Make AI coding agents smarter. Type-aware code search, documentation standards, development conventions. CLI + installable skills for Claude, Cursor, Copilot.
# @plaited/development-skills [](https://www.npmjs.com/package/@plaited/development-skills) [](https://github.com/plaited/development-skills/actions/workflows/ci.yml) [](https://opensource.org/licenses/ISC) > TypeScript LSP tools and AI agent skills for modern development workflows ## Examples ```bash # Find where a type is defined bunx @plaited/development-skills lsp-find UserConfig # Get type info at cursor position (line 25, column 10) bunx @plaited/development-skills lsp-hover src/app.ts 25 10 # Find all usages of a symbol bunx @plaited/development-skills lsp-refs src/types.ts 15 12 # Validate your AI agent skills bunx @plaited/development-skills validate-skill .cursor/skills # Scaffold development rules for your project bunx @plaited/development-skills scaffold-rules ``` ## Why LSP? Text search finds strings. LSP finds *meaning*. ```bash # Text search: finds "Config" in comments, strings, everywhere grep -r "Config" src/ # LSP search: finds the actual Config type and its usages bunx @plaited/development-skills lsp-find Config ``` LSP understands re-exports, aliases, and type relationships. ## Install for AI Agents ```bash npx skills add plaited/development-skills # or bunx skills add plaited/development-skills ``` ## Commands | Command | What it does | |---------|--------------| | `lsp-hover` | Type info at position | | `lsp-find` | Symbol search | | `lsp-refs` | Find references | | `lsp-analyze` | Batch file analysis | | `validate-skill` | Validate AgentSkills | | `scaffold-rules` | Scaffold dev rules | ## Skills Included - **typescript-lsp** - LSP integration for AI agents - **code-documentation** - TSDoc workflow and standards - **validate-skill** - Skill validation - **scaffold-rules** - Development rules scaffolding #
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.