Install
$ agentstack add skill-ahmadharis-agentskills-azure-work-complete ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Azure DevOps Full Cycle Workflow
Orchestrates the complete development cycle: pick up a work item, implement it, review the code, create a PR, and clean up. Designed to run autonomously with minimal user intervention.
Invocation
| Mode | Command | Behavior | |------|---------|----------| | Single run | /azure-work-complete | Run one full cycle | | Continuous | /loop 30m /azure-work-complete | Repeat on a schedule (session-scoped, 3-day max) |
> Context in loop mode: Each /loop iteration runs in the same session. If context grows large, use /compact between cycles or run in headless mode (claude -p "/azure-work-complete") for full isolation per cycle.
Step 1: Pick Up a Work Item
Invoke the azure-work skill in browse mode (no arguments).
The skill will list open work items. Automatically pick the first item from the list — do not prompt the user for selection.
If the list is too large: If azure-work indicates there are too many items to display, or returns an error about result limits, or the list appears truncated, re-run the WIQL query from azure-work and pipe the output through jq to take only the first 5 results:
az boards query --wiql "SELECT [System.Id], [System.Title], [System.State], [System.WorkItemType] FROM WorkItems WHERE ..." --org "https://dev.azure.com/$ADO_ORG" --project "$ADO_PROJECT" -o json | jq '.[:5]'
WIQL does not support TOP N or LIMIT. Result limiting must be done client-side.
Then pick the first item from the reduced list.
If no items are returned: Stop the cycle and report: "No open work items found. Cycle complete." If running in a loop, cancel the scheduled task — use CronList to find the task ID, then CronDelete to remove it. Report: "All work items complete. Loop cancelled."
Step 2: Implement the Work Item
The azure-work skill handles the full implementation:
- Reads work item details and attachments
- Creates a feature branch
- Updates work item state
- Brainstorms or implements directly (based on complexity)
- Runs verification checks
Wait for azure-work to complete fully before proceeding.
Step 3: Code Review
After implementation, assess whether the changes need review and simplification.
When to skip this step:
- The change is trivial (single-file fix, config change, documentation-only)
- The change is a one-liner or a few-line bug fix with clear intent
- The verification checks from Step 2 already confirmed quality
When to run this step:
- Multi-file feature implementation
- Refactoring or architectural changes
- Complex logic added
- Significant amount of new code
Claude Code (primary)
If /simplify is available, invoke it:
/simplify
This spawns three parallel review agents (code reuse, quality, efficiency), aggregates findings, and applies fixes automatically.
Codex / Other Platforms (fallback)
If /simplify is not available, perform an inline code review. Review all changed files (from git diff --name-only against the default branch) for:
- Code reuse — duplicated logic or patterns that should be consolidated into shared functions or modules
- Code quality — naming clarity, consistent style, overly complex conditionals, dead code, unclear intent
- Efficiency — unnecessary allocations, redundant iterations, suboptimal data structures, avoidable I/O
For each issue found, fix it directly. Do not report issues without fixing them. After all fixes are applied, re-run the project's verification checks (build, test, lint) to confirm nothing broke.
Step 4: Create Pull Request
Invoke the azure-pr skill with the work item ID from Step 1:
/azure-pr --work-items
Wait for the PR to be created. Note the PR URL from the output.
Step 5: Return to Default Branch
Always run this step — regardless of whether the PR was merged or is awaiting review. The branch has been pushed and the PR created, so the local feature branch is no longer needed. Returning to the default branch is required to be ready for the next work item (especially in loop mode).
Invoke:
/pr-complete
This switches to the default branch, pulls latest, prunes remotes, and deletes stale local branches.
Cycle Complete
Report a summary:
Cycle complete:
- Work item: # —
- Branch: feature/
- PR:
- PR status: awaiting review
- Local: back on default branch, ready for next item
If running in a /loop, the next iteration will begin at the scheduled time and pick up the next available work item.
Notes
- Each cycle is independent — it picks up whatever is first on the backlog at that moment
- Direct mode is not supported for this skill — it always browses and picks the top item
- Work item priority ordering comes from the WIQL query in
azure-work(priority ASC, ID ASC) - If any step fails (authentication, no items, build failure), the cycle stops and reports the error
- The
azure-workskill handles all Azure DevOps interaction — this skill only orchestrates the sequence - Windows: Requires Git Bash or WSL — all orchestrated skills use bash syntax
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ahmadharis
- Source: ahmadharis/agentskills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.