Skip to content
TrustedSkillsbeta
Back to all skills

Azure Devops

Listed
sanjay3290·vlatest·cloud·Apache-2.0

Helps with Azure, DevOps as part of deploying and managing cloud infrastructure workflows.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add sanjay3290/ai-skills --skill azure-devops -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

sanjay3290

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 5 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: advsec.dev.azure.com, almsearch.dev.azure.com, dev.azure.com, login.microsoftonline.com, vssps.dev.azure.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    vssps.dev.azure.comundeclaredalmsearch.dev.azure.comundeclaredadvsec.dev.azure.comundeclareddev.azure.comundeclaredlogin.microsoftonline.comundeclared

    What it found (3 of 8)

    • skills/azure-devops/scripts/api_client.py:21contacts vssps.dev.azure.com
      return f"https://vssps.dev.azure.com/{org}"
    • skills/azure-devops/scripts/api_client.py:23contacts almsearch.dev.azure.com
      return f"https://almsearch.dev.azure.com/{org}"
    • skills/azure-devops/scripts/api_client.py:25contacts advsec.dev.azure.com
      return f"https://advsec.dev.azure.com/{org}"

  • No credential access: failed

    Touches credential material in 3 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found

    • skills/azure-devops/scripts/auth.py:50OS keychain / credential manager
      data_str = keyring.get_password(KEYCHAIN_SERVICE, KEYCHAIN_ACCOUNT)
    • skills/azure-devops/scripts/auth.py:56OS keychain / credential manager
      access_token = keyring.get_password(KEYCHAIN_SERVICE, KEYCHAIN_ACCOUNT_ACCESS_TOKEN)
    • skills/azure-devops/scripts/auth.py:60OS keychain / credential manager
      refresh_token = keyring.get_password(KEYCHAIN_SERVICE, KEYCHAIN_ACCOUNT_REFRESH_TOKEN)

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned sanjay3290/ai-skills at 281d88df19.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
281d88df19
Manifest
skills/azure-devops/SKILL.md
Scanned
18 files, 3,524 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill allows AI agents to interact with Azure DevOps, enabling tasks such as creating work items (like bugs or user stories), managing builds and releases, and querying project data. It provides a programmatic interface for automating common DevOps workflows within the Microsoft ecosystem. The agent can retrieve information about pipelines, repositories, and associated metadata.

When to use it

  • Automated Bug Reporting: Automatically create Azure DevOps work items based on error logs or monitoring alerts.
  • Release Management: Trigger builds and releases in Azure Pipelines based on specific events or conditions.
  • Project Status Updates: Retrieve the status of ongoing builds, deployments, and work item progress for reporting purposes.
  • Code Repository Queries: Search for files within a repository or retrieve commit history information.

Key capabilities

  • Create Work Items
  • Manage Builds
  • Manage Releases
  • Query Project Data
  • Interact with Pipelines
  • Repository Interaction

Example prompts

  • "Create a new bug in Azure DevOps project 'MyProject' with the title 'Login button unresponsive'."
  • "Trigger a release pipeline named 'ProductionRelease'."
  • "What is the status of build number 12345?"
  • "List all commits to the 'main' branch in repository 'MyRepo'."

Tips & gotchas

  • Requires appropriate Azure DevOps credentials and permissions for the AI agent.
  • Be specific with project names, pipeline names, and work item types to avoid ambiguity.