Boards Work Item Summary Agent Skill
Summarize a single Azure DevOps work item (and its links and comments) by ID.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/microsoft/azure-devops-skills --skill boards-work-item-summaryThe instruction itself
4 sections, as written by the authorGet work item
This skill always works with one specific work item ID.
- If the user provides an ID (for example: "for 115770" or "work item 115770"), use that ID directly.
- If the user does not provide an ID, prompt the user once to provide the work item ID.
- If the ID is still not provided after prompting, stop and return a clear message stating that a work item ID is required and do not call any tools.
Tools
Use Azure DevOps MCP Server tools for all interactions with Azure DevOps.
wit_work_item(action:get): Get a work item from Azure DevOps by its ID.wit_work_item(action:list_comments): Get the list of comments for a work item by its ID.wit_work_item(action:get_batch): Get work item details in batch by their IDs. Use this tool to get the details of linked work items, using the links returned fromwit_work_itemwith actionget.
Steps
- Call
wit_work_itemwith actiongetandexpand=allfor the requested ID so that you retrieve fields, relations, and links in a single call.
- If the work item has a parent (for example,
System.Parentor aSystem.LinkTypes.Hierarchy-Reverserelation), include the parent ID in the set of linked IDs to summarize. You do not need a separate call; instead, rely onwit_work_itemwith actionget_batchin the next step.
- From the work item
relationsarray, collect all linked work item IDs (parent, child, related, and any others). Callwit_work_itemwith actionget_batchonce with that list of IDs to get the details of all linked work items.
- Call
wit_work_itemwith actionlist_commentsonce to get the comments for the original work item.
Display results
When displaying the results:
- Show the following fields for the main work item: Id, Title, State, Assigned To (just the display name, not the email), Work Item Type, Created Date formatted as
MM/DD/YYYY, Priority, and Tags.
- Provide a Links table. For each linked work item, display:
- Id as a clickable hyperlink in this exact format:
{ID} - Link type (for example: Parent, Child, Related, or the underlying relation name)
- Work item type
- Title
- State
Group and order the rows in this sequence: Parent links first, then Child links, then Related links, then any other link types.
- If there are pull requests linked to the work item (for example, via artifact links or specific PR relations), list them in a separate Pull Requests table with at least the PR ID, title, status, and a clickable link to the PR.
- Provide a short, plain-language summary of the work item’s description, system information, and repro steps (if those fields exist). Focus on the key intent, scope, and any critical technical or repro details.
- For comments:
- If there are one or more comments, state the total number of comments and give a brief overview of the main themes or decisions mentioned.
- If there are no comments, explicitly state that there are no comments for this work item.
Other skills for the same job
different authors, same section of the catalogue
Automate creating a GitHub repository and deploying a web project to Vercel. Use when the user asks to deploy a website/app to production, publish a project, or set up GitHub + Vercel deployment.
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
How to use it
Take microsoft/boards-work-item-summary from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.