JoshuaRamirez

Efficiently update multiple Azure DevOps work items at once. Use when the user wants to update many work items, bulk state changes, mass updates, batch operations, or update work items in a loop. Use when user mentions "bulk", "batch", "multiple items", "all…

Build and execute WIQL (Work Item Query Language) queries for Azure DevOps. Use when the user wants to query work items, find bugs, list tasks, search by assignee, filter by state, find items in a sprint, or build custom work item queries. Use when user…

Construct ASCII tree visualizations from parent/child work item data. Use when the user asks to "show hierarchy", "show tree", "display parent child", "visualize structure", "show feature tree", or wants to see work item relationships as a tree diagram. This…

Call Azure DevOps REST APIs via az devops invoke command. Use when you need to access Azure DevOps features not available in the CLI, such as work item comments, search, boards, backlogs, capacities, or any wit/work/search API endpoint. Use when the user…

Reference for Azure DevOps work item fields, link types, and states. Use when the user needs to know field names, field paths, reference names, link types, or work item type configurations. Use when user mentions "field name", "field path", "what field",…

Navigate all project documentation. Indexes every docs/ folder and the slash command that manages it. Use when you need to find where to read or write a particular kind of doc.

Manage the Cockburn-style use case catalogue under docs/requirements/use-cases/. Use cases are this project's primary requirements. Subcommands: list, show, new, status, set-status, roadmap, next, audit.

Manage the chronological developer log under docs/devlog/. One file per UTC day, append-only entries. Subcommands: today, show, append, list, latest.

Top-level navigator for project requirements under docs/requirements/. Today the only requirement format is the use case catalogue; delegates to /use-case for that work.

Design a splitty pipeline YAML file from a user's natural-language request. Use when the user describes an analysis goal but has not provided a pipeline file, or when they say "design a pipeline for X", "what pipeline would you use for Y", or "make a splitty…

Execute a splitty pipeline to completion. Use when given a path to a pipeline.yaml file (or an existing run-id to resume). Drives the orchestration loop: init → loop[next → spawn sub-agents → mark done] → finalize. Claude itself is the orchestrator — there is…

Run a chunk-level pipes-and-filters analysis end-to-end. Use when the user says "splitty <do something>", "split this corpus", "map-reduce this", "fan out X across Y", "run a pipeline over <files>", or describes a goal that requires processing many chunks of…

This skill should be used when the user asks to "refine a prompt", "improve this prompt", "run this through APE", "make this prompt better", "iterate on this prompt", "philosophical refinement", "dimensional analysis of a prompt", "prompt engineering with…