gautam-achieveai/ClaudePlugins - 第 2 页

azure-devops

ALWAYS use this FIRST — before any Azure DevOps operation — to authenticate the sandbox. Trigger this before any request to dev.azure.com or *.visualstudio.com: listing/creating PRs, querying work items, reading repos/builds/pipelines, or any ADO REST call.…

原文语言：英语

connect

ALWAYS use this FIRST — before calling ANY external service that does not have a dedicated skill — to authenticate the sandbox. Trigger this before the first request to a third-party API (Slack, Salesforce, OpenAI, Stripe, an internal service, etc.). The…

原文语言：英语

github

ALWAYS use this FIRST — before any GitHub operation — to authenticate the sandbox. Trigger this before: cloning/fetching/pushing a github.com repo (git), running `gh`, calling api.github.com / raw.githubusercontent.com via curl/wget/HTTP clients, or…

原文语言：英语

microsoft-graph

ALWAYS use this FIRST — before any Microsoft Graph / Microsoft 365 operation — to authenticate the sandbox AND to get the correct API recipe. Trigger this before any request to graph.microsoft.com: reading a profile (/me), mail (incl. focused inbox + shared…

原文语言：英语

clean-builds

This skill guides developers through achieving zero-warning builds, consistent code style, and NuGet package version consistency. It provides a comprehensive workflow combining Roslynator analyzer integration (200+ code analyzers), code formatting, build…

原文语言：英语

developer-performance-review

This skill should be used when the user asks to "review [developer]'s work from [date] to [date]", "analyze developer productivity patterns", "prepare performance feedback", "conduct a performance review", "assess developer growth over time", or mentions…

原文语言：英语

egress-auth

Core sandbox egress authentication skill — the shared engine that the github / azure-devops / microsoft-graph / connect skills reference and use. Authentication is a REQUIRED FIRST STEP for any outbound call in the sandbox: the proxy blocks unauthenticated…

原文语言：英语

sandbox-auth-flow

Use before diagnosing sandbox network, credential, OAuth, egress proxy, auth webhook, deferred auth, or token injection failures. Explains the sandbox auth model and the security boundaries agents must preserve.

原文语言：英语

sandbox-memory

Use whenever a sandbox task needs durable state, task notes, handoff material, or project facts remembered across turns. Maintains Memory/ topic files and Memory/tasks/ task files instead of relying on hidden model state.

原文语言：英语

sandbox-scripts

Use when a sandbox workspace task needs repeatable setup, discovery, scaffolding, or verification commands. Guides when to create scripts, how to run them, and what not to automate.

原文语言：英语

sandbox-workspace-bootstrap

Use at the start of any non-trivial sandbox workspace task. Initializes the workspace coordination surface: Memory/ topic files, Memory/tasks/ task state, scripts/ helper directory, and a task-memory scaffold. Also use when the user asks how workspace files,…

原文语言：英语

orleans-code-review

Review Orleans code for correctness — loads orleans-patterns rules and systematically checks grain design, concurrency, communication, streams, and serialization

原文语言：英语

orleans-patterns

Comprehensive Orleans patterns and rules — grain design, concurrency, cross-grain communication, streams, and serialization

原文语言：英语