用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/praxstack/ai-visual-code-review --skill appinsights-instrumentation命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Principal-engineer-grade autonomous execution mode for any AI coding agent. Calibrates rigor to task size: one primitive cycle for tiny work, 3-phase contract for small, 10-phase for medium/large. Loops until verified. Keep-or-revert on every change. Writes Actionable Side Information on failures. Escalates through a 6-tier Fallback Matrix. Respects 6 Ambiguity Blockers as the only valid pause reasons. Emits binary acceptance criteria per phase and a structured Final Summary at completion. Use on explicit opt-in via the APEX-ON token, /apex or /autonomous slash commands, auto-task wrapper, or the phrase apply APEX after echo-confirmation. Trigger keywords: APEX, autonomous mode, principal engineer mode, rigorous execution, godel primitives, keep-or-revert, loop-until-verified, ambiguity blocker, fallback matrix, ASI, auto-task, apex-on, /apex, /autonomous. Not for conversational exploration or trivial edits.
Host-neutral autonomous software work protocol. Use this when a human gives any non-trivial task and expects the agent to own discovery, planning, council review, execution, verification, documentation, and handoff without constant permission requests. Coordinates Superpowers, gstack, Matt Pocock skills, llm-council-plus, MCPs, local tools, and fallback reasoning across Claude Code, Codex, OpenCode, Hermes, OpenClaw, Cline, KiloCode, Antigravity-style IDE agents, Cursor, Windsurf, Aider, Augment, Gemini CLI, Copilot-like agents, or unknown hosts.
Principal-engineer standards for backend services, APIs, data modeling, distributed systems, and reliability. Use when building or reviewing REST/GraphQL/gRPC APIs, database schemas, service boundaries, caching strategies, messaging, observability, or scaling patterns. Triggers on "design an API", "database schema", "service architecture", "distributed system", "caching strategy", "rate limit", "reliability pattern", "migration plan", "message queue", "SLI/SLO", and backend production reviews. Covers API disciplines, data modeling, scaling patterns, reliability patterns, DevOps and infra, data storage, observability, and performance. Loaded by super-mode-core for backend-heavy work.
| name | appinsights-instrumentation |
| description | Instrument a webapp to send useful telemetry data to Azure App Insights |
This skill enables sending telemetry data of a webapp to Azure App Insights for better observability of the app's health.
Use this skill when the user wants to enable telemetry for their webapp.
The app in the workspace must be one of these kinds
Find out the (programming language, application framework, hosting) tuple of the application the user is trying to add telemetry support in. This determines how the application can be instrumented. Read the source code to make an educated guess. Confirm with the user on anything you don't know. You must always ask the user where the application is hosted (e.g. on a personal computer, in an Azure App Service as code, in an Azure App Service as container, in an Azure Container App, etc.).
If the app is a C# ASP.NET Core app hosted in Azure App Service, use AUTO guide to help user auto-instrument the app.
Manually instrument the app by creating the AppInsights resource and update the app's code.
Use one of the following options that fits the environment.
No matter which option you choose, recommend the user to create the App Insights resource in a meaningful resource group that makes managing resources easier. A good candidate will be the same resource group that contains the resources for the hosted app in Azure.