OneLinersCommand workbench
Guides
Operational guides

Complete procedures with a way back.

Searchable, versioned procedures with prerequisites, verification, concrete output, and rollback.

Guides
243
Favorites
0
243 launch guides · 2601 reviewed steps
3 of 243 guides

AI/ML · Software Engineering · Security

Reduce Claude cost and latency with prompt caching

Add explicit prompt-cache breakpoints to stable Claude tool, system, document, and conversation prefixes; measure creation and read tokens, test invalidation and minimum-size behavior, compare uncached and cached latency, and roll back without corrupting the prompt contract.
Save to collectionCreate a collection in the sidebar first.
caution165 minadvanced10 stepsNode.js

AI/ML · Software Engineering · Security

Build a page-cited Claude assistant for long PDF documents

Build a long-document assistant that validates and quarantines PDFs, chooses inline or Files API intake deliberately, enables native citations, preserves page-aware citation blocks, refuses unsupported conclusions, and lets reviewers inspect every claim against the original page.
Save to collectionCreate a collection in the sidebar first.
caution210 minadvanced10 stepsNode.js

AI/ML · Observability & Monitoring · Software Engineering

Benchmark local LLMs reproducibly: TTFT, throughput, memory, quality, context, and tools

Create a reproducible Linux and NVIDIA benchmark that separates time to first meaningful content, end-to-end latency, exact server-reported token throughput, memory phases, deterministic task quality, long-context retrieval, structured output, and tool-call correctness. Results remain tied to immutable artifacts, scorer revisions, deployment flags, and host state.
Save to collectionCreate a collection in the sidebar first.
caution240 minadvanced15 stepsUbuntu Server