Use when bringing a recipe in the spark-recipes repo up on the 2-node DGX Spark cluster — starting/staging a recipe directory, tearing down the currently-serving model, rebuilding the patched image, launching worker-then-head, and confirming health. Triggers: "bring up <recipe>", "start <recipe> on the sparks", "deploy the glm/qwen/deepseek recipe", "latest recipe not running", "fresh head/worker after a model change", DFlash2/DFlash enablement.
bring-up-spark-recipe is a Claude Code agent skill that use when bringing a recipe in the spark-recipes repo up on the 2-node DGX Spark cluster — starting/staging a recipe directory, tearing down the currently-serving model, rebuilding the patched image, launching worker-then-head, and confirming health. Triggers: "bring up <recipe>", "start <recipe> on the sparks", "deploy the glm/qwen/deepseek recipe", "latest recipe not running", "fresh head/worker after a model change", DFlash2/DFlash enablement.
npx skills add https://github.com/taoofshawn/spark-recipes/tree/main/.agents/skills/bring-up-spark-recipeUse when bringing a recipe in the spark-recipes repo up on the 2-node DGX Spark cluster — starting/staging a recipe directory, tearing down the currently-serving model, rebuilding the patched image, launching worker-then-head, and confirming health. Triggers: "bring up ", "start on the sparks", "deploy the glm/qwen/deepseek recipe", "latest recipe not running", "fresh head/worker after a model change", DFlash2/DFlash enablement.
This repo contains 1 individual skill — each has its own dedicated page.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Prisma ORM patterns for TypeScript backends — schema design, query optimization, transactions, pagination, and critical traps like updateMany returning count not records, $transaction timeouts, migrate dev resetting the DB, @updatedAt skipped on bulk writes, and serverless connection exhaustion.
Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding background jobs, scheduled tasks, or async processing to a Django app.
Quarkus 3.x LTS architecture patterns with Camel for messaging, RESTful API design, CDI services, data access with Panache, and async processing. Use for Java Quarkus backend work with event-driven architectures.