pipeliner
Build/run pipeliner modules (npm pi-pipeliner) — defineModule/defineChain + Thompson sampling. Use when wiring scheduled jobs, multi-step LLM pipelines, or anything cron-driven.
Works with
Claude CodeCursorCodex CLIGitHub CopilotGemini CLI
---
name: pipeliner
description: Build/run pipeliner modules (npm pi-pipeliner) — defineModule/defineChain + Thompson sampling. Use when wiring scheduled jobs, multi-step LLM pipelines, or anything cron-driven.
license: MIT
---
# pipeliner
Import from `pi-pipeliner` (source `~/repos/pipeliner`). All modules `.ts` via `defineModule`.
## Contract
- `defineModule({ name, input/output schemas, run(), postApply?() })` — atomic single-turn ops; decompose multi-step work into chained modules, not one mega-prompt.
- `defineChain` composes modules; Thompson sampling picks among variant arms.
- Scheduling: system cron → shell → pipeliner module (module may call `claude -p "/skill"` — CLI+skill = one turn, not whole job). Never CronCreate inside workers.
## Rules
- "pipeline" from Aaron = this framework, always. "directly"/"agentically" = bypass it.
- Read `~/repos/pipeliner/README.md` for API detail before writing a new module — don't guess shapes.More Data Engineering skills
data-pipeline
claude-office-skills/skills
Data pipeline and ETL automation - extract, transform, load workflows for data integration and analytics
4.1k
ETL Pipeline
claude-office-skills/skills
Design and automate Extract, Transform, Load data pipelines for data integration and analytics
3.9k
data-throughput-accelerator
affaan-m/ecc
Use when large data ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, or table synchronization needs to become much faster while preserving data correctness.
3.6k
