ADO Backlog Toolkit

Show my assigned Azure DevOps work items as a grouped table with clickable ticket links — open work first, sorted by priority. The daily "what's on my plate / read the task hub" view.

Run the full findings -> Azure DevOps backlog process on a file or pasted text. Extract findings, triage, classify by the project's process, dry-run, then create on approval and write ticket links back. Use whenever someone wants to turn an audit/spreadsheet/list of issues into ADO work items.

Check that everything needed for the ado-backlog toolkit is installed and configured (Azure CLI + login, .NET 10 SDK, Python + openpyxl, target org/project). Run this first on a new machine or when ADO calls fail with auth errors.

Authenticate to Azure DevOps and fix auth problems — the shared primitive every other ado-* skill relies on. Use this BEFORE any create/query when ADO auth setup is uncertain, and whenever an ADO call misbehaves: a REST call returns 401 or 403, "az not logged in" / token expired, results come back from the wrong org or empty, or you hit "A potentially dangerous Request.Path value was detected (:)". Covers the two supported methods (Entra token via `az`, or AZDO_PAT), a one-line PowerShell verify snippet against the projects API, and a 401/403/wrong-org troubleshooting table. Invoke when someone says "I'm getting a 401 from Azure DevOps", "create-backlog says it can't get a token", "ado auth failing", or "check my ADO login before we run".

Create Azure DevOps work items from a backlog_input.json (the output of classify-work-items) via the bundled create-backlog.cs script. Always does a dry-run validation first and only creates real items after the user explicitly approves. Use this whenever there is a backlog_input.json or any file of items to file in ADO, or when the user says "create these work items", "file the backlog", "push these to Azure DevOps", "create the tickets/bugs/stories", "make the work items", or asks to turn a classified list of findings into a real ADO backlog. This is the step that actually writes to the org, so prefer it over hand-rolling REST/MCP calls when a backlog_input.json exists. After creating, it writes backlog_result.json for ado-writeback-tracking.

Add traceability columns to a spreadsheet source and write created Azure DevOps ticket IDs/URLs back into it, matched row-by-row by key. Use this right after creating work items — when you have a backlog_result.json and the original source was a spreadsheet (xlsx/csv). Triggers on "write the ticket links back", "track which row got which ticket", "update the spreadsheet with the ADO IDs", "fill in the ticket column", "close the loop on the audit sheet", or any request to record created-item IDs back onto the source rows. Runs the bundled tracking.py (add-columns + writeback). For doc/pasted-text input there are no rows to write to — in that case just report the created links instead.

Map triaged findings to the correct Azure DevOps work item types for the TARGET project's process, and emit backlog_input.json ready for creation. Use this AFTER triage and BEFORE creating items — when the user asks "what type should these be", "make these into work items / tickets", "turn these findings into a backlog", "classify these for ADO", or "build the backlog input". The type you choose MUST exist on the target board: a Basic-process project has no Bug or User Story, so picking those silently fails at creation time. This skill discovers the project's process first, applies industry typing rules (defect vs new capability vs grouping parent), maps severity to Priority, builds the per-type fields (titles, tags, repro/description as escaped HTML), carries each finding's `key` through, and hands off to ado-create-work-items.

Normalize ANY input into findings.json — the first step toward turning review notes into an Azure DevOps backlog. Use whenever someone hands you a list of issues, discrepancies, gaps, review notes, or audit results they want to act on: an Excel/CSV/TSV audit sheet, a Word/PDF/Markdown spec, or chat/text pasted into the conversation. Trigger even when the user does NOT say "extract" — e.g. "here's a naming audit", "these are the problems we found", "turn this spreadsheet into tickets", "I reviewed the portal and noted these gaps", "make a backlog from this doc". If the goal is eventually ADO work items, this runs first. Hands off to triage-findings (then classify-work-items, ado-create-work-items). Driven end-to-end by the findings-to-ado-backlog orchestrator.