- Home
- Skills
- Agents & Orchestration
- azure ado task context
Works with the AI Agents you already use
azure ado task context
Capture Azure Boards work items, attachments, and comments directly into your repo for offline context and planning.
$4.99
azure ado task context
Example session with this skill installed
Import task 4502 from our Azure Board so I can start reviewing the code impact.
- Read your context and instructions
- Compiled the azure ado task
I have successfully captured the context for Azure Boards task
4502. The data has been stored in .aw/tasks/4502/ and I have mapped the stated requirements to the local repository.
Task 4502: Implement Retry Logic for Gateway Services
| Requirement ID | Description | Source | Code Mapping |
|---|---|---|---|
| REQ-01 | Implement exponential backoff for 5xx errors | Description | src/services/gateway.js |
| REQ-02 | Max retry limit must be configurable via ENV | Comment (2023-11-10) | src/config/defaults.ts |
| REQ-03 | Log all failed attempts to Telemetry | Criteria | src/lib/logger.ts |
Evidence & Attachments
source.md: Full task snapshot captured.attachments/sequence-diag.png: Reviewed. Shows the expected handshake flow.attachments/error-codes.xlsx: Reviewed. Contains the mapping of retryable vs. fatal status codes.
Observations
- The task description mentions 5xx errors, but a developer comment from two days ago suggests including 429 (Too Many Requests).
src/services/gateway.jscurrently has no retry wrapper; it throws immediately on non-200 responses.
Next steps
- Review the requirement conflict regarding 429 status codes in
context.md. - Verify if the proposed exponential backoff library is already a project dependency.
- Run
npm teston the gateway service to establish a baseline.
Status: Ready for planning
Connects securely to your tools. The creator never sees your data.
About this skill
Azure Boards Task Context is a specialized retrieval tool for developers who need to bridge the gap between Azure DevOps work items and their local development environment. It eliminates the manual effort of context switching between the browser and the IDE by programmatically capturing work item details, comments, and attachments directly into your project structure.
What it does
- Captures work items by fetching descriptions, acceptance criteria, custom fields, and paginated comments using Azure DevOps APIs.
- Syncs attachments by downloading images, PDFs, and spreadsheets from the same organization for local inspection.
- Maps code paths by identifying and citing relevant repository symbols and files associated with specific task requirements.
- Generates structured evidence by creating a local
.aw/tasks/directory containing a machine-readable JSON snapshot and a Markdown context file. - Maintains provenance by assigning stable IDs to requirements and tracking the source of every observation or decision.
- Preserves manual notes during refreshes, ensuring that human-added analysis in
context.mdis never overwritten by API updates.
How it works
- Resolve: Pass a work item ID or full Azure Boards URL to the agent; it validates your
ado.organizationandado.projectconfiguration. - Collect: The skill executes a bundled PowerShell script to retrieve the task data and download attachments to a local task folder.
- Review: The agent inspects the repository to locate code relevant to the task and assesses any attached documentation.
- Document: The agent populates a context template with requirements, mapping them to specific code locations and evidence.
Frameworks & tools
This skill requires PowerShell 7+ and an Azure DevOps Personal Access Token (PAT) with Work Items read access. It operates within your local file system, specifically under the .aw/tasks/ directory.
Why this beats prompting it yourself
Generic prompts often miss deep-linked comments, related work item relations, or custom fields that hold critical business logic. This skill uses a dedicated collector script to ensure a lossless, structured capture that handles pagination and binary attachments which standard LLM windows cannot process reliably.
Use cases
- Task Onboarding: Quickly pull all context for a newly assigned ticket without clicking through the ADO UI.
- Requirement Mapping: Trace specific acceptance criteria to existing symbols and functions in a legacy codebase.
- Offline Analysis: Review complex task histories and attached design specs while working in an air-gapped or low-connectivity environment.
- Pre-planning: Generate a formal evidence report to surface contradictions or missing info before a sprint planning session.
Known limitations
Requires a manual setup of the COPILOT_ADO_PAT environment variable. It does not support cross-organization attachments or automatic migration of archived task folders.
Requires PowerShell 7+ and manual environment variable setup. Does not support cross-organization attachments or recursive fetching of related items by default.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
Requires