Auto-detect project tech stacks (React, Vue, Express, Django, etc.). Recognize package managers and configuration patterns. Use when starting work on any project, analyzing dependencies, or providing framework-specific guidance.
/plugin marketplace add rsmdt/the-startup/plugin install team@the-startupThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/framework-signatures.mdCheck for package manager indicators in the project root:
| File | Package Manager | Ecosystem |
|---|---|---|
package-lock.json | npm | Node.js |
yarn.lock | Yarn | Node.js |
pnpm-lock.yaml | pnpm | Node.js |
bun.lockb | Bun | Node.js |
requirements.txt | pip | Python |
Pipfile.lock | pipenv | Python |
poetry.lock | Poetry | Python |
uv.lock | uv | Python |
Cargo.lock | Cargo | Rust |
go.sum | Go Modules | Go |
Gemfile.lock | Bundler | Ruby |
composer.lock | Composer | PHP |
Examine root-level configuration files for framework indicators:
package.json - Check dependencies and devDependencies for framework packagespyproject.toml - Check [project.dependencies] or [tool.poetry.dependencies]next.config.js, vite.config.ts, angular.json, etc.Identify framework conventions:
app/ or src/app/ - Next.js App Router, Angularpages/ - Next.js Pages Router, Nuxt.jscomponents/ - React/Vue component-based architectureroutes/ - Remix, SvelteKitviews/ - Django, Rails, Laravelcontrollers/ - MVC frameworks (Rails, Laravel, NestJS)Apply detection patterns from the framework signatures reference.
START
|
v
[Check lock files] --> Identify package manager
|
v
[Read manifest] --> package.json / pyproject.toml / Cargo.toml
|
v
[Check dependencies] --> Match against known frameworks
|
v
[Check config files] --> Framework-specific configuration
|
v
[Verify directory structure] --> Confirm framework conventions
|
v
[Output] --> Framework, version, package manager, key patterns
When reporting detected framework, include:
See references/framework-signatures.md for comprehensive detection patterns for all major frameworks.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.