rlm-init
25Command
Command "rlm-init" from spideynolove/claude-dotfiles, covering rlm-init (prompt template), usage pattern, script (recommended), python (windows/macos/linux) and windows powershell.
Command
Command "rlm-init" from spideynolove/claude-dotfiles, covering rlm-init (prompt template), usage pattern, script (recommended), python (windows/macos/linux) and windows powershell.
Command
Command "rlm-status" from spideynolove/claude-dotfiles, covering rlm-status (prompt template), usage pattern, script (recommended), python (windows/macos/linux) and windows powershell.
Skill Claude CodeCodex
Use when RLM requirement involves debugging a bug, test failure, or unexpected behavior. Insert Phase 1.5 between Phase 1 and Phase 2 to perform systematic root cause analysis before attempting any fixes. Trigger phrases: "debug", "investigate", "failing tests", "crash", "root cause".
Skill Claude CodeCodex
Master skill for parallel subagent-driven execution with automatic fallback to single-agent sequential mode. Use when implementing plans with multiple independent sub-phases (SP1, SP2...) to dispatch parallel subagents, or when requiring code review between implementation and testing. Trigger phrases: "parallelize"…
Skill Claude CodeCodex
Use when implementing any code in RLM Phase 3. Enforces strict RED-GREEN-REFACTOR discipline with The Iron Law - no production code without a failing test first. Trigger phrases: "implement this", "add feature", "fix bug", "write a failing test", "TDD".
Skill Claude CodeCodex
Use when starting any RLM requirement to set up an isolated git worktree. REQUIRED before Phase 1 - creates isolated workspace, verifies clean test baseline, and prevents main branch pollution. Trigger phrases: "create worktree", "worktree isolation", "set up worktree", "do not work on main".
Skill Claude CodeCodex
/home/hung/.claude/skills/vue-enterprise/SKILL.md.
Command Claude Code
Delegate task with intelligent profile selection [AUTO ENHANCE].
Command Claude Code
Monitor GitHub Actions CI status and track runs until completion.
Command Claude Code
Generate a conventional commit message from staged changes (clipboard only, no git commands).
Command Claude Code
Create detailed implementation plans through interactive research and iteration.
Command Claude Code
Analyze code for design patterns and SOLID principles violations.
Command Claude Code
Detect the project type from file-presence signals and generate developer roles. No LLM inference — deterministic file checks only.
Command Claude Code
Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.
Command Claude Code
Explain how code works with detailed analysis, flow, and examples.
Command Claude Code
Post-mortem investigation for stuck or failed workflows — read-only diagnostic.
Command Claude Code
Implement an approved plan phase-by-phase with checkbox tracking and human gates.
Command Claude Code
Generate a CLAUDE.md file for the current project using an external AI CLI.
Command Claude Code
Iterate on an existing implementation plan with targeted research and surgical edits.
Command Claude Code
Extract reusable patterns from the current session and save them as skills.
Command Claude Code
Start a managed autonomous loop pattern with safety defaults.
Command Claude Code
Inspect active loop state, progress, and failure signals.
Command Claude Code
Spawn the codebase-analyst agent to build a persistent knowledge graph for the current project into .aim/memory.jsonl.
Command Claude Code
Refactor code safely with SOLID scoring and technical debt quantification.