Loading...
Loading...
Found 1,832 Skills
Full lifecycle orchestrator - spec/impl/test. Spawn-wait-close pipeline with inline discuss subagent, shared explore cache, fast-advance, and consensus severity routing.
Set up Azure Pipelines for CI/CD, configure build and release pipelines, manage Azure DevOps projects, and integrate with Azure services. Use when working with Azure DevOps Services or Server for enterprise DevOps workflows.
Pipeline state management for Goldsky Turbo — pause, resume, restart, and delete commands with their rules and safety behavior. Use this skill when the user asks: will deleting my pipeline lose the data already in my postgres/clickhouse table, how do I pause a pipeline while doing database maintenance, how do I restart from block zero to reprocess all historical data, can I update a running streaming pipeline in place or do I have to delete and redeploy, will resuming a paused pipeline pick up from where it left off (checkpoint), how do I re-run a completed job pipeline from the beginning, can I pause or restart a job-mode pipeline. Also covers what happens to checkpoint state on delete, and job auto-deletion 1 hour after termination. For actively diagnosing why a pipeline is broken or erroring, use /turbo-doctor instead.
Diagnose and fix broken Goldsky Turbo pipelines interactively. Use whenever the user has a specific pipeline that is misbehaving — error state, stuck in 'starting', connection refused, slow backfill, not getting data in postgres/clickhouse, duplicate rows, missing fields, named pipeline failing ('my base-usdc-transfers keeps failing'), or any symptom where something is wrong with a deployed pipeline. Runs goldsky turbo logs and status commands, identifies root cause, and offers to run fixes. For looking up CLI syntax or error message definitions WITHOUT an active problem, use /turbo-monitor-debug instead.
Design and generate CI/CD pipelines from detected project stack signals. Covers GitHub Actions, GitLab CI, CircleCI, and Buildkite with caching, matrix builds, deployment strategies (blue-green, canary, rolling), environment gates, and security scanning. Use when bootstrapping CI, migrating pipelines, or optimizing build times.
Goldsky CLI command and flag reference — all valid subcommands, arguments, and options for goldsky turbo, pipeline, subgraph, secret, project, dataset, indexed, and telemetry. Consult before suggesting any goldsky command to avoid hallucinating invalid commands or flags.
Focused Signals scout for PostHog projects moving data through pipelines. Watches the three delivery surfaces — CDP destinations and transformations (hog functions), batch exports, and hog flows (workflows/messaging) — for contradictions between configured state and actual delivery: functions the watcher quietly degraded or disabled, failure rates stepping above a pipeline's own baseline, batch export runs failing or stalling (a growing data gap), and active flows failing for the people they trigger on. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.
Advanced concurrency patterns for Tokio including fan-out/fan-in, pipeline processing, rate limiting, and coordinated shutdown. Use when building high-concurrency async systems.
Analyzes pipeline coverage, tracks forecast accuracy with MAPE, and calculates GTM efficiency metrics for SaaS revenue optimization
Chain multiple AI steps into one reliable pipeline. Use when your AI task is too complex for one prompt, you need to break AI logic into stages, combine classification then generation, do multi-step reasoning, build a compound AI system, orchestrate multiple models, or wire AI components together. Powered by DSPy multi-module pipelines.
Execute and Monitor Testany Tests - Trigger Pipeline Execution, View Results, Check Status
Data validation and pipeline testing utilities for ML training projects. Validates datasets, model checkpoints, training pipelines, and dependencies. Use when validating training data, checking model outputs, testing ML pipelines, verifying dependencies, debugging training failures, or ensuring data quality before training.