inspecto

Use when the AI should handle Inspecto annotation sessions through MCP, including claiming the next task, replying with progress, and resolving work when complete.

Use when Codex should install or set up Inspecto in the current frontend project through the shared onboarding workflow.

Use when creating or maintaining assistant-specific Inspecto onboarding skills that should follow the shared detect, plan, apply, and doctor workflow.

Use when the user wants CodeBuddy to install, configure, or diagnose Inspecto in the current project.

Use when Claude Code should install or set up Inspecto in the current frontend project through the shared onboarding workflow.

Help users install, configure, or diagnose Inspecto in the current repository. Use this skill when asked to set up Inspecto.

Use when the user wants Cursor to install or set up Inspecto in the current project.

Help users install, configure, or diagnose Inspecto in the current workspace. Use this skill when asked to set up Inspecto.

Help users set up Inspecto in their project or diagnose Inspector runtime issues. Trigger this skill when the user asks "Set up Inspecto in this project" or similar queries.

Deep code quality review for the inspecto monorepo. Use this skill whenever the user wants to review, audit, or assess the quality of code in the inspecto project — even if they just say "check this file", "is this well written", "review my implementation", or "does this follow the architecture?". Accepts a file path (e.g. packages/core/src/client/component.ts) or a package directory (e.g. packages/unplugin). Produces a structured report covering architecture, implementation quality, modularity, TypeScript safety, and a scored verdict. Trigger on: /review-code, "review this", "check code quality", "audit this file", "is this good code", "does this follow the pattern", "code review".

Analyze the parameter signature of a specific VSCode extension command by reverse-engineering the minified extension.js source code. Given an extension ID and a command name, extracts the registerCommand callback's formal parameters, infers types from runtime type-checking patterns (typeof, Array.isArray), and checks URI handlers for human-readable parameter names. Use when the user asks: what parameters does a command accept, how to call executeCommand with arguments, what's the signature of a specific extension command, reverse-engineer command parameters. Run list-commands first to discover available commands, then use this skill to deep-dive into specific ones.

Extract raw source code context around a specific VSCode extension command's registerCommand call. Outputs the surrounding N characters of minified code for manual inspection. Use when the user wants to see the actual source code around a command registration, needs to understand the internal implementation details that automated analysis missed, or wants to trace how a command interacts with other parts of the extension. This is the low-level "grep" equivalent — for structured analysis, use analyze-params instead.

List all commands registered by a VSCode extension, including hidden ones not declared in package.json. Given an extension ID (e.g. anthropic.claude-code), finds the installed extension, extracts declared commands from package.json and runtime-registered commands from extension.js. Use when the user asks: what commands does an extension have, list extension commands, find hidden commands, discover undocumented commands of a VSCode extension.