ar4mirez/ralph
internal/builtins/content/ralph/SKILL.md
Ralph methodology — Samuel's default iteration loop. Plan, edit, verify, reflect; repeat until quality checks pass or max iterations is reached. Use when the user asks Samuel to "drive" a task autonomously, run a TDD loop, or apply the default methodology body. Bodies arrive in Milestone 4 (PRD 0004); this placeholder exists so the embedded built-ins directory is non-empty after `samuel init`.
testing
Updated May 13, 2026
$ install --global
skillsauthnpx skillsauth add ar4mirez/samuel ralphInstall 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: May 13, 2026, 3:36 AM177.9s1 file scanned
SKILL.md
- name:
- ralph
- description:
- |
- license:
- MIT
- author:
- samuel
- version:
- 0.1.0
- category:
- methodology
- kind:
- builtin
Ralph Methodology (placeholder)
Ralph is Samuel's default methodology — a small, opinionated loop that plans, edits, verifies, and reflects on each iteration until quality checks pass.
The full executable body lands with PRD 0004. This file is the manifest
the framework ships so samuel doctor reports a healthy built-in tree
after a fresh samuel init.
Loop
- Plan — break the request into a short ordered task list.
- Edit — make the smallest change that moves the plan forward.
- Verify — run the configured quality checks (tests, linters).
- Reflect — adjust the plan based on what verify revealed.
Stop when every task is done, every quality check passes, or
max_iterations is reached. Hand control back to the user otherwise.
Configuration
Defaults live in samuel.toml [methodology.ralph]:
agent— coding assistant the loop drives (default:claude)max_iterations— safety brake (default: 25)quality_checks— commands the loop must pass before stopping
Related Skills
ar4mirez/zig-guide
development
VerifiedTrustedCommunity
Zig language guardrails, patterns, and best practices for AI-assisted development. Use when working with Zig files (.zig), build.zig, or when the user mentions Zig. Provides comptime patterns, allocator conventions, C interop guidelines, and testing standards specific to this project's coding standards.
8SKILL.mdUpdated Apr 30, 2026
ar4mirez/wordpress
tools
VerifiedTrustedCommunity
WordPress framework guardrails, patterns, and best practices for AI-assisted development. Use when working with WordPress projects, or when the user mentions WordPress. Provides theme development, plugin architecture, REST API, blocks, and security guidelines.
8SKILL.mdUpdated Apr 30, 2026
ar4mirez/webapp-testing
tools
VerifiedTrustedCommunity
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. Use when testing web apps, automating browser interactions, or debugging frontend issues.
8SKILL.mdUpdated Apr 30, 2026
ar4mirez/web-artifacts-builder
tools
VerifiedTrustedCommunity
Suite of tools for creating elaborate, multi-component web applications using modern frontend technologies (React, Tailwind CSS, shadcn/ui). Use for complex projects requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX pages.
8SKILL.mdUpdated Apr 30, 2026