Automated summary
This skill enables interaction with Azure DevOps (ADO) to query, create, update, and search work items using MCP tools and a subagent for efficient token usage.
Strengths
- Token-efficient by isolating ADO context to a subagent, reducing main conversation load.
- Provides clear mappings between JIRA and ADO statuses and work item types.
- Supports querying, creating, updating, and searching work items with strict type validation.
- Includes predefined project and type mappings for quick setup.
Limitations
- Only configured for the 'TTracker' project; organization hardcoded.
- Requires specific MCP tools to be available in the environment.
- Mappings from JIRA to ADO may not align with all organizational processes.
Use when you need to interact with Azure DevOps work items for querying, creating, updating, or searching, especially to keep ADO context separate from main conversation.
Do not use for general ADO workflow discussions without actual queries, or when working with JIRA instead.
Security analysis
SafeThe skill only uses Azure DevOps MCP tools and filesystem write for legitimate work item operations. No destructive commands, data exfiltration, or obfuscation.
No concerns found
How this analysis is madeExamples
Check ADO item 123Create a bug in ADO for 'Duplicate articles appearing'Search ADO for clusteringAzure DevOps Integration Skill
Description
Automatically use this skill when user wants to interact with Azure DevOps (ADO).
Trigger when user says things like:
- "Check ADO item 123" or "look at work item 123"
- "Create a work item for [description]"
- "Create a story in ADO for [feature]"
- "Create a bug in ADO for [issue]"
- "What's the status of ADO 123?"
- "Update the ADO item to Active"
- "Search ADO for [query]"
- "Export ADO backlog"
- "How many items in ADO?"
Do NOT trigger when:
- User just references an ADO item in passing without asking to query it
- Discussing ADO workflow concepts without needing actual queries
- Working with JIRA (use JIRA skill instead)
Key patterns:
- "ADO [number]" or "work item [number]" → Query that ADO work item
- "create in ADO" or "add to ADO" → Create new work item
- "search ADO" → Search work items
- "export ADO" → Export backlog to file
ADO Instance Details (HARDCODED - use these directly)
Project: TTracker
Organization: (inferred from MCP connection)
Work Item Type Mappings
| JIRA Type | ADO Type | When to Use |
|-----------|----------|-------------|
| Epic | Epic | Grouping stories |
| Story | User Story | DEFAULT - all dev work |
| Bug | Bug | Something is broken |
| Task | Task | Sub-work items (rare) |
State Mappings (JIRA → ADO)
| JIRA Status | ADO State | |-------------|-----------| | Backlog | New | | To Do | New | | In Progress | Active | | In Review | Active | | Ready for Test | Active | | Done | Closed |
Purpose
Handle ADO operations via subagent to isolate 20-30K token context cost. ADO MCP tools return full work item details - this skill processes internally and returns only summaries.
Instructions
Launch a Task tool (general-purpose subagent) with the ADO operation. The subagent will:
- Execute the ADO operation using MCP tools
- Process the full response internally (absorbing the 20-30K tokens)
- Return only a concise summary to main conversation
Subagent Prompt Template
Execute ADO operation: [DESCRIBE WHAT USER WANTS]
**USE THESE VALUES DIRECTLY (already known):**
- Project: TTracker
**MCP Tools:**
- mcp__azure-devops__wit_get_work_item(project, id) - Get single work item
- mcp__azure-devops__wit_get_work_items_batch_by_ids(project, ids) - Get multiple items
- mcp__azure-devops__wit_create_work_item(project, workItemType, fields) - Create item
- mcp__azure-devops__wit_update_work_item(id, updates) - Update item
- mcp__azure-devops__search_workitem(searchText, project) - Search items
- mcp__azure-devops__wit_my_work_items(project) - Get my items
- mcp__azure-devops__wit_work_items_link(project, updates) - Link items
**Example - Query work item:**
mcp__azure-devops__wit_get_work_item(project="TTracker", id=123)
**Example - Create User Story:**
mcp__azure-devops__wit_create_work_item(
project="TTracker",
workItemType="User Story",
fields=[
{"name": "System.Title", "value": "Feature title here"},
{"name": "System.Description", "value": "Description here"},
{"name": "System.Tags", "value": "jira:TTRC-XXX"}
]
)
**Example - Update work item:**
mcp__azure-devops__wit_update_work_item(
id=123,
updates=[
{"path": "/fields/System.Description", "value": "New description"}
]
)
**Example - Search:**
mcp__azure-devops__search_workitem(searchText="clustering", project=["TTracker"])
Return ONLY a summary in this format:
[ADO #ID]: [Title]
Type: [Epic/User Story/Bug/Task] | State: [New/Active/Closed]
Tags: [tags if any]
[Action taken or key finding]
Do NOT return full descriptions, field dumps, or raw API responses.
Work Item Type Rules (STRICT)
When creating work items:
Bug
Use ONLY when something existing is broken.
- Keywords: fix, broken, error, wrong, not working, crash, fail
- Example: "Duplicate articles appearing" → Bug
User Story (DEFAULT)
Use for ALL other work. When in doubt, use User Story.
- Keywords: add, implement, create, build, enhance, improve, refactor, update
- Example: "Add entity-based dedup" → User Story
- Example: "Improve clustering" → User Story
Epic
ONLY when user explicitly says "epic" or "initiative".
- Must be explicit request to group Stories
- Example: "Create an epic for Clustering V2" → Epic
Task
Rare - only for sub-items of stories.
- Example: Specific implementation tasks within a story
Common Field Paths
| Field | Path |
|-------|------|
| Title | /fields/System.Title |
| Description | /fields/System.Description |
| State | /fields/System.State |
| Tags | /fields/System.Tags |
| Area Path | /fields/System.AreaPath |
| Iteration Path | /fields/System.IterationPath |
| Parent | /relations/- (link type) |
Bulk Operations
For operations involving many items (export, batch create, batch update):
- Launch subagent with clear batch instructions
- Have subagent write results to file (e.g.,
scripts/ado-export.json) - Return only count/summary to main conversation
Example bulk export prompt:
Export ALL work items from TTracker project to scripts/ado-export.json.
For each item extract:
- id, title, type, state, tags, description (first 200 chars), parentId
Use mcp__azure-devops__search_workitem with project=["TTracker"] and top=1000.
Save results to file using mcp__filesystem__write_file.
Return only: "Exported X items to scripts/ado-export.json"
Context Savings
Main conversation: ~100 tokens (summary only) Subagent absorbs: 20-30K tokens (full ADO response) Savings: 99.5%
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/azure-devops-integration-mm78nnxt/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/azure-devops-integration-mm78nnxt' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/azure-devops-integration-mm78nnxt/download' --output '.skill-downloads/azure-devops-integration-mm78nnxt/SKILL.md.part' && mv '.skill-downloads/azure-devops-integration-mm78nnxt/SKILL.md.part' '.skill-downloads/azure-devops-integration-mm78nnxt/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/azure-devops-integration-mm78nnxt/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.