pradeepmouli/template-initialization
.agents/skills/template-initialization/SKILL.md
Initialize a new project from template-ts non-interactively. Use when the user wants to set up a fresh repository from the template, customize project metadata (name, author, description), configure package scope, and optionally remove example packages/tests. This automates the entire scripts/init-template.sh workflow without manual prompts.
$ install --global
skillsauthnpx skillsauth add pradeepmouli/lspeasy template-initializationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 4:51 AM6.5s1 file scanned
SKILL.md
- name:
- template-initialization
- description:
- Initialize a new project from template-ts non-interactively. Use when the user wants to set up a fresh repository from the template, customize project metadata (name, author, description), configure package scope, and optionally remove example packages/tests. This automates the entire scripts/init-template.sh workflow without manual prompts.
Template Initialization
Automate project initialization from template-ts by driving the interactive script non-interactively.
Workflow
- Gather inputs - Ask user for required fields (project name, author, description) and optional fields (email, repo URL, scope, cleanup preferences)
- Validate environment - Check Node.js >= 20, pnpm >= 10, and scripts are executable
- Execute initialization - Run init script with piped answers
- Verify setup - Run lint and tests, report results
Required Inputs
Collect these from the user before proceeding:
project_name- Project name (e.g., "my-awesome-app")author_name- Author name (e.g., "Jane Doe")description- Project description
Optional (use defaults if not provided):
author_email- Author email (default: "")repository_url- Repository URL (default: "")package_scope- Package scope (default: "company")remove_example_packages- Remove example packages? (default: "y")remove_example_tests- Remove example tests? (default: "y")remove_example_e2e- Remove E2E tests? (default: "y")replace_template_initialization- Replace TEMPLATE_INITIALIZATION.md? (default: "y")
Execution
Make scripts executable and pipe answers to init script:
chmod +x scripts/*.sh
printf '%s\n' \
"$project_name" \
"$author_name" \
"$author_email" \
"$description" \
"$repository_url" \
y \
"$package_scope" \
"$remove_example_packages" \
"$remove_example_tests" \
"$remove_example_e2e" \
"$replace_template_initialization" \
| scripts/init-template.sh
Note: The 6th line (y) confirms to proceed after showing the configuration summary.
Post-Initialization
Run validation commands:
pnpm run lint
pnpm test
What Gets Updated
package.json- Project metadata, author, description, repositoryREADME.md- Generated with project detailsAGENTS.md- Generated with project name and agent guidancescripts/TEMPLATE_INITIALIZATION.md- Optionally replaced with starter guide- Example packages/tests - Optionally removed based on user choices
- Git repository - Initialized with initial commit if not already present
Deliverables
Report to user:
- Configuration summary (inputs used)
- Commands executed
- Lint results
- Test results
- Location of updated files
Related Skills
pradeepmouli/lsp-refactor
tools
VerifiedTrustedCommunity
Use for ANY rename, file-move, or move-symbol refactor — especially rename-heavy work across multiple files. Claude Code's built-in LSP tool is READ-ONLY (find references, but no rename / file-move / move-symbol). Hand-editing those refactors silently misses re-exports, aliased imports, type-only imports, and {@link} doc references. This skill drives a real language server via the `lspeasy` CLI to apply a correct WorkspaceEdit that catches every reference. Trigger when the user asks to rename a function/class/variable/type project-wide, move a file and fix its importers, or pull a symbol out into another module.
2SKILL.mdUpdated Jun 3, 2026
pradeepmouli/lspeasy-core
tools
VerifiedTrustedCommunity
Documentation site for lspeasy Use when: You are building a browser-based LSP client, a WebSocket-backed language....
2SKILL.mdUpdated Apr 17, 2026
pradeepmouli/lspeasy-client
tools
VerifiedTrustedCommunity
Documentation site for lspeasy Use when: You are implementing a custom client layer and need the same validation....
2SKILL.mdUpdated Apr 17, 2026
pradeepmouli/lspeasy
tools
VerifiedTrustedCommunity
Use when working with lspeasy (client, core, server). Covers: lsp, language-server-protocol, lsp-client, language-client, jsonrpc, transport, lsp-server, language-server.
1SKILL.mdUpdated Apr 25, 2026