ln-750-commands-generator
npx machina-cli add skill levnikolaevich/claude-code-skills/ln-750-commands-generator --openclawPaths: File paths (
shared/,references/,../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.
ln-750-commands-generator
Type: L2 Domain Coordinator Category: 7XX Project Bootstrap Parent: ln-700-project-bootstrap
Generates .claude/commands/ with project-specific Claude Code commands.
Overview
| Aspect | Details |
|---|---|
| Input | Project structure, tech stack |
| Output | .claude/commands/*.md files |
| Worker | ln-751-command-templates |
Workflow
- Analyze project structure and detect tech stack
- Extract variables (paths, ports, frameworks)
- Delegate to ln-751 with template name and variables
- Verify generated commands exist
Generated Commands
| Command | Purpose | Condition |
|---|---|---|
| refresh_context.md | Restore project context | Always |
| refresh_infrastructure.md | Restart services | Always |
| build-and-test.md | Full verification | Always |
| ui-testing.md | UI tests with Playwright | If Playwright detected |
| deploy.md | Deployment workflow | If CI/CD config exists |
| database-ops.md | Database operations | If database detected |
Variables Extracted
| Variable | Source | Example |
|---|---|---|
{{PROJECT_NAME}} | package.json / .csproj | "my-app" |
{{TECH_STACK}} | Auto-detected | "React + .NET + PostgreSQL" |
{{FRONTEND_ROOT}} | Directory scan | "src/frontend" |
{{BACKEND_ROOT}} | Directory scan | "src/MyApp.Api" |
{{FRONTEND_PORT}} | vite.config / package.json | "3000" |
{{BACKEND_PORT}} | launchSettings.json | "5000" |
Templates and full variable list: see ln-751-command-templates/references/
Detection Logic
Frontend: vite.config.ts, package.json (react/vue/angular) Backend: *.csproj with Web SDK, or express/fastapi in deps Database: docker-compose.yml postgres/mysql, or connection strings Playwright: playwright.config.ts or @playwright/test in deps CI/CD: .github/workflows/, azure-pipelines.yml, Dockerfile
Critical Rules
- Detect before generate: Only create commands for detected stack components (no empty templates)
- Variable completeness: All
{{VARIABLE}}placeholders must be resolved before delegation - Delegate via Task: All template rendering goes through ln-751 with context isolation
- No hardcoded paths: All paths derived from project structure analysis, not assumptions
Definition of Done
- Project structure analyzed and tech stack detected
- Variables extracted (project name, ports, roots, stack)
- Commands delegated to ln-751 with correct template name and variables
- All generated
.claude/commands/*.mdfiles verified to exist - No unresolved
{{VARIABLE}}placeholders remain in output
Reference Files
- Variables reference: references/variables_reference.md
- Questions: references/questions_commands.md
Version: 2.0.0 Last Updated: 2026-01-10
Source
git clone https://github.com/levnikolaevich/claude-code-skills/blob/master/ln-750-commands-generator/SKILL.mdView on GitHub Overview
Generates project-specific .claude/commands/*.md files for Claude Code. It analyzes the project structure and tech stack, extracts key variables, then delegates rendering to ln-751-command-templates to produce ready-to-use command docs.
How This Skill Works
The skill analyzes the project structure to detect frontend/backend stacks and relevant components. It extracts variables (like project name, roots, ports, and tech stack), then delegates rendering to ln-751-command-templates with the chosen template and variables. Finally, it verifies that the generated .claude/commands/*.md files exist and contain no unresolved placeholders.
When to Use It
- Starting a new project bootstrap and generating initial Claude Code commands
- Working on a monorepo with shared, references, and ln-* folders needing project-specific commands
- When Playwright is detected and ui-testing commands are needed
- When CI/CD configuration exists and deployment-related commands should be generated
- When a database is detected and database-ops commands are required
Quick Start
- Step 1: Analyze the project structure and detect the tech stack (frontend, backend, database, labs like Playwright, CI/CD).
- Step 2: Extract variables (project name, ROOT paths, ports, stack) from the project files and scans.
- Step 3: Delegate to ln-751-command-templates with the chosen template and variables; verify the .claude/commands/*.md files exist.
Best Practices
- Detect and validate stack components before generating commands; avoid empty templates
- Ensure all {{VARIABLE}} placeholders are resolved before delegation to avoid incomplete outputs
- Delegate rendering through ln-751 with context isolation and the correct template name
- Derive all paths from actual project structure; do not hardcode paths
- Verify the generated .claude/commands/*.md files exist and are syntactically correct
Example Use Cases
- A full-stack app with React frontend, .NET backend, and PostgreSQL detected; all commands like refresh_context.md, refresh_infrastructure.md, build-and-test.md, ui-testing.md, deploy.md, and database-ops.md are generated
- A project where Playwright is detected triggers generation of ui-testing.md alongside other standard commands
- A repository with CI/CD workflows present leads to generation of deploy.md and related deployment commands
- A database-backed application results in generation of database-ops.md and relevant config guidance
- A monorepo with shared and ln-* folders yields project-specific commands tailored to the detected structure without empty templates
