.github/skills/azure-devops-rest-api/SKILL.md
Guide for working with Azure DevOps REST APIs and OpenAPI specifications. Use this skill when implementing new Azure DevOps API integrations, exploring API capabilities, understanding request/response formats, or referencing the official OpenAPI specifications from the vsts-rest-api-specs repository.
npx skillsauth add tiberriver256/mcp-server-azure-devops azure-devops-rest-apiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides guidance for working with Azure DevOps REST APIs using the official OpenAPI specifications from the vsts-rest-api-specs repository. It helps with implementing new API integrations, understanding API capabilities, and referencing the correct request/response formats.
Azure DevOps REST APIs are organized into the following main areas:
The vsts-rest-api-specs repository is organized by API area and version:
specification/
├── {api-area}/ (e.g., git, build, pipelines)
│ ├── 7.2/ Latest stable version
│ │ ├── {area}.json OpenAPI spec file
│ │ └── httpExamples/ Example requests/responses
│ ├── 7.1/
│ └── ...
{area}.json file contains all endpoints, schemas, and parametersWhen exploring what APIs are available for a specific feature:
/tmp/vsts-rest-api-specsExample workflow:
cd /tmp
git clone --depth 1 https://github.com/MicrosoftDocs/vsts-rest-api-specs.git
cd vsts-rest-api-specs/specification/git/7.2
# Review git.json for endpoint definitions
# Check httpExamples/ for request/response samples
When adding new API functionality to the MCP server:
When you need to understand the exact format of API requests or responses:
specification/{area}/{version}/httpExamples/GET_repositories.json)Contains helper utilities for working with the API specifications:
clone_specs.sh - Clone or update the vsts-rest-api-specs repositoryfind_endpoint.py - Search for specific endpoints across all API specsContains curated reference documentation:
api_areas.md - Comprehensive list of all API areas and their purposescommon_patterns.md - Common request/response patterns across APIsauthentication.md - API authentication methods and patternsFinding the right API:
paths section to find endpoint URLstags property to understand the API categoryoperationId for the internal Azure DevOps method nameUnderstanding schemas:
definitions section of the OpenAPI spec$ref properties to follow schema referencesVersion selection:
When implementing features in this MCP server:
src/features/{api-area}/repositoryId, pullRequestId)Example feature implementation pattern:
// src/features/{api-area}/{operation}/
├── feature.ts // Core implementation using azure-devops-node-api
├── schema.ts // Zod schemas based on OpenAPI definitions
├── feature.spec.unit.ts // Tests using httpExamples data
└── index.ts // Exports
tools
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.