, scheduling" mentioned.
claude-code-hooks
Expert in Claude Code hooks - user-defined shell commands that execute at specific points in Claude Code's lifecycle. Provides guaranteed automation that doesn't rely on the LLM "remembering" to do something. Essential for enterprise workflows, code quality enforcement, and deterministic behavior in agentic coding. Use when "claude code hooks, automate claude, block tool use, pre tool use, post tool use, session start hook, claude lifecycle, claude-code, automation, hooks, lifecycle, cli, workflow, devtools" mentioned.
computer-use-agents
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when "computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation, Claude computer, OpenAI Operator, browser agent, visual agent, RPA with AI, " mentioned.
automation-ai-tools
Master the AI tools that automate repetitive work and connect your tools. From simple Zapier integrations to complex AI-powered workflows, reclaim hours every week. Use when "automation, workflow, integrate tools, connect apps, zapier, no-code, automate process, rpa, automation, workflow, integration, no-code, zapier, make, rpa" mentioned.
long-running-jobs
Run shell commands in the background with output capture and completion callbacks. Use when a command might take more than ~30 seconds (builds, tests, deployments, data processing) and you want to keep working while it runs.
chainlink-worker
Run a Chainlink backlog worker that claims ready issues, dispatches them to Codex sessions, and loops through review until approval. Use when the user wants autonomous issue execution via chainlink + codex, needs to start or stop the worker, or needs help reviewing `ready-for-review` issues.
linker-scripts
Linker script skill for embedded bare-metal targets. Use when writing or modifying GNU ld linker scripts, placing code and data in specific flash or RAM regions, understanding VMA vs LMA, configuring startup .bss/.data initialization, using MEMORY and SECTIONS commands, or debugging linker errors about regions. Activates on queries about linker scripts, MEMORY command, SECTIONS command, .bss init, VMA vs LMA, weak symbols, or placing functions in specific memory regions.
hecras-compute-remote
Distributed HEC-RAS execution across remote workers (PsExec, Docker, SSH, cloud). Handles worker initialization, queue scheduling, and result aggregation. Use when setting up remote execution, distributed computation, cloud workflows, scaling HEC-RAS across machines, parallel processing on multiple computers, Windows remote execution, container-based execution, session-based remote execution, PsExec configuration, Docker worker setup, or multi-machine HEC-RAS workflows. Triggers: remote execution, distributed execution, PsExec, Docker worker, SSH execution, cloud execution, parallel remote, multi-machine, session_id, remote worker, worker initialization, queue scheduling, network share, container execution.
