ClaudePlugins

This skill should be used when the user asks to "babysit a PR", "babysit my pull request", "monitor my PR", "watch my pull request", "keep my PR green", "fix PR build failures automatically", "handle PR review comments", or wants autonomous Azure DevOps PR monitoring that fixes build breaks, test failures, code coverage gaps, and review comments on a polling loop.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Publish local changes as an Azure DevOps pull request — analyzes commits, creates or links a work item (bug, task, or user story), pushes the branch, composes a PR description, and optionally tends to reviewer feedback and build failures until the PR is merged.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Conduct code reviews of individual pull requests analyzing performance, code alignment, correct usage of external libraries, testing coverage, and code quality. Provides structured feedback with file:line references and code examples. Use when asked to "review PR #[number]", "code review pull request", "check PR for issues", or "analyze PR changes". Works on GitHub or Azure DevOps, with PR numbers, branch names, or GitHub/Azure DevOps PR URLs. NOT for developer performance reviews over time.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Set up structured JSONL logging in a codebase for both production code and test frameworks (unit tests, integration tests). Supports C#, JavaScript/TypeScript, Python, and Rust. Use when asked to "add logging", "set up structured logging", "enable test logging", "make this debuggable", "add JSONL logging", "configure log output", "instrument this code with logs", "fix unit test logging", "set up test framework logging", "add logging to tests", "replace Console.WriteLine in tests", or "configure xUnit/NUnit/MSTest/Jest/Vitest/pytest logging". NOT for debugging issues (use debug-with-logs) or reviewing logging quality (use logging-review agent).

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Router that turns rough requirements into a well-structured work item and posts it to GitHub (issue) or Azure DevOps (work item). Detects the backend automatically from the git remote, classifies the intent, then delegates to a deep sub-skill — draft-feature for new features/user stories, draft-bug for defects — or handles Tasks and trivial items inline. Owns provider resolution, tooling setup, duplicate check, the confirmation preview, creation, and follow-up. Use when the user says "draft a work item", "I have a rough requirement", "help me write a bug report", "turn this into a user story", or provides unstructured requirements and wants an issue or work item created.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Provider-agnostic autonomous two-phase development workflow driven by a work item — a GitHub issue or an Azure DevOps work item. First run: analyzes the problem using all available tools (codebase, logs, database, observability, CI), designs a solution, creates a plan, posts it to the work item, and waits for explicit user approval via HITL before proceeding. Subsequent runs: incorporate feedback or execute the approved plan — implement, verify, and publish a PR. The agent NEVER proceeds to implementation without explicit approval. Resolves the backend once (explicit from a wrapper, else auto-detected from the git remote), then runs an identical flow. Used by the gh:gh-work-on and ado:ado-work-on wrappers, or directly when the user says "work on <number>", "implement work item <number>", "pick up <number>".

Use when the user asks to "babysit a PR", "babysit my pull request", "monitor my PR", "watch my pull request", "keep my PR green", "fix PR check failures automatically", "handle PR review comments", or wants autonomous GitHub PR monitoring that fixes build breaks, test failures, coverage gaps, and review comments on a polling loop.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Publish local changes as a GitHub pull request — analyzes commits, creates or links a work item (backed by a GitHub issue), pushes the branch, composes a PR description, and optionally tends to reviewer feedback and failing checks until the PR is merged.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Internal helper. Load only when explicitly named by another skill or agent.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes